{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-comprehensive-study-on-colorectal-polyp","title":"A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation","arxiv_id":"2107.12435","date":"2021-07-26","proceeding":null,"authors":["Debesh Jha","Pia H. Smedsrud","Dag Johansen","Thomas de Lange","Håvard D. Johansen","Pål Halvorsen","Michael A. Riegler"],"abstract":"Colonoscopy is considered the gold standard for detection of colorectal cancer and its precursors. Existing examination methods are, however, hampered by high overall miss-rate, and many abnormalities are left undetected. Computer-Aided Diagnosis systems based on advanced machine learning algorithms are touted as a game-changer that can identify regions in the colon overlooked by the physicians during endoscopic examinations, and help detect and characterize lesions. In previous work, we have proposed the ResUNet++ architecture and demonstrated that it produces more efficient results compared with its counterparts U-Net and ResUNet. In this paper, we demonstrate that further improvements to the overall prediction performance of the ResUNet++ architecture can be achieved by using conditional random field and test-time augmentation. We have performed extensive evaluations and validated the improvements using six publicly available datasets: Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib Polyp DB, ASU-Mayo Clinic Colonoscopy Video Database, and CVC-VideoClinicDB. Moreover, we compare our proposed architecture and resulting model with other State-of-the-art methods. To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation. The experimental results show that applying CRF and TTA improves the performance on various polyp segmentation datasets both on the same dataset and cross-dataset.","url_abs":"https://arxiv.org/abs/2107.12435v1","url_pdf":"https://arxiv.org/pdf/2107.12435v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-comprehensive-study-on-colorectal-polyp","repo_url":"https://github.com/DebeshJha/ResUNet-with-CRF-and-TTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"}],"methods":[{"method_slug":"crf","method_name":"CRF"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/medical-image-segmentation-on-cvc-clinicdb","task":"Medical Image Segmentation","dataset":"CVC-ClinicDB","model":"ResUNet++ + TTA","rank_in_archive_order":42,"of":48,"metrics":{"mean Dice":"0.9020"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc-clinicdb","task":"Medical Image Segmentation","dataset":"CVC-ClinicDB","model":"ResUNet++ + CRF+ TTA","rank_in_archive_order":43,"of":48,"metrics":{"mean Dice":"0.9017"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc-colondb","task":"Medical Image Segmentation","dataset":"CVC-ColonDB","model":"ResUNet++ + TTA","rank_in_archive_order":8,"of":25,"metrics":{"mIoU":"0.8466","mean Dice":"0.8474"},"uses_additional_data":true},{"leaderboard":"/sota/medical-image-segmentation-on-cvc","task":"Medical Image Segmentation","dataset":"CVC-VideoClinicDB","model":"ResUNet++ + TTA","rank_in_archive_order":1,"of":5,"metrics":{"Dice":"0.8125","Recall":"0.6896","mIoU":"0.8467","precision":"0.6421"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc","task":"Medical Image Segmentation","dataset":"CVC-VideoClinicDB","model":"ResUNet++ + TTA + CRF","rank_in_archive_order":2,"of":5,"metrics":{"Dice":"0.8130","Recall":"0.6875","mIoU":"0.8477","precision":"0.6276"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-cvc","task":"Medical Image Segmentation","dataset":"CVC-VideoClinicDB","model":"ResUNet++ + CRF","rank_in_archive_order":4,"of":5,"metrics":{"Dice":"0.8811","Recall":"0.7743","mIoU":"0.8739","precision":"0.6706"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-etis","task":"Medical Image Segmentation","dataset":"ETIS-LARIBPOLYPDB","model":"ResUNet++ + TTA","rank_in_archive_order":25,"of":25,"metrics":{"mIoU":"0.7458","mean Dice":"0.6136"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-segmentation-on-kvasir-seg","task":"Medical Image Segmentation","dataset":"Kvasir-SEG","model":"ResUNet++ + TTA + CRF","rank_in_archive_order":52,"of":58,"metrics":{"FPS":"69.59","mIoU":"0.7800","mean Dice":"0.8508"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.12435","atlas_url":"https://app.syntology.ai/?focus=2107.12435","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}