{"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/self-pre-training-with-masked-autoencoders","title":"Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation","arxiv_id":"2203.05573","date":"2022-03-10","proceeding":null,"authors":["Lei Zhou","Huidong Liu","Joseph Bae","Junjun He","Dimitris Samaras","Prateek Prasanna"],"abstract":"Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual information to infer masked image regions. We believe that this context aggregation ability is particularly essential to the medical image domain where each anatomical structure is functionally and mechanically connected to other structures and regions. Because there is no ImageNet-scale medical image dataset for pre-training, we investigate a self pre-training paradigm with MAE for medical image analysis tasks. Our method pre-trains a ViT on the training set of the target data instead of another dataset. Thus, self pre-training can benefit more scenarios where pre-training data is hard to acquire. Our experimental results show that MAE self pre-training markedly improves diverse medical image tasks including chest X-ray disease classification, abdominal CT multi-organ segmentation, and MRI brain tumor segmentation. Code is available at https://github.com/cvlab-stonybrook/SelfMedMAE","url_abs":"https://arxiv.org/abs/2203.05573v2","url_pdf":"https://arxiv.org/pdf/2203.05573v2.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":"self-pre-training-with-masked-autoencoders","repo_url":"https://github.com/cvlab-stonybrook/SelfMedMAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"brain-tumor-segmentation","task_name":"Brain Tumor Segmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"lung-disease-classification","task_name":"Lung Disease Classification"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"},{"task_slug":"organ-segmentation","task_name":"Organ Segmentation"},{"task_slug":"tumor-segmentation","task_name":"Tumor Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.05573","atlas_url":"https://app.syntology.ai/?focus=2203.05573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05573"}},"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/cvlab-stonybrook/SelfMedMAE","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"b41d2c14b4051c2d","entry":"build_perceptron_position_embedding","repo":"cvlab-stonybrook/SelfMedMAE","repo_kind":"official","path":"lib/models/mae3d.py","file_url":"https://github.com/cvlab-stonybrook/SelfMedMAE/blob/HEAD/lib/models/mae3d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b41d2c14b4051c2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}