{"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/anatomask-enhancing-medical-image","title":"AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking","arxiv_id":"2407.06468","date":"2024-07-09","proceeding":null,"authors":["Yuheng Li","Tianyu Luan","Yizhou Wu","Shaoyan Pan","Yenho Chen","Xiaofeng Yang"],"abstract":"Due to the scarcity of labeled data, self-supervised learning (SSL) has gained much attention in 3D medical image segmentation, by extracting semantic representations from unlabeled data. Among SSL strategies, Masked image modeling (MIM) has shown effectiveness by reconstructing randomly masked images to learn detailed representations. However, conventional MIM methods require extensive training data to achieve good performance, which still poses a challenge for medical imaging. Since random masking uniformly samples all regions within medical images, it may overlook crucial anatomical regions and thus degrade the pretraining efficiency. We propose AnatoMask, a novel MIM method that leverages reconstruction loss to dynamically identify and mask out anatomically significant regions to improve pretraining efficacy. AnatoMask takes a self-distillation approach, where the model learns both how to find more significant regions to mask and how to reconstruct these masked regions. To avoid suboptimal learning, Anatomask adjusts the pretraining difficulty progressively using a masking dynamics function. We have evaluated our method on 4 public datasets with multiple imaging modalities (CT, MRI, and PET). AnatoMask demonstrates superior performance and scalability compared to existing SSL methods. The code is available at https://github.com/ricklisz/AnatoMask.","url_abs":"https://arxiv.org/abs/2407.06468v2","url_pdf":"https://arxiv.org/pdf/2407.06468v2.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":"anatomask-enhancing-medical-image","repo_url":"https://github.com/ricklisz/anatomask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"mim","method_name":"MIM"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.06468","atlas_url":"https://app.syntology.ai/?focus=2407.06468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06468"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ricklisz/anatomask","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"33adf3650aa33afe","entry":"convert_labels_back_to_BraTS","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/dataset_conversion/Dataset137_BraTS21.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/dataset_conversion/Dataset137_BraTS21.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":"33adf3650aa33afe"}},{"code_sha256_prefix":"517ad51ee69e8a2d","entry":"copy_files","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/dataset_conversion/Dataset027_ACDC.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/dataset_conversion/Dataset027_ACDC.py","link_basis":"harvester_set","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":"517ad51ee69e8a2d"}},{"code_sha256_prefix":"c66e8feb67225a1b","entry":"copy_files","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/dataset_conversion/Dataset115_EMIDEC.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/dataset_conversion/Dataset115_EMIDEC.py","link_basis":"plan_row","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":"c66e8feb67225a1b"}},{"code_sha256_prefix":"2a83a2bc5120febe","entry":"get_vendor_split","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/dataset_conversion/Dataset114_MNMs.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/dataset_conversion/Dataset114_MNMs.py","link_basis":"plan_row","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":"2a83a2bc5120febe"}},{"code_sha256_prefix":"86ec2ccc2984b8bf","entry":"merge","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/batch_running/generate_lsf_runs_customDecathlon.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/batch_running/generate_lsf_runs_customDecathlon.py","link_basis":"harvester_set","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":"86ec2ccc2984b8bf"}},{"code_sha256_prefix":"882441705cf75b1d","entry":"read_csv","repo":"ricklisz/anatomask","repo_kind":"official","path":"nnunetv2/dataset_conversion/Dataset114_MNMs.py","file_url":"https://github.com/ricklisz/anatomask/blob/HEAD/nnunetv2/dataset_conversion/Dataset114_MNMs.py","link_basis":"plan_row","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":"882441705cf75b1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}