{"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/polypgen-a-multi-center-polyp-detection-and","title":"A multi-centre polyp detection and segmentation dataset for generalisability assessment","arxiv_id":"2106.04463","date":"2021-06-08","proceeding":null,"authors":["Sharib Ali","Debesh Jha","Noha Ghatwary","Stefano Realdon","Renato Cannizzaro","Osama E. Salem","Dominique Lamarque","Christian Daul","Michael A. Riegler","Kim V. Anonsen","Andreas Petlund","Pål Halvorsen","Jens Rittscher","Thomas de Lange","James E. East"],"abstract":"Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp's number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as \\textit{PolypGen}) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation. Our dataset can be downloaded from \\url{ https://doi.org/10.7303/syn26376615}.","url_abs":"https://arxiv.org/abs/2106.04463v3","url_pdf":"https://arxiv.org/pdf/2106.04463v3.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":"polypgen-a-multi-center-polyp-detection-and","repo_url":"https://github.com/sharibox/EndoCV2021-polyp_det_seg_gen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"polypgen-a-multi-center-polyp-detection-and","repo_url":"https://github.com/sharibox/polypgen-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"polypgen-a-multi-center-polyp-detection-and","repo_url":"https://github.com/sharib-vision/PolypGen-Benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.04463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04463"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sharibox/EndoCV2021-polyp_det_seg_gen","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sharib-vision/PolypGen-Benchmark","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sharibox/polypgen-benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran":1,"unverified":12},"by_repo_kind":{"official":{"samples":10,"ran":1,"repositories":1},"listed":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"network/axialNet.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/network/axialNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"3297c96e4c60ba89","entry":"locate_folders","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"metrics/compute_seg.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/metrics/compute_seg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3297c96e4c60ba89"}},{"code_sha256_prefix":"6d292246dab9d292","entry":"panel_imgs","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"metrics/compute_seg.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/metrics/compute_seg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d292246dab9d292"}},{"code_sha256_prefix":"868e1e3a3d191711","entry":"rescale_im_stack","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"metrics/compute_seg.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/metrics/compute_seg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"868e1e3a3d191711"}},{"code_sha256_prefix":"df035572d17eaf87","entry":"axial50s","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"network/axialNet.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/network/axialNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df035572d17eaf87"}},{"code_sha256_prefix":"ce942a958c0ae909","entry":"convert_to_separable_conv","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"network/_deeplab.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/network/_deeplab.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce942a958c0ae909"}},{"code_sha256_prefix":"56689af33d286bee","entry":"convrelu","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"network/axialNet.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/network/axialNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56689af33d286bee"}},{"code_sha256_prefix":"4ed3491d5fe9d707","entry":"create_predFolder","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"polypGen_inference-seg.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/polypGen_inference-seg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ed3491d5fe9d707"}},{"code_sha256_prefix":"26e4e1876120be62","entry":"deeplabv3_mobilenet","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26e4e1876120be62"}},{"code_sha256_prefix":"187bc8c967b6d23b","entry":"deeplabv3_resnet101","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"187bc8c967b6d23b"}},{"code_sha256_prefix":"85f770a1a3693de2","entry":"deeplabv3_resnet50","repo":"sharib-vision/PolypGen-Benchmark","repo_kind":"listed","path":"network/modeling.py","file_url":"https://github.com/sharib-vision/PolypGen-Benchmark/blob/HEAD/network/modeling.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85f770a1a3693de2"}},{"code_sha256_prefix":"228421b7a5601682","entry":"detect_imgs","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"polypGen_inference-seg.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/polypGen_inference-seg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"228421b7a5601682"}},{"code_sha256_prefix":"569164e3b040e8bb","entry":"download_extract","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"datasets/polypGen2021.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/datasets/polypGen2021.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"569164e3b040e8bb"}},{"code_sha256_prefix":"d77b4e5c7bc5bd55","entry":"kmoment","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"network/network.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/network/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d77b4e5c7bc5bd55"}},{"code_sha256_prefix":"871e79260c9007eb","entry":"plotInference","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"main_polypGen.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/main_polypGen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"871e79260c9007eb"}},{"code_sha256_prefix":"874968823d3561fe","entry":"voc_cmap","repo":"sharibox/polypgen-benchmark","repo_kind":"official","path":"datasets/polypGen2021.py","file_url":"https://github.com/sharibox/polypgen-benchmark/blob/HEAD/datasets/polypGen2021.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"874968823d3561fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}