Shahed Khan, University of Saskatchewan Rate Professors

Shahed Khan

Courses3
Reviews4

Rate This Professor

School: University of Saskatchewan
Campus:
Department: Statistics
Email address: Join to see
Phone: Join to see
Location:
Saskatoon, SK
Dates at University of Saskatchewan: January 2012 - January 2014
Office Hours: Join to see

Social Profile:

Join to see

4 Reviews Pending Approval

Biography

University of Saskatchewan - Statistics

Experience

University of British Columbia Electrical and Computer Engineering
Graduate Teaching Assistant
Course: CPEN 314: Digital System and Microcomputers
Course Teacher: Dr. Jesús Calviño-Fraga
University of British Columbia Electrical and Computer Engineering
Graduate Teaching Assistant
Course: EECE 571R: Introduction to Robotics
Course Instructor: Prof. Tim Salcudean
University of Saskatchewan
Graduate Research Assistant
Conducting independent research to develop image compression algorithm for wireless capsule endoscopy system, participating in collaborative research to extend and commercialize the use of wireless capsule endoscopy system in non-human patient such as horse and dog, designing image enhancement algorithm to improve the performance of automated computer aided detection system, organizing laboratory demonstration to the collaborators.
University of Saskatchewan
Graduate Teaching Assistant
CME 331: Microprocessor based embedded system: designing laboratory manual, instructing students, debugging errors in both code and hardware connection, evaluating class performance, lab reports and assignments and giving suggestion to improve the course.
Electrical and Computer Engineering Graduate Student Association (ECEGSA)
Vice President Academic
Shahed worked at Electrical and Computer Engineering Graduate Student Association (ECEGSA) as a Vice President Academic
The University of British Columbia
Graduate Research Assistant
Shahed worked at The University of British Columbia as a Graduate Research Assistant

Education

University of British Columbia Electrical and Computer Engineering
Doctor of Philosophy (Ph.D.)
Electrical and Computer Engineering
Bangladesh University of Engineering and Technology
Bachelor of Science (B.Sc.)
Electrical and Electronics Engineering
Undergraduate Thesis Title: " A complete analytical model of a clamped edge square diaphragm capacitive pressure sensor"
Dean's List Scholarship

Awarded in every year of my undergraduate study as a recognition of outstanding academic performance
University of Saskatchewan
Master of Science (M.Sc.)
Electrical and Electronics Engineering
My research focuses on efficient embedded system design for wearable medical systems, image processing, and encoding. I have been awarded the Department Scholarship for my excellent performance in academics and research in January 2015.
University of Saskatchewan
Graduate Research Assistant

Conducting independent research to develop image compression algorithm for wireless capsule endoscopy system, participating in collaborative research to extend and commercialize the use of wireless capsule endoscopy system in non-human patient such as horse and dog, designing image enhancement algorithm to improve the performance of automated computer aided detection system, organizing laboratory demonstration to the collaborators.
University of Saskatchewan
Graduate Teaching Assistant

CME 331: Microprocessor based embedded system: designing laboratory manual, instructing students, debugging errors in both code and hardware connection, evaluating class performance, lab reports and assignments and giving suggestion to improve the course.
International Tuition Award
Four Year Fellowship
University of British Columbia Electrical and Computer Engineering
Graduate Teaching Assistant

Course: CPEN 314: Digital System and Microcomputers Course Teacher: Dr. Jesús Calviño-Fraga
University of British Columbia Electrical and Computer Engineering
Graduate Teaching Assistant

Course: EECE 571R: Introduction to Robotics Course Instructor: Prof. Tim Salcudean

