AIM:To investigate the performance of a new software-based colonoscopy quality assessment system.METHODS:The software-based system employs a novel image processing algorithm which detects the levels of image clarity,w...AIM:To investigate the performance of a new software-based colonoscopy quality assessment system.METHODS:The software-based system employs a novel image processing algorithm which detects the levels of image clarity,withdrawal velocity,and level of the bowel preparation in a real-time fashion from live video signal.Threshold levels of image blurriness and the withdrawal velocity below which the visualization could be considered adequate have initially been determined arbitrarily by review of sample colonoscopy videos by two experienced endoscopists.Subsequently,an overall colonoscopy quality rating was computed based on the percentage of the withdrawal time with adequate visualization(scored 1-5;1,when the percentage was 1%-20%;2,when the percentage was 21%-40%,etc.).In order to test the proposed velocity and blurriness thresholds,screening colonoscopy withdrawal videos from a specialized ambulatory colon cancer screening center were collected,automatically processed and rated.Quality ratings on the withdrawal were compared to the insertion in the same patients.Then,3 experienced endoscopists reviewed the collected videos in a blinded fashion and rated the overall quality of each withdrawal(scored 1-5;1,poor;3,average;5,excellent) based on 3 major aspects:image quality,colon preparation,and withdrawal velocity.The automated quality ratings were compared to the averaged endoscopist quality ratings using Spearman correlation coefficient.RESULTS:Fourteen screening colonoscopies were assessed.Adenomatous polyps were detected in 4/14(29%) of the collected colonoscopy video samples.As a proof of concept,the Colometer software rated colonoscope withdrawal as having better visualization than the insertion in the 10 videos which did not have any polyps(average percent time with adequate visualization:79% ± 5% for withdrawal and 50% ± 14% for insertion,P < 0.01).Withdrawal times during which no polyps were removed ranged from 4-12 min.The median quality rating from the automated system and the reviewers was 3.45 [interquartile range(IQR),3.1-3.68] and 3.00(IQR,2.33-3.67) respectively for all colonoscopy video samples.The automated rating revealed a strong correlation with the reviewer's rating(ρ coefficient= 0.65,P = 0.01).There was good correlation of the automated overall quality rating and the mean endoscopist withdrawal speed rating(Spearman r coefficient= 0.59,P = 0.03).There was no correlation of automated overall quality rating with mean endoscopists image quality rating(Spearman r coefficient= 0.41,P = 0.15).CONCLUSION:The results from a novel automated real-time colonoscopy quality feedback system strongly agreed with the endoscopists' quality assessments.Further study is required to validate this approach.展开更多
High resolution cameras and multi camera systems are being used in areas of video surveillance like security of public places, traffic monitoring, and military and satellite imaging. This leads to a demand for computa...High resolution cameras and multi camera systems are being used in areas of video surveillance like security of public places, traffic monitoring, and military and satellite imaging. This leads to a demand for computational algorithms for real time processing of high resolution videos. Motion detection and background separation play a vital role in capturing the object of interest in surveillance videos, but as we move towards high resolution cameras, the time-complexity of the algorithm increases and thus fails to be a part of real time systems. Parallel architecture provides a surpass platform to work efficiently with complex algorithmic solutions. In this work, a method was proposed for identifying the moving objects perfectly in the videos using adaptive background making, motion detection and object estimation. The pre-processing part includes an adaptive block background making model and a dynamically adaptive thresholding technique to estimate the moving objects. The post processing includes a competent parallel connected component labelling algorithm to estimate perfectly the objects of interest. New parallel processing strategies are developed on each stage of the algorithm to reduce the time-complexity of the system. This algorithm has achieved a average speedup of 12.26 times for lower resolution video frames(320×240, 720×480, 1024×768) and 7.30 times for higher resolution video frames(1360×768, 1920×1080, 2560×1440) on GPU, which is superior to CPU processing. Also, this algorithm was tested by changing the number of threads in a thread block and the minimum execution time has been achieved for 16×16 thread block. And this algorithm was tested on a night sequence where the amount of light in the scene is very less and still the algorithm has given a significant speedup and accuracy in determining the object.展开更多
