CIRSeg: Coarse-to-Fine Intensity-Robust Liver Segmentation with Source-Free Continual Test-Time Adaptation

2026-10-07

AI Summary

This work addresses the challenges of limited generalization, ambiguous boundaries, and false positives in contrast-enhanced MRI liver segmentation caused by annotation scarcity and scanner variability. We propose a source-free continual test-time adaptation framework built upon an nnU-Netv2-based coarse-to-fine cascade architecture. To mitigate domain shift, 3D CutMix and Nyul histogram matching are incorporated during training. During inference, adaptive optimization is achieved by integrating confidence filtering with probability prior regularization, while isolated false positives are eliminated via maximum connected component analysis. Evaluated on the CARE 2026 test set, the proposed method achieves Dice scores of 97.13% and 97.93% for in-domain and unseen-domain data, respectively, alongside significantly reduced HD95 values. These results demonstrate highly robust and precise cross-domain liver segmentation.

Abstract

Reliable liver segmentation in contrast-enhanced MRI is essential for quantitative hepatic assessment, treatment planning, and longitudinal disease monitoring. However, limited annotated data and scanner- or vendor-dependent intensity variations can cause overfitting and poor generalization to unseen acquisition domains. Moreover, simultaneously achieving robust global localization and precise boundary delineation remains challenging, while predictions may contain isolated false-positive regions outside the main liver component. To address these challenges, we propose CIRSeg, a coarse-to-fine, intensity-robust liver segmentation framework based on nnU-Netv2. CIRSeg combines 3D CutMix with stochastic intensity transfer using either Nyul augmentation or histogram matching to improve robustness to heterogeneous MRI intensities. Its cascaded architecture decouples low-resolution anatomical localization from full-resolution boundary refinement. At inference, source-free test-time adaptation based on confidence-filtered predictions and probability-prior regularization further improves robustness to out-of-distribution inputs. As a final deterministic post-processing step, largest connected component filtering removes isolated false-positive regions. On the CARE 2026 test set, CIRSeg achieves Dice scores of 97.13\% and 97.93\% on the in-domain and unseen-domain subsets, with corresponding HD95 values of 20.18 mm and 11.30 mm, respectively. These results demonstrate consistently accurate segmentation across both in-domain and unseen acquisition settings. The code is available at https://github.com/jingkunchen/MICCAI_CARE_2026

Problem

• Liver Segmentation
• Contrast-enhanced MRI
• Intensity Variation
• Domain Generalization
• False-positive Regions

Innovation

• Source-Free Test-Time Adaptation
• Coarse-to-Fine Segmentation
• Intensity Robustness
• Liver Segmentation
• Stochastic Intensity Transfer