Publications

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Feature selection using modified ant colony optimization for wireless capsule endoscopy
Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE Annual
In this study, a modified ant colony optimization algorithm has been proposed to find a feature subset most relevant to the classification task. The algorithm incorporates a new heuristic information component based on classification accuracy. The proposed methodology has been applied in a multiclass classification problem of capsule endoscopic images, where image regions will be classified as bleeding, non-bleeding and uninformative regions. 75 dimensional features extracted from five color spaces have been investigated in the experiments. The proposed MACO algorithm efficiently finds the optimum feature subset over the five color spaces including RGB, HSV, Lab, YCbCr, and CMYK, resulting in a feature subset outperforming those obtained individually from each color space. The comparative study with state-of-the-art methods of feature selection demonstrated that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Feature selection using modified ant colony optimization for wireless capsule endoscopy
Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE Annual
In this study, a modified ant colony optimization algorithm has been proposed to find a feature subset most relevant to the classification task. The algorithm incorporates a new heuristic information component based on classification accuracy. The proposed methodology has been applied in a multiclass classification problem of capsule endoscopic images, where image regions will be classified as bleeding, non-bleeding and uninformative regions. 75 dimensional features extracted from five color spaces have been investigated in the experiments. The proposed MACO algorithm efficiently finds the optimum feature subset over the five color spaces including RGB, HSV, Lab, YCbCr, and CMYK, resulting in a feature subset outperforming those obtained individually from each color space. The comparative study with state-of-the-art methods of feature selection demonstrated that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System
2016 International Joint Conference on Neural Networks (IJCNN)
Wireless capsule endoscopy (WCE) plays a significant role in the non-invasive small intestine screening for obscure gastrointestinal bleeding detection. However, the task of reviewing 60,000 frames to detect the bleeding encumbers the clinician, leading to visual fatigue and false diagnosis. In this paper, we propose a color feature based bleeding detection system with feature selection using a modified ant colony optimization (MACO) algorithm. We have utilized the feature selection capability of MACO algorithm to find the optimum feature subset over the color space of RGB and HSV, which provided a classifier that outperforms the classifier formed from RGB and HSV features individually. Comprehensive experimental results reveal that the proposed MACO algorithm can detect the optimal feature subset with performance comparable to exhaustive search in case of individual classifier from RGB and HSV requiring 2% of the computational time compared to exhaustive search. The comparative study of feature selection showed that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Feature selection using modified ant colony optimization for wireless capsule endoscopy
Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE Annual
In this study, a modified ant colony optimization algorithm has been proposed to find a feature subset most relevant to the classification task. The algorithm incorporates a new heuristic information component based on classification accuracy. The proposed methodology has been applied in a multiclass classification problem of capsule endoscopic images, where image regions will be classified as bleeding, non-bleeding and uninformative regions. 75 dimensional features extracted from five color spaces have been investigated in the experiments. The proposed MACO algorithm efficiently finds the optimum feature subset over the five color spaces including RGB, HSV, Lab, YCbCr, and CMYK, resulting in a feature subset outperforming those obtained individually from each color space. The comparative study with state-of-the-art methods of feature selection demonstrated that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System
2016 International Joint Conference on Neural Networks (IJCNN)
Wireless capsule endoscopy (WCE) plays a significant role in the non-invasive small intestine screening for obscure gastrointestinal bleeding detection. However, the task of reviewing 60,000 frames to detect the bleeding encumbers the clinician, leading to visual fatigue and false diagnosis. In this paper, we propose a color feature based bleeding detection system with feature selection using a modified ant colony optimization (MACO) algorithm. We have utilized the feature selection capability of MACO algorithm to find the optimum feature subset over the color space of RGB and HSV, which provided a classifier that outperforms the classifier formed from RGB and HSV features individually. Comprehensive experimental results reveal that the proposed MACO algorithm can detect the optimal feature subset with performance comparable to exhaustive search in case of individual classifier from RGB and HSV requiring 2% of the computational time compared to exhaustive search. The comparative study of feature selection showed that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Lossless Compression in Bayer Color Filter Array for Capsule Endoscopy
IEEE Access
This paper presents a compression algorithm for color filter array (CFA) images in a wireless capsule endoscopy system. The proposed algorithm consists of a new color space transformation (known as YLMN), a raster-order prediction model, and a single context adaptive Golomb–Rice encoder to encode the residual signal with variable length coding. An optimum reversible color transformation derivation model is presented first, which incorporates a prediction model to find the optimum color transformation. After the color transformation, each color component has been independently encoded with a low complexity raster-order prediction model and Golomb–Rice encoder. The algorithm is implemented using a TSMC 65-nm CMOS process, which shows a reduction in gate count by 38.9% and memory requirement by 71.2% compared with existing methods. Performance assessment using CFA database shows the proposed design can outperform existing lossless and near-lossless compression algorithms by a large margin, which makes it suitable for capsule endoscopy application.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Feature selection using modified ant colony optimization for wireless capsule endoscopy
Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE Annual
In this study, a modified ant colony optimization algorithm has been proposed to find a feature subset most relevant to the classification task. The algorithm incorporates a new heuristic information component based on classification accuracy. The proposed methodology has been applied in a multiclass classification problem of capsule endoscopic images, where image regions will be classified as bleeding, non-bleeding and uninformative regions. 75 dimensional features extracted from five color spaces have been investigated in the experiments. The proposed MACO algorithm efficiently finds the optimum feature subset over the five color spaces including RGB, HSV, Lab, YCbCr, and CMYK, resulting in a feature subset outperforming those obtained individually from each color space. The comparative study with state-of-the-art methods of feature selection demonstrated that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System
