DCA: Densely Cross-scale Attention Network for Anatomically-plausible Medical Image Segmentation

Yang Ning, Dawei Wang, Tianming Tan, Caiming Zhang

Abstract: Deep learning models applied to medical image segmentation have achieved remarkable performance across various tasks. Despite their high accuracy, these models may produce predictions that clinicians deem anatomically implausible. This limitation arises due to the inherent anatomical variability and indistinct boundaries present in clinical segmentation targets, impeding the effectiveness of existing research efforts. To overcome these challenges, we propose an innovative architectural framework known as Densely Cross-scale Attention (DCA) network. This framework efficiently incorporates multi-scale local and global attention dependencies using dense connections, resulting in anatomically-plausible segmentations. DCA comprises three new modules: 1) a multi-level feature aggregation module that merges multi-scale local features to acquire feature representations with diverse granularities, thereby compensating for information loss caused by gradient dispersion; 2) a cross-scale attention module that facilitates the modeling of long-range dependencies across scales while effectively diminishing task-irrelevant noise; and 3) a multi-scale self-attention module that captures the multi-scale global spatial relationships of single-scale local features, further enhancing the model’s resilience in addressing complex lesions. The proposed efficient dense connections offer a versatile and potent methodology for modeling long-range dependencies across scales in any segmentation network. The efficacy of our approach is demonstrated through experiments conducted on two clinically relevant datasets, substantiating its ability to achieve superior segmentation accuracy and anatomical plausibility.