Abstract
To decrease colon polyp miss-rate during colonoscopy, a real-time detection system with high accuracy is needed. Recently, there have been many efforts to develop models for real-time polyp detection, but work is still required to develop real-time detection algorithms with reliable results. We use single-shot feed-forward fully convolutional neural networks (F-CNN) to develop an accurate real-time polyp detection system. F-CNNs are usually trained on binary masks for object segmentation. We propose the use of 2D Gaussian masks instead of binary masks to enable these models to detect different types of polyps more effectively and efficiently and reduce the number of false positives. The experimental results showed that the proposed 2D Gaussian masks are efficient for detection of flat and small polyps with unclear boundaries between background and polyp parts. The masks make a better training effect to discriminate polyps from the polyp-like false positives. The proposed method achieved state-of-the-art results on two polyp datasets. On the ETIS-LARIB dataset we achieved 86.54% recall, 86.12% precision, and 86.33% F1-score, and on the CVC-ColonDB we achieved 91% recall, 88.35% precision, and F1-score 89.65%.
Highlights
Colorectal cancer (CRC) is the third most common cause of cancer mortality for men and women globally, and CRC is the overall second leading cause of cancer-related death (Bray et al, 2018)
Many false positives (FP) could be removed from the final results, because the confidence values of the predicted masks were less than the threshold value which we set to be 0.5
Many other FPs were eliminated because Gaussian masks were successful for reduction of the effect of outer edges during training
Summary
Colorectal cancer (CRC) is the third most common cause of cancer mortality for men and women globally, and CRC is the overall second leading cause of cancer-related death (Bray et al, 2018). Most cases of CRC are initially non-cancerous called polyps. If polyps are left untreated, they may become malignant and potentially life-threatening cancer (Arnold et al, 2017). Early detection and removal of precancerous polyps in the colon are crucial for prevention. Colonoscopy is the most sensitive method for colon screening. It is effective for detection of colonic lesions and polyps of any size, and allows removal of lesions during the procedure. Colonoscopy is an operator-dependent procedure and prone to human errors. Polyp miss rate is reported to be as high as 22%-28% in certain cases (Leufkens et al, 2012). A number of supportive systems have been proposed to help clinicians detect polyps and tumors during colonoscopy, reducing polyp miss-rate and optimize the screening procedure
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
