HGNet: High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention Network for Colorectal Polyp Detection
This addresses the challenge of accurate and interpretable polyp detection for medical practitioners, with incremental improvements in existing methods.
The paper tackles the problem of detecting colorectal polyps in medical images, which is crucial for early cancer prevention, by proposing HGNet to improve detection of small lesions and boundary localization, achieving 94% accuracy, 90.6% recall, and 90% mAP@0.5.
Colorectal cancer (CRC) is closely linked to the malignant transformation of colorectal polyps, making early detection essential. However, current models struggle with detecting small lesions, accurately localizing boundaries, and providing interpretable decisions. To address these issues, we propose HGNet, which integrates High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention. Key innovations include: (1) an Efficient Multi-Scale Context Attention (EMCA) module to enhance lesion feature representation and boundary modeling; (2) the deployment of a spatial hypergraph convolution module before the detection head to capture higher-order spatial relationships between nodes; (3) the application of transfer learning to address the scarcity of medical image data; and (4) Eigen Class Activation Map (Eigen-CAM) for decision visualization. Experimental results show that HGNet achieves 94% accuracy, 90.6% recall, and 90% mAP@0.5, significantly improving small lesion differentiation and clinical interpretability. The source code will be made publicly available upon publication of this paper.