LAEDNet: A Lightweight Attention Encoder–Decoder Network for ultrasound medical image segmentation

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 previ...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & electrical engineering Ročník 99; s. 107777
Hlavní autoři: Zhou, Quan, Wang, Qianwen, Bao, Yunchao, Kong, Lingjun, Jin, Xin, Ou, Weihua
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier Ltd 01.04.2022
Elsevier BV
Témata:
Coders
Datasets
EfficientNet
Encoder–decoder network
Image contrast
Image segmentation
Lightweight
Lightweight network
Mathematical models
Medical imaging
Medical ultrasound image segmentation
Parameters
Ultrasonic imaging
Visual attention
EfficientNet
Encoder–decoder network
Visual attention
Medical ultrasound image segmentation
Lightweight network
ISSN:0045-7906, 1879-0755
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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. •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
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0045-7906
1879-0755
DOI:10.1016/j.compeleceng.2022.107777