CIRSeg combines 3D CutMix with stochastic intensity transfer using either Nyul augmentation or histogram matching to improve robustness to heterogeneous MRI intensities, and cascaded architecture decouples low-resolution anatomical localization from full-resolution boundary refinement.
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
A formulation-driven segmentation framework is introduced that explic-itly integrates global structural modeling and boundary-aware constraints and yields a principled foundation for developing clinically reliable segmentation systems.
Ali Mohamed El-Eraky, Mohamed El-Gamel, A. ElTanboly· International journal of re...· 0 citations
Accurate kidney and renal-tumor segmentation is challenging because lesion size, location, morphology, and boundary contrast vary substantially across abdominal CT scans. Most existing methods rely on a single form of local evidence and struggle to recover the boundaries of small lesions while maintaining global anatom...
Si-Yuan Liang, Cheng-Chuan Xu, Chao Lu et al.· Frontiers in Artificial Inte...· 0 citations
Results indicate that Hybrid DeepLabV3+ can identify and map tumor regions with high fidelity, supporting its potential integration into clinical decision-support systems.
A. Karim, I. Purnama, Kusmanto Kusmanto et al.· Jurnal Teknik Informatika (J...· 0 citations
Accurate tumor segmentation in Positron Emission Tomography/Computed Tomography (PET/CT) is essential for clinical diagnosis, staging, and treatment planning. However, the reliance on time-consuming pixel-level annotations limits the practical deployment of deep learning-based segmentation methods. Weakly supervised se...
The effectiveness of DGSA-Net is evaluated on three heterogeneous benchmark datasets, including dermoscopic, CT, and chest X-ray datasets, demonstrating that DGSA-Net consistently outperforms state-of-the-art methods.
Dhiraj Kumar Raut, Pandu Sowkuntla· IEEE Open Journal of the Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.