{"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/segvol-universal-and-interactive-volumetric","title":"SegVol: Universal and Interactive Volumetric Medical Image Segmentation","arxiv_id":"2311.13385","date":"2023-11-22","proceeding":null,"authors":["Yuxin Du","Fan Bai","Tiejun Huang","Bo Zhao"],"abstract":"Precise image segmentation provides clinical study with instructive information. Despite the remarkable progress achieved in medical image segmentation, there is still an absence of a 3D foundation segmentation model that can segment a wide range of anatomical categories with easy user interaction. In this paper, we propose a 3D foundation segmentation model, named SegVol, supporting universal and interactive volumetric medical image segmentation. By scaling up training data to 90K unlabeled Computed Tomography (CT) volumes and 6K labeled CT volumes, this foundation model supports the segmentation of over 200 anatomical categories using semantic and spatial prompts. To facilitate efficient and precise inference on volumetric images, we design a zoom-out-zoom-in mechanism. Extensive experiments on 22 anatomical segmentation tasks verify that SegVol outperforms the competitors in 19 tasks, with improvements up to 37.24% compared to the runner-up methods. We demonstrate the effectiveness and importance of specific designs by ablation study. We expect this foundation model can promote the development of volumetric medical image analysis. The model and code are publicly available at: https://github.com/BAAI-DCAI/SegVol.","url_abs":"https://arxiv.org/abs/2311.13385v4","url_pdf":"https://arxiv.org/pdf/2311.13385v4.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":"segvol-universal-and-interactive-volumetric","repo_url":"https://github.com/baai-dcai/segvol","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"volumetric-medical-image-segmentation","task_name":"Volumetric Medical Image Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.13385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13385"}},"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":"deterministic:regex_extraction","url":"https://github.com/BAAI-DCAI/SegVol","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baai-dcai/segvol","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":2,"ran_fixture":2,"unverified":7},"by_repo_kind":{"official":{"samples":17,"ran":10,"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":"36f26d56281c52ef","entry":"BCELoss","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36f26d56281c52ef"}},{"code_sha256_prefix":"89f037803e582646","entry":"BinaryDiceLoss","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89f037803e582646"}},{"code_sha256_prefix":"f28d43cf11e329dc","entry":"collate_fn","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f28d43cf11e329dc"}},{"code_sha256_prefix":"3ce5ee054e5ef306","entry":"combine_gt_fh","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_process/pseudo_mask_process.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_process/pseudo_mask_process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ce5ee054e5ef306"}},{"code_sha256_prefix":"3d04f3558b5dfd24","entry":"dice_score","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"inference_demo.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/inference_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d04f3558b5dfd24"}},{"code_sha256_prefix":"22ca9778295d4921","entry":"generate_box","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22ca9778295d4921"}},{"code_sha256_prefix":"733d7f0bedcb74c2","entry":"get_rel_pos","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"segment_anything_volumetric/modeling/image_encoder.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/segment_anything_volumetric/modeling/image_encoder.py","link_basis":"harvester_set","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":"733d7f0bedcb74c2"}},{"code_sha256_prefix":"472c84cf48b2a3a1","entry":"normalize","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_process/train_data_process.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_process/train_data_process.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"472c84cf48b2a3a1"}},{"code_sha256_prefix":"ca023fe736b612b2","entry":"select_points","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca023fe736b612b2"}},{"code_sha256_prefix":"105fa08885dc36cc","entry":"window_partition","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"segment_anything_volumetric/modeling/image_encoder.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/segment_anything_volumetric/modeling/image_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"105fa08885dc36cc"}},{"code_sha256_prefix":"144a0c9e8f82ddf9","entry":"SegVol","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.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":"144a0c9e8f82ddf9"}},{"code_sha256_prefix":"7f2202c6eb9e6be5","entry":"TextEncoder","repo":"baai-dcai/segvol","repo_kind":"official","path":"network/model.py","file_url":"https://github.com/baai-dcai/segvol/blob/HEAD/network/model.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":"7f2202c6eb9e6be5"}},{"code_sha256_prefix":"9ffc89cec399a67d","entry":"build_concat_dataset","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_utils.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":"9ffc89cec399a67d"}},{"code_sha256_prefix":"0421924382775c16","entry":"build_sam_vit_3d","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"segment_anything_volumetric/build_sam.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/segment_anything_volumetric/build_sam.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":"0421924382775c16"}},{"code_sha256_prefix":"883ac6b675c5850b","entry":"get_loader","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_utils.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":"883ac6b675c5850b"}},{"code_sha256_prefix":"18dff7ff75958f6b","entry":"process_ct_gt","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"data_process/demo_data_process.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/data_process/demo_data_process.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":"18dff7ff75958f6b"}},{"code_sha256_prefix":"27be441cc8213e52","entry":"window_unpartition","repo":"BAAI-DCAI/SegVol","repo_kind":"official","path":"segment_anything_volumetric/modeling/image_encoder.py","file_url":"https://github.com/BAAI-DCAI/SegVol/blob/HEAD/segment_anything_volumetric/modeling/image_encoder.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":"27be441cc8213e52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}