{"ID":2866329,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19711","arxiv_id":"2509.19711","title":"Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis","abstract":"The rise of In-Context Learning (ICL) for universal medical image segmentation has introduced an unprecedented demand for large-scale, diverse datasets for training, exacerbating the long-standing problem of data scarcity. While data synthesis offers a promising solution, existing methods often fail to simultaneously achieve both high data diversity and a domain distribution suitable for medical data. To bridge this gap, we propose \\textbf{SynthICL}, a novel data synthesis framework built upon domain randomization. SynthICL ensures realism by leveraging anatomical priors from real-world datasets, generates diverse anatomical structures to cover a broad data distribution, and explicitly models inter-subject variations to create data cohorts suitable for ICL. Extensive experiments on four held-out datasets validate our framework's effectiveness, showing that models trained with our data achieve performance gains of up to 63\\% in average Dice and substantially enhanced generalization to unseen anatomical domains. Our work helps mitigate the data bottleneck for ICL-based segmentation, paving the way for robust models. Our code and the generated dataset are publicly available at https://github.com/jiesihu/Neuroverse3D.","short_abstract":"The rise of In-Context Learning (ICL) for universal medical image segmentation has introduced an unprecedented demand for large-scale, diverse datasets for training, exacerbating the long-standing problem of data scarcity. While data synthesis offers a promising solution, existing methods often fail to simultaneously a...","url_abs":"https://arxiv.org/abs/2509.19711","url_pdf":"https://arxiv.org/pdf/2509.19711v1","authors":"[\"Jiesi Hu\",\"Yanwu Yang\",\"Zhiyu Ye\",\"Chenfei Ye\",\"Hanyang Peng\",\"Jianfeng Cao\",\"Ting Ma\"]","published":"2025-09-24T02:44:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609363,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2866329,"paper_url":"https://arxiv.org/abs/2509.19711","paper_title":"Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis","repo_url":"https://github.com/jiesihu/Neuroverse3D","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}