UACNet: Uncertainty-aware Network with Opinion Conjunction and Evidence-driven Channel Attention for Medical Image Segmentation

Uncertainty-aware deep learning methods have shown promising results in medical image segmentation, maintaining accuracy while quantifying prediction confidence. However, existing evidence-theory-based approaches fail to exploit multi-scale uncertainty and overlook evidence quality, leading to belief conflicts and evidence scarcity. They also rely on single-channel attention, resulting in biased and unreliable channel scores. Accordingly, this paper proposes a novel uncertainty-aware network with opinion conjunction and evidence-driven channel attention (UACNet) for medical image segmentation. Initially, a certainty-aware mechanism filters ambiguous features during feature extraction. Secondly, an opinion conjunction operator captures multi-scale uncertainty, converted to a joint certainty mask for skip connections to improve boundary accuracy and prevent risk oversight. Furthermore, a dual-path evidence-driven channel attention (DECA) module is designed to dynamically fuse dual-path attention scores with uncertainty awareness, focusing on critical channels while enabling self-assessment. Finally, three evidence-based losses mitigate belief conflicts and evidence insufficiency problems. Extensive experiments demonstrate the superiority of UACNet over state-of-the-art methods.