STRATIFYHF
Published May 20, 2026 | Version v1
Conference paper Open

Echocardiography View Classification as an Important Step to Heart Failure Diagnosis: A Case Study of the EchoJEPA Foundation Model

Authors/Creators

  • 1. Institute for Information Technologies, University of Kragujevac
  • 2. Bioengineering Research and Development Center (BioIRC), Kragujevac
  • 3. Faculty of Medicine, University of Novi Sad
  • 4. Institute for Cardio Metabolic Medicine, University Hospitals Coventry and Warwickshire
  • 5. ROR icon University Medical Center Utrecht

Description

Accurate classification of echocardiographic views (e.g. apical 2- and 4-chamber, parasternal long-axis) is an important prerequisite for reliable ejection-fraction assessment and heart failure diagnosis, but manual classification is time-consuming. This study evaluates the EchoJEPA foundation model, pretrained on more than 18 million ultrasound recordings, with modified output layers for automatic echocardiographic view classification, providing a baseline component for a larger automated pipeline for HF diagnosis from echocardiography video/image data. This work was presented at the 5th Serbian International Conference on Applied Artificial Intelligence (SICAAI 2026), Kragujevac, Serbia, and was carried out within the STRATIFYHF project.

Files

10_Pavic_et_al_Echocardiography_View_Classification_EchoJEPA_SICAAI2026.pdf

Files (209.3 kB)

Additional details

Funding

European Commission
STRATIFYHF - Artificial intelligence-based decision support system for risk stratification and early detection of heart failure in primary and secondary care 101080905