Motion Correction Using Deep Learning Neural Networks - Effects of Data Representation

Rifkat Zaydullin, Anil A. Bharath, Enrico Grisan, Kirsten Christensen-Jeffries, Wenjia Bai, Meng-Xing Tang

Research output: Chapter in Book/Report/Conference proceedingConference paper

2 Citations (Scopus)

Abstract

An in-silico investigation of the effects of ultrasound data representation on the accuracy of the motion prediction made using deep learning neural networks was carried out. The representations studied include: linear ('envelope'), log compressed, linear with phase and log compressed with phase. A UNet model was trained to predict non-rigid deformation field using a fixed and a moving image pair as the input. The results illustrate that the choice of the representation plays an important role on the accuracy of motion estimation. Specifically, representations with phase information outperform the representations without phase. Furthermore, log-compressed data yielded predictions with higher accuracy than the linear data.

Original languageEnglish
Title of host publicationIUS 2022 - IEEE International Ultrasonics Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665466578
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Ultrasonics Symposium, IUS 2022 - Venice, Italy
Duration: 10 Oct 202213 Oct 2022

Publication series

NameIEEE International Ultrasonics Symposium, IUS
Volume2022-October
ISSN (Print)1948-5719
ISSN (Electronic)1948-5727

Conference

Conference2022 IEEE International Ultrasonics Symposium, IUS 2022
Country/TerritoryItaly
CityVenice
Period10/10/202213/10/2022

Keywords

  • data representation
  • deep learning
  • motion correction
  • motion estimation
  • ultrasound

Fingerprint

Dive into the research topics of 'Motion Correction Using Deep Learning Neural Networks - Effects of Data Representation'. Together they form a unique fingerprint.

Cite this