2016 International Joint Conference on Neural Networks (IJCNN)
Wireless capsule endoscopy (WCE) plays a significant role in the non-invasive small intestine screening for obscure gastrointestinal bleeding detection. However, the task of reviewing 60,000 frames to detect the bleeding encumbers the clinician, leading to visual fatigue and false diagnosis. In this paper, we propose a color feature based bleeding detection system with feature selection using a modified ant colony optimization (MACO) algorithm. We have utilized the feature selection capability of MACO algorithm to find the optimum feature subset over the color space of RGB and HSV, which provided a classifier that outperforms the classifier formed from RGB and HSV features individually. Comprehensive experimental results reveal that the proposed MACO algorithm can detect the optimal feature subset with performance comparable to exhaustive search in case of individual classifier from RGB and HSV requiring 2% of the computational time compared to exhaustive search. The comparative study of feature selection showed that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Lossless Compression in Bayer Color Filter Array for Capsule Endoscopy
IEEE Access
This paper presents a compression algorithm for color filter array (CFA) images in a wireless capsule endoscopy system. The proposed algorithm consists of a new color space transformation (known as YLMN), a raster-order prediction model, and a single context adaptive Golomb–Rice encoder to encode the residual signal with variable length coding. An optimum reversible color transformation derivation model is presented first, which incorporates a prediction model to find the optimum color transformation. After the color transformation, each color component has been independently encoded with a low complexity raster-order prediction model and Golomb–Rice encoder. The algorithm is implemented using a TSMC 65-nm CMOS process, which shows a reduction in gate count by 38.9% and memory requirement by 71.2% compared with existing methods. Performance assessment using CFA database shows the proposed design can outperform existing lossless and near-lossless compression algorithms by a large margin, which makes it suitable for capsule endoscopy application.
Efficient Color Reproduction Algorithm for Endoscopic Images based on Dynamic Color Map
Journal of Medical and Biological Engineering
Improved visual quality and color information in endoscopic images play an important role in diagnosing various gastrointestinal (GI)-tract-related diseases. This paper presents a grayscale-to-color image reproduction method, which is preceded by a pre-processing scheme, for endoscopic images. The color reproduction is achieved by generating a dictionary-based color mapping from a theme color image and then applying it to the pre-processed grayscale image. The theme color image is chosen from a nearby GI tract location of the input grayscale image so that the generated output color image contains similar color tone. The color map is dynamic as its contents change with the change of the theme image. The proposed method is used on low-contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. The method is also used to colorize grayscale video sequences of wireless capsule endoscopy. Based on the statistic visual representation, the proposed method can better highlight the mucosa structure compared to other methods. The color similarity was verified using the delta E color difference, structure similarity index, mean structure similarity index, and structure and hue similarity. The proposed algorithm has low and linear time complexity, which results in higher execution speed than those of related works. Finally, the quality of the generated color images was verified visually by several professional gastroenterologists, whose mean opinion score is presented.
Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,
SpringerPlus
In this paper, we present a real-time preprocessing algorithm for image enhancement for endoscopic images. A novel dictionary based color mapping algorithm is used for reproducing the color information from a theme image. The theme image is selected from a nearby anatomical location. A database of color endoscopy image for different location is prepared for this purpose. The color map is dynamic as its contents change with the change of the theme image. This method is used on low contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. It can also be applied to enhance the tone of color images. The statistic visual representation and universal image quality measures show that the proposed method can highlight the mucosa structure compared to other methods. The color similarity has been verified using Delta E color difference, structure similarity index, mean structure similarity index and structure and hue similarity. The color enhancement was measured using color enhancement factor that shows considerable improvements. The proposed algorithm has low and linear time complexity, which results in higher execution speed than other related works.
Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
An efficient and automated abnormality detection method can significantly reduce the burden of screening of the enormous visual information resulting from capsule endoscopic procedure. As a pre-processing stage, color enhancement could be useful to improve the image quality and the detection performance. Therefore, in this paper, we have proposed a two-stage automated abnormality detection algorithm. In the first stage, an adaptive color enhancement method based on Retinex theory is applied on the endoscopic images. In the second stage, an efficient salient region detection algorithm is applied to detect the clinically significant regions. The proposed algorithm is applied on a dataset containing images with diverse pathologies. The algorithm can successfully detect a significant percentage of the abnormal regions. From our experiment, it was evident that color enhancement method improves the performance of abnormality detection. The proposed algorithm can achieve a sensitivity of 97.33% and specificity of 79%, higher than state-of-the-art performance.
A complete analytical model for square diaphragm capacitive sensor with clamped edge
2013 8th IEEE International Conference on NEMS
Capacitive Pressure Sensors have been among the most promising MEMS in recent years due to its inherently low power consumption, higher reliability and better performance. A complete analytical model is necessary to accurately determine the effects of sensing variables on the sensor. In this paper, a mathematical model is developed for square diaphragm capacitive sensors, which includes analytical equations for load-deflection characteristic, pull-in voltage and critical distance at pull-in and capacitance. The work is different from the previous ones in the way that it adopts a direct method to solve the governing equations of deflection which gives the load-deflection characteristic without involving any numerical aid and accounts for both small and large deflection. Again, the numerical integration for capacitance calculation has been replaced by an approximate analytical model which reduces the computational effort comparably. Comparison with experimental data reveals excellent accuracy of the model.
An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video
38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
