MDEANet: A multi-scale deep enhanced attention net for popliteal fossa segmentation in ultrasound images.
Authors
Affiliations (8)
Affiliations (8)
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; School of Anesthesiology, Naval Medical University, Shanghai 200433, China.
- Department of Anesthesiology, Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200023, China.
- The First Hospital of Putian, Putian 351100, China.
- Jiangsu Cancer Hospital, Jiangsu 213164, China.
- School of Anesthesiology, Naval Medical University, Shanghai 200433, China.
- The First Hospital of Putian, Putian 351100, China. Electronic address: [email protected].
- School of Anesthesiology, Naval Medical University, Shanghai 200433, China. Electronic address: [email protected].
- School of Anesthesiology, Naval Medical University, Shanghai 200433, China; Faculty of Anesthesiology, Changhai Hospital, Naval Medical University, Shanghai 200433, China. Electronic address: [email protected].
Abstract
Popliteal sciatic nerve block is a widely used technique for lower limb anesthesia. However, despite ultrasound guidance, the complex anatomical structures of the popliteal fossa can present challenges, potentially leading to complications. To accurately identify the bifurcation of the sciatic nerve for nerve blockade, we propose MDEANet, a deep learning-based segmentation network designed for the precise localization of nerves, muscles, and arteries in ultrasound images of the popliteal region. MDEANet incorporates Cascaded Multi-scale Atrous Convolutions (CMAC) to enhance multi-scale feature extraction, Enhanced Spatial Attention Mechanism (ESAM) to focus on key anatomical regions, and Cross-level Feature Fusion (CLFF) to improve contextual representation. This integration markedly improves segmentation of nerves, muscles, and arteries. Experimental results demonstrate that MDEANet achieves an average Intersection over Union (IoU) of 88.60% and a Dice coefficient of 93.95% across all target structures, outperforming state-of-the-art models by 1.68% in IoU and 1.66% in Dice coefficient. Specifically, for nerve segmentation, the Dice coefficient reaches 93.31%, underscoring the effectiveness of our approach. MDEANet has the potential to provide decision-support assistance for anesthesiologists, thereby enhancing the accuracy and efficiency of ultrasound-guided nerve blockade procedures.