PCaSFUA-Net: Spatial frequency collaboration and uncertainty-aware fusion for multimodal prostate cancer segmentation.
Authors
Affiliations (8)
Affiliations (8)
- State Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570288, China; School of Artificial Intelligence, Hainan Normal University, Haikou, 571158, China.
- State Key Laboratory of Marine Resource Utilization in South China Sea, School of Information and Communication Engineering, Hainan University, Haikou 570288, China. Electronic address: [email protected].
- School of Artificial Intelligence, Hainan Normal University, Haikou, 571158, China. Electronic address: [email protected].
- School of Mechanical and Electrical Engineering, Hainan University, Haikou, 570288, China.
- School of Computer science and Technology, Hainan University, Haikou 570288, China.
- School of Artificial Intelligence, Hainan Normal University, Haikou, 571158, China; Haikou Key Laboratory of Intelligent Analysis and Secure Sharing of Tropical Biodiversity Data, Hainan Normal University, Haikou, 571158, China.
- School of Artificial Intelligence, Hainan Normal University, Haikou, 571158, China.
- Haikou Municipal People's Hospital and Central South University Xiangya Medical College Affiliated Hospital, Haikou 570288, China.
Abstract
Accurate prostate cancer segmentation is essential for disease progression assessment and prognostic evaluation. Multiparametric MRI (mpMRI) offers complementary structural and functional information, enabling more reliable lesion segmentation than single-modality MRI. However, existing methods still struggle to preserve high-frequency details and handle modality uncertainty, which limits multimodal fusion effectiveness and segmentation accuracy under ambiguous tumor boundaries, complex lesion morphology, and substantial inter-modality heterogeneity. To address these challenges, we propose PCaSFUA-Net, a multimodal prostate cancer segmentation network built upon a pretrained medical vision foundation model, enabling efficient task adaptation with minimal parameter updates. The proposed network integrates a unified multimodal enhancement and fusion (MEF) framework with a coarse-to-fine (C2F) strategy for spatial prompt refinement. Specifically, the MEF framework includes a spatial-frequency collaborative (SFC) module to enhance intra-modality boundary and texture representations and a modality uncertainty-aware fusion (MUAF) module to adaptively reweight multimodal features for robust cross-modal fusion. Extensive experiments on two public datasets and one private dataset show that PCaSFUA-Net consistently outperforms existing methods across multiple evaluation metrics.