A Comparative Analysis of Vision Transformers and Convolutional Neural Networks in Cardiac Image Segmentation

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

1 Scopus citations

Abstract

In recent years, Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have emerged as dominant automated cardiac image segmentation methods. CNNs are efficient architectures that capture local spatial patterns, whereas ViTs can model long-range global dependencies. Each network has been shown to provide better performance on certain types of tasks and datasets. In this work, we conducted a comparative analysis between ViTs and CNNs in the context of cardiac image segmentation. We statistically evaluated the performance of five CNNs and ViTs architectures using the publicly available Automated Cardiac Diagnosis Challenge (ACDC) MRI dataset. Employing a one-way ANOVA and Tukey is test, our analysis indicates that CNNs exhibit superior performance compared to Transformers in segmenting the right ventricle cavity, the left ventricle cavity, and the left ventricle myocardium. Furthermore, CNN architectures tend to be smaller and easier to train. Among all the networks considered, LinkN et achieves the highest performance with a mean dice of 0.8965 and a mean ASSD of 0.2960.

Original languageEnglish
Title of host publication12th International Symposium on Digital Forensics and Security, ISDFS 2024
EditorsAsaf Varol, Murat Karabatak, Cihan Varol, Eva Tuba
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350330366
DOIs
StatePublished - 2024
Event12th International Symposium on Digital Forensics and Security, ISDFS 2024 - San Antonio, United States
Duration: 29 Apr 202430 Apr 2024

Publication series

Name12th International Symposium on Digital Forensics and Security, ISDFS 2024

Conference

Conference12th International Symposium on Digital Forensics and Security, ISDFS 2024
Country/TerritoryUnited States
CitySan Antonio
Period29/04/2430/04/24

Keywords

  • Cardiac MRI Segmentation
  • Convolutional Neural Networks (CNNs)
  • Image Segmentation
  • Transformers
  • Vision Transformers (ViT)

Fingerprint

Dive into the research topics of 'A Comparative Analysis of Vision Transformers and Convolutional Neural Networks in Cardiac Image Segmentation'. Together they form a unique fingerprint.

Cite this