{"ID":2826654,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18176","arxiv_id":"2512.18176","title":"Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation","abstract":"Accurate medical image segmentation is essential for clinical diagnosis and treatment planning. While recent interactive foundation models (e.g., nnInteractive) enhance generalization through large-scale multimodal pretraining, they still depend on precise prompts and often perform below expectations in contexts that are underrepresented in their training data. We present AtlasSegFM, an atlas-guided framework that customizes available foundation models to clinical contexts with a single annotated example. The core innovations are: 1) a pipeline that provides context-aware prompts for foundation models via registration between a context atlas and query images, and 2) a test-time adapter to fuse predictions from both atlas registration and the foundation model. Extensive experiments across public and in-house datasets spanning multiple modalities and organs demonstrate that AtlasSegFM consistently improves segmentation, particularly for small, delicate structures. AtlasSegFM provides a lightweight, deployable solution one-shot customization of foundation models in real-world clinical workflows. The code will be made publicly available.","short_abstract":"Accurate medical image segmentation is essential for clinical diagnosis and treatment planning. While recent interactive foundation models (e.g., nnInteractive) enhance generalization through large-scale multimodal pretraining, they still depend on precise prompts and often perform below expectations in contexts that a...","url_abs":"https://arxiv.org/abs/2512.18176","url_pdf":"https://arxiv.org/pdf/2512.18176v1","authors":"[\"Ziyu Zhang\",\"Yi Yu\",\"Simeng Zhu\",\"Ahmed Aly\",\"Yunhe Gao\",\"Ning Gu\",\"Yuan Xue\"]","published":"2025-12-20T02:29:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}