Skip to main navigation Skip to search Skip to main content

A deep residual networks classification algorithm of fetal heart CT images

  • Beihang University

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

Abstract

This paper proposes a deep residual networks classification algorithm of fetal heart CT images. It is difficult to diagnose Fetal Congenital Heart Disease (FCHD) due to medical CT images of fetal heart has much noisy than general natural scenes images and fetal body position is not fixed. These are great difficulties for medical experts so they cannot give every subject correct diagnosis. The algorithm in this paper exploits deep residual networks to classify the FCHD CT images and may give higher accuracy and precision than medical experts. The residual networks we proposed are based on ResNet34 [1] and a fully connected (FC) layer is added to the last layer of ResNet34 due to the binary classification for negative or positive of FCHD. This residual networks mechanism achieves superior performance than other baseline deep network for binary classification of FCHD.

Original languageEnglish
Title of host publicationIST 2018 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538666289
DOIs
StatePublished - 14 Dec 2018
Event2018 IEEE International Conference on Imaging Systems and Techniques, IST 2018 - Krakow, Poland
Duration: 16 Oct 201818 Oct 2018

Publication series

NameIST 2018 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

Conference

Conference2018 IEEE International Conference on Imaging Systems and Techniques, IST 2018
Country/TerritoryPoland
CityKrakow
Period16/10/1818/10/18

Keywords

  • CT images classification
  • deep residual network
  • fetal congenital heart disease

Fingerprint

Dive into the research topics of 'A deep residual networks classification algorithm of fetal heart CT images'. Together they form a unique fingerprint.

Cite this