A domain-adaptive deep contrastive network for magnetic resonance imaging-driven bladder cancer classification
Document Type
Article
Publication Date
12-1-2026
Abstract
Bladder cancer is one of the most prevalent malignancies of the urinary system and is associated with high morbidity and mortality. With advances in medical image analysis, deep learning has shown promise for automated bladder cancer classification using magnetic resonance imaging (MRI). However, clinical deployment remains challenging due to substantial inter-center distributional discrepancies and limited feature discriminability between non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC). To address these challenges, we propose a Domain-Adaptive Deep Contrastive Network (DADCNet) for MRI-based bladder cancer classification. The proposed framework jointly incorporates source- and target-domain samples during feature learning to obtain domain-invariant yet discriminative representations, thereby improving cross-center generalization. In addition, a deep contrastive learning strategy is introduced to enhance inter-class separability and intra-class compactness, leading to more robust classification. Experiments conducted on a multi-center bladder cancer MRI dataset demonstrate that DADCNet consistently outperforms existing convolutional neural network- and Transformer-based methods, achieving an accuracy of 0.955, an F1-score of 0.955, and an area under the curve of 0.991.
Keywords
Bladder cancers; Cancer classification; Discriminability; Feature learning; Generalisation; Inter class; Learning strategy; Medical image analysis; Target domain; Urinary system
Publication Title
Npj Digital Medicine
ISSN
2398-6352
DOI
10.1038/s41746-026-02499-4
Recommended Citation
Huang, Junjun; Hu, Haixia; Sun, Mengdan; Wu, Weiting; Xu, Keyi; Xu, Juan; Sun, Xufeng; Hu, Dongdong; Yao, Dandan; He, Tianran; Wei, Wei; Song, Baiyang; and Fang, Li, "A domain-adaptive deep contrastive network for magnetic resonance imaging-driven bladder cancer classification" (2026). Research Publications (2026 to 2030). 464.
https://knova.um.edu.my/research_publications_2026_2030/464
Volume
9
Issue
1