Multi-Class Segmentation of Knee MRI Based on Hybrid Attention

Yuhang Xiang¹Xinglin Zhang²Tao Meng^2,3*Tao Chen^4,5*

• ¹Gannan Medical University, Ganzhou, China
• ²Shanghai Medical Image Insights Intelligent Technology Co., Ltd., Shanghai, China
• ³Jiangxi Rimag Group Co., Ltd., Nanchang, China
• ⁴Big Data Research Lab, University of Waterloo, Waterloo, Canada
• ⁵Labor and Worklife Program, Harvard University, Cambridge, United States

Accurate segmentation of knee MRI images is crucial for the diagnosis and treatment of degenerative knee disease and sports injuries. However, existing multi-class segmentation methods tend to ignore small targets and are challenged by class imbalance, resulting in suboptimal segmentation performance. This paper applies hybrid attention and multi-scale feature extraction to the problem of multi-class segmentation of knee MRI images and innovates the classic U-Net architecture. Firstly, we propose a Hierarchical Feature Enhancement Fusion (HFEF) module, which is integrated into both the skip connections and the bottleneck layer. This module captures channel and spatial information at multiple levels, enabling the model to efficiently combine local and global features. Secondly, we introduce the Atrous Squeeze Attention (ASA) module, which enables the model to focus on multi-scale features and capture long-range dependencies, thereby improving the segmentation accuracy of complex multi-class structures.Lastly, the loss function is optimized to address the challenges of class imbalance and limited data. The improved loss function enhances the model's ability to learn underrepresented classes, thus enhancing the overall segmentation performance. We evaluated our method on a knee joint MRI dataset and compared it with U-Net. HASA-ResUNet achieved a 12.12% improvement in Intersection over Union (IoU) for the low-frequency and small-sized class (Anterior cruciate ligament) and an overall improvement of 3.32% in mIoU.