{"ID":2888950,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23110","arxiv_id":"2507.23110","title":"Rethink Domain Generalization in Heterogeneous Sequence MRI Segmentation","abstract":"Clinical magnetic-resonance (MR) protocols generate many T1 and T2 sequences whose appearance differs more than the acquisition sites that produce them. Existing domain-generalization benchmarks focus almost on cross-center shifts and overlook this dominant source of variability. Pancreas segmentation remains a major challenge in abdominal imaging: the gland is small, irregularly, surrounded by organs and fat, and often suffers from low T1 contrast. State-of-the-art deep networks that already achieve \u003e90% Dice on the liver or kidneys still miss 20-30% of the pancreas. The organ is also systematically under-represented in public cross-domain benchmarks, despite its clinical importance in early cancer detection, surgery, and diabetes research. To close this gap, we present PancreasDG, a large-scale multi-center 3D MRI pancreas segmentation dataset for investigating domain generalization in medical imaging. The dataset comprises 563 MRI scans from six institutions, spanning both venous phase and out-of-phase sequences, enabling study of both cross-center and cross-sequence variations with pixel-accurate pancreas masks created by a double-blind, two-pass protocol. Through comprehensive analysis, we reveal three insights: (i) limited sampling introduces significant variance that may be mistaken for distribution shifts, (ii) cross-center performance correlates with source domain performance for identical sequences, and (iii) cross-sequence shifts require specialized solutions. We also propose a semi-supervised approach that leverages anatomical invariances, significantly outperforming state-of-the-art domain generalization techniques with 61.63% Dice score improvements and 87.00% on two test centers for cross-sequence segmentation. PancreasDG sets a new benchmark for domain generalization in medical imaging. Dataset, code, and models will be available at https://pancreasdg.netlify.app.","short_abstract":"Clinical magnetic-resonance (MR) protocols generate many T1 and T2 sequences whose appearance differs more than the acquisition sites that produce them. Existing domain-generalization benchmarks focus almost on cross-center shifts and overlook this dominant source of variability. Pancreas segmentation remains a major c...","url_abs":"https://arxiv.org/abs/2507.23110","url_pdf":"https://arxiv.org/pdf/2507.23110v1","authors":"[\"Zheyuan Zhang\",\"Linkai Peng\",\"Wanying Dou\",\"Cuiling Sun\",\"Halil Ertugrul Aktas\",\"Andrea M. Bejar\",\"Elif Keles\",\"Gorkem Durak\",\"Ulas Bagci\"]","published":"2025-07-30T21:26:28Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","project_urls":"[\"https://pancreasdg.netlify.app\"]","has_code":false}