{"ID":2829063,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.13534","arxiv_id":"2512.13534","title":"Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains","abstract":"A single biomedical image can be meaningfully segmented in multiple ways, depending on the desired application. For instance, a brain MRI can be segmented according to tissue types, vascular territories, broad anatomical regions, fine-grained anatomy, or pathology, etc. Existing automatic segmentation models typically either (1) support only a single protocol, the one they were trained on, or (2) require labor-intensive manual prompting to specify the desired segmentation. We introduce Pancakes, a framework that, given a new image from a previously unseen domain, automatically generates multi-label segmentation maps for multiple plausible protocols, while maintaining semantic consistency across related images. Pancakes introduces a new problem formulation that is not currently attainable by existing foundation models. In a series of experiments on seven held-out datasets, we demonstrate that our model can significantly outperform existing foundation models in producing several plausible whole-image segmentations, that are semantically coherent across images.","short_abstract":"A single biomedical image can be meaningfully segmented in multiple ways, depending on the desired application. For instance, a brain MRI can be segmented according to tissue types, vascular territories, broad anatomical regions, fine-grained anatomy, or pathology, etc. Existing automatic segmentation models typically...","url_abs":"https://arxiv.org/abs/2512.13534","url_pdf":"https://arxiv.org/pdf/2512.13534v1","authors":"[\"Marianne Rakic\",\"Siyu Gai\",\"Etienne Chollet\",\"John V. Guttag\",\"Adrian V. Dalca\"]","published":"2025-12-15T17:00:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}