DualBranchNetwork3D: A Hybrid CNN–Swin Transformer Model for Automated Cirrhotic Liver Segmentation on MRI

Abstract

Accurate segmentation of cirrhotic livers from Magnetic Resonance Imaging (MRI) remains a critical challenge due to irregular liver morphology, heterogeneous tissue textures, and modality-specific artifacts. In this study, we propose DualBranchNetwork3D, a hybrid architecture that integrates a residual convolutional encoder for local texture modeling with Swin Transformer blocks for global context learning, combined via multi-scale feature fusion. The model employs a composite loss function incorporating Dice, Focal, Tversky, and boundary losses to address class imbalance and complex anatomical variations. Evaluated on the CirrMRI600+ dataset, comprising 310 T1-weighted (T1W) and 318 T2-weighted (T2W) MRI scans, our approach achieved state-of-the-art performance with Dice scores of 0.9545 on T1W and 0.9241 on T2W, outperforming existing baselines by 7.5% and 5.9%, respectively. These results validate the effectiveness of hybrid CNN-Transformer architectures for cirrhotic liver segmentation and highlight the potential for integrating such models into clinical workflows for fibrosis staging, volumetric assessment, and treatment planning.