In biomedical applications including classification of endoscopic videos, class imbalance is a common problem arising from the significant difference between the prior probabilities of different classes. In this paper, we investigate the performance of different classifiers for varying training data distribution in case of bleeding detection problem through three experiments. In the first experiment, we analyze the classifier performance for different class distribution with a fixed sized training dataset. The experiment provides the indication of the required class distribution for optimum classification performance. In the second and third experiments, we investigate the effect of both training data size and class distribution on the classification performance. From our experiments, we found that a larger dataset with moderate class imbalance yields better classification performance compared to a small dataset with balanced distribution. Ensemble classifiers are more robust to the variation in training dataset compared to single classifier.
A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images
The Canadian Medical and Biological Engineering Society
Angioectasia is the most common origin of obscure gastrointestinal bleeding (OGIB), constituting 30-40% of the OGIB cases. It consists of dilated, ectatic, tortuous, thin-walled vessels of the mucosa or submucosa, involving small capillaries, veins, and arteries. Angioectasias lesions are mostly located in small bowel, and thus inaccessible to conventional wired endoscopy. Small bowel capsule endoscopy (SBCE), enabling the visualization of the entire small bowel, has become a particularly useful tool in the detection and management of angioectasia. To address the inadequate investigation in the field of automatic detection of angioectasia from capsule endoscopic images, we propose a two-staged saliency-based unsupervised detection algorithm. In the first stage, we construct a saliency map by combining a patch distinctness (PD) map and an Index of Hemoglobin ( IHb) map obtained from original endoscopic images. The PD map is formed using a distance measure which computes the distinctness of image patches compared to an average image patch. The IHb map is formed using index of hemoglobin (IHb) to exploit the characterizing red hue of angioectasias. Finally, the PD map and the IHb map are combined to form the final saliency map. In the second stage, we perform a local maxima search from gradient image obtained from the saliency map to localize the ROIs (region-of-interests) containing angioectasias lesions. The proposed method yields 100% sensitivity and 90.1% accuracy in detecting angioectasia with low computational effort.
Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function
IEEE Transactions on Biomedical Circuits and Systems
Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.
Feature selection using modified ant colony optimization for wireless capsule endoscopy
Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE Annual
In this study, a modified ant colony optimization algorithm has been proposed to find a feature subset most relevant to the classification task. The algorithm incorporates a new heuristic information component based on classification accuracy. The proposed methodology has been applied in a multiclass classification problem of capsule endoscopic images, where image regions will be classified as bleeding, non-bleeding and uninformative regions. 75 dimensional features extracted from five color spaces have been investigated in the experiments. The proposed MACO algorithm efficiently finds the optimum feature subset over the five color spaces including RGB, HSV, Lab, YCbCr, and CMYK, resulting in a feature subset outperforming those obtained individually from each color space. The comparative study with state-of-the-art methods of feature selection demonstrated that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System
2016 International Joint Conference on Neural Networks (IJCNN)
Wireless capsule endoscopy (WCE) plays a significant role in the non-invasive small intestine screening for obscure gastrointestinal bleeding detection. However, the task of reviewing 60,000 frames to detect the bleeding encumbers the clinician, leading to visual fatigue and false diagnosis. In this paper, we propose a color feature based bleeding detection system with feature selection using a modified ant colony optimization (MACO) algorithm. We have utilized the feature selection capability of MACO algorithm to find the optimum feature subset over the color space of RGB and HSV, which provided a classifier that outperforms the classifier formed from RGB and HSV features individually. Comprehensive experimental results reveal that the proposed MACO algorithm can detect the optimal feature subset with performance comparable to exhaustive search in case of individual classifier from RGB and HSV requiring 2% of the computational time compared to exhaustive search. The comparative study of feature selection showed that MACO can provide the most relevant features and improve the performance in terms of accuracy, sensitivity and computational time.
Lossless Compression in Bayer Color Filter Array for Capsule Endoscopy
IEEE Access
This paper presents a compression algorithm for color filter array (CFA) images in a wireless capsule endoscopy system. The proposed algorithm consists of a new color space transformation (known as YLMN), a raster-order prediction model, and a single context adaptive Golomb–Rice encoder to encode the residual signal with variable length coding. An optimum reversible color transformation derivation model is presented first, which incorporates a prediction model to find the optimum color transformation. After the color transformation, each color component has been independently encoded with a low complexity raster-order prediction model and Golomb–Rice encoder. The algorithm is implemented using a TSMC 65-nm CMOS process, which shows a reduction in gate count by 38.9% and memory requirement by 71.2% compared with existing methods. Performance assessment using CFA database shows the proposed design can outperform existing lossless and near-lossless compression algorithms by a large margin, which makes it suitable for capsule endoscopy application.
Efficient Color Reproduction Algorithm for Endoscopic Images based on Dynamic Color Map
Journal of Medical and Biological Engineering
Improved visual quality and color information in endoscopic images play an important role in diagnosing various gastrointestinal (GI)-tract-related diseases. This paper presents a grayscale-to-color image reproduction method, which is preceded by a pre-processing scheme, for endoscopic images. The color reproduction is achieved by generating a dictionary-based color mapping from a theme color image and then applying it to the pre-processed grayscale image. The theme color image is chosen from a nearby GI tract location of the input grayscale image so that the generated output color image contains similar color tone. The color map is dynamic as its contents change with the change of the theme image. The proposed method is used on low-contrast grayscale white light images and raw narrow band images to highlight the vascular and mucosa structures and to colorize the images. The method is also used to colorize grayscale video sequences of wireless capsule endoscopy. Based on the statistic visual representation, the proposed method can better highlight the mucosa structure compared to other methods. The color similarity was verified using the delta E color difference, structure similarity index, mean structure similarity index, and structure and hue similarity. The proposed algorithm has low and linear time complexity, which results in higher execution speed than those of related works. Finally, the quality of the generated color images was verified visually by several professional gastroenterologists, whose mean opinion score is presented.

