A Multi-constraint Hybrid Network for Ultrasound Image Synthesis

Kaibin Cao, Danni Ai*, Deqiang Xiao, Jian Yang

*Corresponding author for this work

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

Abstract

Simulating ultrasound (US) through US image synthesis is crucial for preoperative training and learning ultrasound techniques for doctors. Due to the significant modality differences between magnetic resonance (MR) images and US images, the structure of the synthesized US images tends to be blurry and of lower quality. In this paper, we propose a hybrid network combining CNN and Transformer that enhances the synthesis performance by integrating their respective abilities in local and global feature extraction. We also introduce multiple constraints to improve the quality of the synthesized images. Firstly, we introduce a multi-scale perceptor (MSP) to enhance the structural content information of the synthesized images, thereby improving their authenticity. Additionally, we address the blurriness issue of synthesized images by incorporating a gradient difference loss in the loss function, which enhances the structural edge information and further improves the quality of synthesized images. Experimental results demonstrate that our proposed method achieves a PSNR of 14.7251 and an SSIM of 0.8556, outperforming other advanced methods currently available.

Original languageEnglish
Title of host publicationITOEC 2023 - IEEE 7th Information Technology and Mechatronics Engineering Conference
EditorsBing Xu, Kefen Mou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2147-2151
Number of pages5
ISBN (Electronic)9798350334197
DOIs
Publication statusPublished - 2023
Event7th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2023 - Chongqing, China
Duration: 15 Sept 202317 Sept 2023

Publication series

NameITOEC 2023 - IEEE 7th Information Technology and Mechatronics Engineering Conference

Conference

Conference7th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2023
Country/TerritoryChina
CityChongqing
Period15/09/2317/09/23

Keywords

  • GAN
  • Generative
  • Neural networks
  • Transformer
  • Ultrasound image synthesis
  • Virtual reality simulation

Fingerprint

Dive into the research topics of 'A Multi-constraint Hybrid Network for Ultrasound Image Synthesis'. Together they form a unique fingerprint.

Cite this