Skip to main navigation Skip to search Skip to main content

3D Deep Adaptively Efficient Attention Model to segment Automated Breast Ultrasound

  • Hyunsu Jeong*
  • , Chiho Yoon
  • , Hyunseok Lim
  • , Jongjun Won
  • , Gongning Luo
  • , Mingwang Xu
  • , Kiduk Kim
  • , Namkug Kim
  • , Chulhong Kim
  • *Corresponding author for this work
  • Pohang University of Science and Technology
  • University of Ulsan
  • Faculty of Computing, Harbin Institute of Technology

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

Abstract

3D automated breast ultrasound (ABUS) data includes a huge number of slices with lesion-related artifacts and size variants, causing false positive cases. In addition, applying transformer-based models with self-attention considering long-range dependency to 3D ABUS data is challenging because of the small number of data. We propose 3D deep adaptively efficient attention model with a multi-task learning to segment the small number of 3D ABUS datasets. Our network consists of adaptive hybrid-transformer blocks for computationally efficient self-attention and multi-task learning to minimize false positive cases. Additionally, a novel attention gate is also implanted to considering long-range dependency between channel-attentive features. Our model performed 58.27%, 23.59 mm, and 0.054% on Dice, HD95, and FPR, respectively.

Original languageEnglish
Title of host publicationIEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium, UFFC-JS 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350371901
DOIs
StatePublished - 2024
Externally publishedYes
Event2024 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium, UFFC-JS 2024 - Taipei, Taiwan, Province of China
Duration: 22 Sep 202426 Sep 2024

Publication series

NameIEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium, UFFC-JS 2024 - Proceedings

Conference

Conference2024 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium, UFFC-JS 2024
Country/TerritoryTaiwan, Province of China
CityTaipei
Period22/09/2426/09/24

Keywords

  • 3D automated breast ultrasound (ABUS) segmentation
  • Channel-attentive model
  • Hybrid transformer
  • Multi-task learning

Fingerprint

Dive into the research topics of '3D Deep Adaptively Efficient Attention Model to segment Automated Breast Ultrasound'. Together they form a unique fingerprint.

Cite this