STAT 111

STAT111 Description

3.3(2)

Level:
Credit hours: 0

STAT 241

STAT241 Description

1.5(1)

Level:
Credit hours: 0

STATS 246

STATS246 Description

4(1)

Level:
Credit hours: 0

Shahed Khan

Shahed Khan

Biography

Experience

University of British Columbia Electrical and Computer Engineering

University of British Columbia Electrical and Computer Engineering

University of Saskatchewan

University of Saskatchewan

Electrical and Computer Engineering Graduate Student Association (ECEGSA)

The University of British Columbia

Education

University of British Columbia Electrical and Computer Engineering

Bangladesh University of Engineering and Technology

University of Saskatchewan

University of Saskatchewan

University of Saskatchewan

University of British Columbia Electrical and Computer Engineering

University of British Columbia Electrical and Computer Engineering

Publications

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Feature selection using modified ant colony optimization for wireless capsule endoscopy

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Feature selection using modified ant colony optimization for wireless capsule endoscopy

Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Feature selection using modified ant colony optimization for wireless capsule endoscopy

Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System

Lossless Compression in Bayer Color Filter Array for Capsule Endoscopy

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Feature selection using modified ant colony optimization for wireless capsule endoscopy

Application of Modied Ant Colony Optimization for Computer Aided Bleeding Detection System

Lossless Compression in Bayer Color Filter Array for Capsule Endoscopy

Efficient Color Reproduction Algorithm for Endoscopic Images based on Dynamic Color Map

Color Reproduction and Processing Algorithm Based on Real-time Mapping for Endoscopic Images,

Unsupervised Abnormality Detection Using Saliency and Retinex based Color Enhancement

A complete analytical model for square diaphragm capacitive sensor with clamped edge

An Empirical Study on the Effect of Imbalanced Data on Bleeding Detection in Endoscopic Video

A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images

Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function