LAEDNet: A Lightweight Attention Encoder–Decoder Network for ultrasound medical image segmentation. (April 2022)

• Record Type: Journal Article
• Authors: Zhou, Quan; Wang, Qianwen; Bao, Yunchao; Kong, Lingjun; Jin, Xin; Ou, Weihua
• Is Part Of: Computers & electrical engineering. Volume 99(2022)
• Publication Date: 2022-04
• Subjects: Lightweight network -- Medical ultrasound image segmentation -- Encoder–decoder network -- Visual attention -- EfficientNet; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107777
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Automatic ultrasound image segmentation plays an important role in early diagnosis of human diseases. This paper introduces a novel and efficient encoder–decoder network, called Lightweight Attention Encoder–Decoder Network (LAEDNet), for automatic ultrasound image segmentation. In contrast to previous encoder–decoder networks that involve complicated architecture with numerous parameters, our LAEDNet adopts lightweight version of EfficientNet as encoder. On the other hand, a Lightweight Residual Squeeze-and-Excitation (LRSE) block is employed in decoder. To achieve trade-off between segmentation accuracy and implementing efficiency, we also present a family of models, from light to heavy (denoted as LAEDNet-S, LAEDNet-M, and LAEDNet-L, respectively), with varying lightweight version of EfficientNet backbones. To evaluate LAEDNet, we have conducted extensive experiments on Brachial Plexus Dataset (BP), Breast Ultrasound Images Dataset (BUSI), and Head Circumference Ultrasound Images Dataset (HCUS), where ultrasound images are suffered from high noise, blurred borders and low contrast. The experiments show that, compared with U-Net and its variants, e.g., M-Net, U-Net++ and TransUNet, our LAEDNet achieves better results in terms of Dice Coefficient (DSC) and running speed. Particularly, LAEDNet-M only has 10.75M model parameters with 40.7 FPS, yet obtaining 73.0%, 73.8% and 91.3% DSC on BP, BUSI and HCUS datasets, respectively. Highlights: We design a Lightweight Attention Encoder–Decoder Network (LAEDNet) for ultrasound medical image segmentation. With the guidance of visual attention, a LRSE block is designed to coupled with LAEDNet backbone. LAEDNet achieves best trade-off of accuracy and efficiency on 3 ultrasound medical image datasets