Abstract
Analysis of colonoscopy images plays a significant role in early detection of colorectal cancer. Automated tissue segmentation can be useful for two of the most relevant clinical target applications—lesion detection and classification, thereby providing important means to make both processes more accurate and robust. To automate video colonoscopy analysis, computer vision and machine learning methods have been utilized and shown to enhance polyp detectability and segmentation objectivity. This paper describes a polyp segmentation algorithm, developed based on fully convolutional network models, that was originally developed for the Endoscopic Vision Gastrointestinal Image Analysis (GIANA) polyp segmentation challenges. The key contribution of the paper is an extended evaluation of the proposed architecture, by comparing it against established image segmentation benchmarks utilizing several metrics with cross-validation on the GIANA training dataset. Different experiments are described, including examination of various network configurations, values of design parameters, data augmentation approaches, and polyp characteristics. The reported results demonstrate the significance of the data augmentation, and careful selection of the method’s design parameters. The proposed method delivers state-of-the-art results with near real-time performance. The described solution was instrumental in securing the top spot for the polyp segmentation sub-challenge at the 2017 GIANA challenge and second place for the standard image resolution segmentation task at the 2018 GIANA challenge.
Highlights
Colorectal cancer (CRC) is one of the major causes of cancer incidence and death worldwide; e.g., in the United States, it is the third largest cause of cancer deaths, whereas in Europe, it is the second largest with 243,000 deaths in 2018
Compared to that conference paper, this paper extends the analysis by proving more in-depth evaluation, including added justification for the network architecture, test-time data augmentation, analysis of the cross-validation, results visualization, processing-time, and comparisons with other segmentation methods evaluated on equivalent segmentation problem
FCN8s is is a a well-known fully convolutional network, the is a simplified version of the network from well-known fully convolutional network, the ResFCN is a simplified version of the network from
Summary
Colorectal cancer (CRC) is one of the major causes of cancer incidence and death worldwide; e.g., in the United States, it is the third largest cause of cancer deaths, whereas in Europe, it is the second largest with 243,000 deaths in 2018. Colorectal polyps are generally small, with no strongly distinctive which intelligent systems can play key roles in improving the effectiveness of the CRC screening features At this stage they could be mistaken for other intestinal structures, such as procedures [8]. Lesion segmentation can be used to determine whether there is a polyp-like structure in wrinkles and folds Later, when they evolve, they often get bigger and their morphology changes, the image, assist in becoming polyp detection, accurately delineate the polypin region, which helps withislesion with the features more and distinctive. With new, advanced machine learning methodologies, including the so-called deep learning, it seems conceivable to significantly increase the robustness and effectiveness of colorectal cancer screening, and improve the segmentation accuracy, lesion detectability, and the accuracy of the histological characterization. Compared to that conference paper, this paper extends the analysis by proving more in-depth evaluation, including added justification for the network architecture, test-time data augmentation, analysis of the cross-validation, results visualization, processing-time, and comparisons with other segmentation methods evaluated on equivalent segmentation problem
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.
