SGF-SCA: A Spatial Gated Framework with Shared Channel Attention for Breast Ultrasound Image Segmentation

  • Tianyu Xu
  • , Yue Li
  • , Zixiang Song
  • , Yipeng Xu
  • , Yuzhe Wu
  • , Xiangjian He

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Breast ultrasound (US) image Segmentation is a significant challenge due to high noise levels, blurred boundaries, and low signal-to-noise ratios. To address these issues, we propose SGF-SCA, a Swin-Unet-based architecture enhanced with Spatial Gated Unit (SGU) and Shared Channel Attention Fusion Unit (SCAFU). The SGU in the encoder focuses on suppressing irrelevant features and enhancing relevant tokens in US images. In the decoder, SCAFU efficiently fuses skip connections with up-sampled features using shared channel attention mechanism. The enhancements improve feature extraction and refinement and facilitate solving the above issues of US image segmentation. Our method demonstrates improved performance on the BUSI dataset, with a Dice Coefficient of 79.9%, showing robustness in handling the complexities of ultrasound images.

Original languageEnglish
Title of host publicationProceedings of the 2024 6th International Conference on Video, Signal and Image Processing, VSIP 2024
PublisherAssociation for Computing Machinery, Inc
Pages69-74
Number of pages6
ISBN (Electronic)9798400709647
DOIs
Publication statusPublished - 27 Feb 2025
Event6th International Conference on Video, Signal and Image Processing, VSIP 2024 - Ningbo, China
Duration: 22 Nov 202424 Nov 2024

Publication series

NameProceedings of the 2024 6th International Conference on Video, Signal and Image Processing, VSIP 2024

Conference

Conference6th International Conference on Video, Signal and Image Processing, VSIP 2024
Country/TerritoryChina
CityNingbo
Period22/11/2424/11/24

Free Keywords

  • Breast Ultrasound Image Segmentation
  • Gating Mechanism
  • Shared Channel Attention

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications
  • Signal Processing

Fingerprint

Dive into the research topics of 'SGF-SCA: A Spatial Gated Framework with Shared Channel Attention for Breast Ultrasound Image Segmentation'. Together they form a unique fingerprint.

Cite this