CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift
2026-07-16 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of medical AI models performing poorly when tested on new types of medical images that differ from the ones they were trained on. They propose a new method called CRISP, which improves image segmentation without needing any data or tuning in the new environment. CRISP works by identifying stable and uncertain regions in images through repeated small changes, then refining these areas iteratively to create better predictions. Their tests on heart and lung images from different hospitals and scanners showed that CRISP outperforms other methods in handling these shifts.
distribution shiftmedical imagingdomain adaptationsegmentationrank stabilityspatial priorsperturbation invariancecardiac MRICT lung vessel segmentation
Authors
Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou
Abstract
Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by exhausting predefined possibilities through simulated shifts or pseudo-supervision. Such strategies struggle in the open-ended and unpredictable real world, where distribution shifts are effectively infinite. To address this challenge, we adopt the "Rank Stability of Positive Regions" as a working assumption under distribution shift, and use it to derive robust spatial hints for source-only segmentation. Guided by this assumption, we propose CRISP, a model-agnostic framework that, unlike deployment-time adaptation, requires no test-time parameter updates and no target-domain data--a target-free, plug-in refinement framework that segments with frozen weights. Rather than using ranking to directly output masks, CRISP exploits the stability of probability rankings under distribution shift to derive robust spatial priors. Via latent feature perturbation, perturbation-invariant high-grade regions define a high-precision (HP) core, while voxels that remain potentially foreground under at least one perturbation define a high-recall (HR) support; these dual priors are then recursively refined under perturbation. We then design an iterative training framework that progressively squeezes HP and HR toward the final segmentation. Extensive evaluations on multi-center cardiac MRI and CT-based lung vessel segmentation demonstrate CRISP's superior robustness, significantly outperforming state-of-the-art methods with striking HD95 reductions of up to 0.14 (7.0% improvement), 1.90 (13.1% improvement), and 8.39 (38.9% improvement) pixels across multi-center, demographic, and modality shifts, respectively.