基金Supported by The Natural Sciences and Engineering Research Council of Canada (Partially)
文摘AIM:To investigate the performance of a new software-based colonoscopy quality assessment system.METHODS:The software-based system employs a novel image processing algorithm which detects the levels of image clarity,withdrawal velocity,and level of the bowel preparation in a real-time fashion from live video signal.Threshold levels of image blurriness and the withdrawal velocity below which the visualization could be considered adequate have initially been determined arbitrarily by review of sample colonoscopy videos by two experienced endoscopists.Subsequently,an overall colonoscopy quality rating was computed based on the percentage of the withdrawal time with adequate visualization(scored 1-5;1,when the percentage was 1%-20%;2,when the percentage was 21%-40%,etc.).In order to test the proposed velocity and blurriness thresholds,screening colonoscopy withdrawal videos from a specialized ambulatory colon cancer screening center were collected,automatically processed and rated.Quality ratings on the withdrawal were compared to the insertion in the same patients.Then,3 experienced endoscopists reviewed the collected videos in a blinded fashion and rated the overall quality of each withdrawal(scored 1-5;1,poor;3,average;5,excellent) based on 3 major aspects:image quality,colon preparation,and withdrawal velocity.The automated quality ratings were compared to the averaged endoscopist quality ratings using Spearman correlation coefficient.RESULTS:Fourteen screening colonoscopies were assessed.Adenomatous polyps were detected in 4/14(29%) of the collected colonoscopy video samples.As a proof of concept,the Colometer software rated colonoscope withdrawal as having better visualization than the insertion in the 10 videos which did not have any polyps(average percent time with adequate visualization:79% ± 5% for withdrawal and 50% ± 14% for insertion,P < 0.01).Withdrawal times during which no polyps were removed ranged from 4-12 min.The median quality rating from the automated system and the reviewers was 3.45 [interquartile range(IQR),3.1-3.68] and 3.00(IQR,2.33-3.67) respectively for all colonoscopy video samples.The automated rating revealed a strong correlation with the reviewer's rating(ρ coefficient= 0.65,P = 0.01).There was good correlation of the automated overall quality rating and the mean endoscopist withdrawal speed rating(Spearman r coefficient= 0.59,P = 0.03).There was no correlation of automated overall quality rating with mean endoscopists image quality rating(Spearman r coefficient= 0.41,P = 0.15).CONCLUSION:The results from a novel automated real-time colonoscopy quality feedback system strongly agreed with the endoscopists' quality assessments.Further study is required to validate this approach.
文摘High resolution cameras and multi camera systems are being used in areas of video surveillance like security of public places, traffic monitoring, and military and satellite imaging. This leads to a demand for computational algorithms for real time processing of high resolution videos. Motion detection and background separation play a vital role in capturing the object of interest in surveillance videos, but as we move towards high resolution cameras, the time-complexity of the algorithm increases and thus fails to be a part of real time systems. Parallel architecture provides a surpass platform to work efficiently with complex algorithmic solutions. In this work, a method was proposed for identifying the moving objects perfectly in the videos using adaptive background making, motion detection and object estimation. The pre-processing part includes an adaptive block background making model and a dynamically adaptive thresholding technique to estimate the moving objects. The post processing includes a competent parallel connected component labelling algorithm to estimate perfectly the objects of interest. New parallel processing strategies are developed on each stage of the algorithm to reduce the time-complexity of the system. This algorithm has achieved a average speedup of 12.26 times for lower resolution video frames(320×240, 720×480, 1024×768) and 7.30 times for higher resolution video frames(1360×768, 1920×1080, 2560×1440) on GPU, which is superior to CPU processing. Also, this algorithm was tested by changing the number of threads in a thread block and the minimum execution time has been achieved for 16×16 thread block. And this algorithm was tested on a night sequence where the amount of light in the scene is very less and still the algorithm has given a significant speedup and accuracy in determining the object.
