HGNet: High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention Network for Colorectal Polyp Detection

TL;DR

HGNet is a novel deep learning model that combines high-order spatial hypergraph reasoning and multi-scale attention to improve colorectal polyp detection, especially for small lesions, with enhanced interpretability.

Contribution

Introduces HGNet, integrating hypergraph convolution and multi-scale attention, with transfer learning and Eigen-CAM for improved accuracy and interpretability in polyp detection.

Findings

Achieves 94% accuracy and 90.6% recall on polyp detection.

Significantly improves detection of small lesions.

Provides interpretable decision visualization.

Abstract

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.