{"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/data-augmentation-using-learned-transforms","title":"Data augmentation using learned transformations for one-shot medical image segmentation","arxiv_id":"1902.09383","date":"2019-02-25","proceeding":"CVPR 2019 6","authors":["Amy Zhao","Guha Balakrishnan","Frédo Durand","John V. Guttag","Adrian V. Dalca"],"abstract":"Image segmentation is an important task in many medical applications. Methods\nbased on convolutional neural networks attain state-of-the-art accuracy;\nhowever, they typically rely on supervised training with large labeled\ndatasets. Labeling medical images requires significant expertise and time, and\ntypical hand-tuned approaches for data augmentation fail to capture the complex\nvariations in such images.\n  We present an automated data augmentation method for synthesizing labeled\nmedical images. We demonstrate our method on the task of segmenting magnetic\nresonance imaging (MRI) brain scans. Our method requires only a single\nsegmented scan, and leverages other unlabeled scans in a semi-supervised\napproach. We learn a model of transformations from the images, and use the\nmodel along with the labeled example to synthesize additional labeled examples.\nEach transformation is comprised of a spatial deformation field and an\nintensity change, enabling the synthesis of complex effects such as variations\nin anatomy and image acquisition procedures. We show that training a supervised\nsegmenter with these new examples provides significant improvements over\nstate-of-the-art methods for one-shot biomedical image segmentation. Our code\nis available at https://github.com/xamyzhao/brainstorm.","url_abs":"http://arxiv.org/abs/1902.09383v2","url_pdf":"http://arxiv.org/pdf/1902.09383v2.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":"data-augmentation-using-learned-transforms","repo_url":"https://github.com/xamyzhao/brainstorm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"data-augmentation-using-learned-transforms","repo_url":"https://github.com/daxiaHuang/brainstorm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/brain-image-segmentation-on-t1-weighted-mri","task":"Brain Image Segmentation","dataset":"T1-weighted MRI","model":"Learned Transformations (random augmentaiton)","rank_in_archive_order":1,"of":1,"metrics":{"Dice Score":"81.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09383"}},"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/xamyzhao/brainstorm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daxiaHuang/brainstorm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":4,"ran":0,"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":"06fae1a1b2df3d75","entry":"get_dataset_files_list","repo":"xamyzhao/brainstorm","repo_kind":"official","path":"src/mri_loader.py","file_url":"https://github.com/xamyzhao/brainstorm/blob/HEAD/src/mri_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06fae1a1b2df3d75"}},{"code_sha256_prefix":"e1d771d7bf82822d","entry":"get_latest_epoch_in_dir","repo":"daxiaHuang/brainstorm","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/daxiaHuang/brainstorm/blob/HEAD/src/utils.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":"e1d771d7bf82822d"}},{"code_sha256_prefix":"7dcf6b1b7708cf8b","entry":"gradient_loss_l2","repo":"daxiaHuang/brainstorm","repo_kind":"listed","path":"src/metrics.py","file_url":"https://github.com/daxiaHuang/brainstorm/blob/HEAD/src/metrics.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":"7dcf6b1b7708cf8b"}},{"code_sha256_prefix":"b0f7bbbec28c1e25","entry":"make_output_dirs","repo":"daxiaHuang/brainstorm","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/daxiaHuang/brainstorm/blob/HEAD/src/utils.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":"b0f7bbbec28c1e25"}},{"code_sha256_prefix":"71489608e9d46658","entry":"onehot_to_labels","repo":"daxiaHuang/brainstorm","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/daxiaHuang/brainstorm/blob/HEAD/src/utils.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":"71489608e9d46658"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}