{"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/concatenate-fine-tuning-re-training-a-sam","title":"Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation","arxiv_id":"2403.11229","date":"2024-03-17","proceeding":null,"authors":["Shumeng Li","Lei Qi","Qian Yu","Jing Huo","Yinghuan Shi","Yang Gao"],"abstract":"Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR$^+$ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR$^+$ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset.","url_abs":"https://arxiv.org/abs/2403.11229v2","url_pdf":"https://arxiv.org/pdf/2403.11229v2.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":"concatenate-fine-tuning-re-training-a-sam","repo_url":"https://github.com/shumengli/cfr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"concatenate-fine-tuning-re-training-a-sam","repo_url":"https://github.com/shumengli/sfr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"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":"semi-supervised-medical-image-segmentation","task_name":"Semi-supervised Medical Image Segmentation"}],"methods":[{"method_slug":"sam","method_name":"SAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.11229","atlas_url":"https://app.syntology.ai/?focus=2403.11229","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}