文献类型：期刊文献

英文题名：CTSC-Reg: Unsupervised multimodal medical image registration via cross-task structural consistency

作者：Wang, Zichen[1];Wang, Yu[1];Bao, Caiyin[1];Shi, Yupeng[1];Yang, Jianlan[2]

第一作者：Wang, Zichen

通信作者：Yang, JL[1]

机构：[1]Gansu Univ Chinese Med, Sch Med Informat Sci & Engn, Lanzhou 730000, Gansu, Peoples R China;[2]Quanzhou Orthoped Traumatol Hosp, Quanzhou 362000, Fujian, Peoples R China

第一机构：甘肃中医药大学

通信机构：[1]corresponding author), Quanzhou Orthoped Traumatol Hosp, Quanzhou 362000, Fujian, Peoples R China.

年份：2026

卷号：128

外文期刊名：BIOMEDICAL SIGNAL PROCESSING AND CONTROL

收录：;EI(收录号：20263321303951);Scopus(收录号：2-s2.0-105047266133);WOS:【SCI-EXPANDED(收录号:WOS:001850007600001)】；

基金：The authors thank the School of Medicine Information Science and Engineering, Gansu University of Chinese Medicine and Quanzhou Orthopedic Traumatological Hospital for their support of this study.

语种：英文

外文关键词：Multimodal medical image registration; Image-to-image translation; Cross-task structural consistency; Anatomy-texture synergistic regularization; Unsupervised learning

摘要：Multimodal medical image registration is pivotal for integrating complementary information across distinct imaging modalities to facilitate precise diagnosis and treatment planning. However, existing translation-based methods typically decouple translation from registration, suffering from unidirectional dependency and reliance on implicit constraints that often compromise anatomical boundary precision. To address these limitations, we propose CTSC-Reg, an unsupervised framework that establishes Cross-Task Structural Consistency for collaborative network optimization. At its core, we introduce an Anatomy-Texture Synergistic Regularization (ATSR) mechanism, which projects heterogeneous features from translation and registration networks into a shared latent anatomical manifold to enforce mutual structural anchors instead of naive feature mimicry. Furthermore, the framework incorporates task-specific differentiated attention mechanisms to optimize global style transfer and local spatial correspondence respectively, alongside an explicit edge consistency loss to maintain boundary integrity. Extensive experiments on MR-CT and T1-T2 benchmark datasets demonstrate that CTSC-Reg consistently outperforms state-of-the-art methods, yielding significant improvements in boundarysensitive metrics.