Skip to main navigation Skip to search Skip to main content

Automatic Thyroid Ultrasound Image Segmentation Based on U-shaped Network

  • Jianrui Ding*
  • , Zichen Huang
  • , Mengdie Shi
  • , Chunping Ning
  • *Corresponding author for this work
  • School of Computer Science and Technology, Harbin Institute of Technology
  • Qingdao University

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

Abstract

Automatic tumor segmentation of thyroid ultrasound image is quite challenging due to the poor image quality. Recently the U-shaped network, especially U-Net, has achieved good results in medical image segmentation. In this paper, we proposed a modified U-Net model (ReAgU-Net), which embedded the improved residual units into the skip connection among the encoding and decoding path and introduce the attention gate mechanism to multiply the weight feature maps obtained from shallow layers and deep layers. Also, a hyperparameter is introduced to combine Focal-Tversky Loss, Dice Loss and Cross-entropy Loss to jointly guide the model optimization process. The experimental results demonstrate that the proposed approach outperforms the other U-shaped models.

Original languageEnglish
Title of host publicationProceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
EditorsQingli Li, Lipo Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728148526
DOIs
StatePublished - Oct 2019
Externally publishedYes
Event12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019 - Huaqiao, China
Duration: 19 Oct 201921 Oct 2019

Publication series

NameProceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019

Conference

Conference12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
Country/TerritoryChina
CityHuaqiao
Period19/10/1921/10/19

Keywords

  • ReAgU-Net
  • U-Net
  • automatic segmentation
  • thyroid ultrasound image

Fingerprint

Dive into the research topics of 'Automatic Thyroid Ultrasound Image Segmentation Based on U-shaped Network'. Together they form a unique fingerprint.

Cite this