mlsanityData to 7 Oct 2026

Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation

arXiv 2107.00977 ↗First posted 2 Jul 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Cardiac ultrasound imaging is used to diagnose various heart diseases. Common analysis pipelines involve manual processing of the video frames by expert clinicians. This suffers from intra- and inter-observer variability. We propose a novel approach to ultrasound video analysis using a transformer architecture based on a Residual Auto-Encoder Network and a BERT model adapted for token classification. This enables videos of any length to be processed. We apply our model to the task of End-Systolic (ES) and End-Diastolic (ED) frame detection and the automated computation of the left ventricular ejection fraction. We achieve an average frame distance of 3.36 frames for the ES and 7.17 frames for the ED on videos of arbitrary length. Our end-to-end learnable approach can estimate the ejection fraction with a MAE of 5.95 and R2 of 0.52 in 0.15s per video, showing that segmentation is not the only way to predict ejection fraction. Code and models are available at https://github.com/HReynaud/UVT.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 8 of its 27 references that are in the map. First posted on arXiv 2 Jul 2021.

Builds on

8 of 27 references.

References · 8

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2018Video Action Transformer Networkcited by 316
  7. 2016SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasoundcited by 71
  8. 2018Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequencescited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 5; 2024: 5; 2025: 8; 2026: 6.

34 papers.

Sort:

By area:

  1. 2022Transformers in Medical Imaging: A Surveycited by 245
  2. 2023Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Reviewcited by 62
  3. 2022Transformers in Medical Image Analysis: A Reviewcited by 41
  4. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  5. 2022D'ARTAGNAN: Counterfactual Video Generationcited by 27
  6. 2022EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networkscited by 17
  7. 2021Adaptive Contrast for Image Regression in Computer-Aided Disease Assessmentcited by 16
  8. 2022EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiographycited by 16
  9. 2022Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasoundcited by 15
  10. 2022Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videoscited by 12
  11. 2023GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosiscited by 9
  12. 2024CoReEcho: Continuous Representation Learning for 2D+time Echocardiography Analysiscited by 8
22 more
  1. 2025Latent Motion Profiling for Annotation-free Cardiac Phase Detection in Adult and Fetal Echocardiography Videoscited by 6
  2. 2022BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Videocited by 4
  3. 2025EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generationcited by 4
  4. 2022Memory transformers for full context and high-resolution 3D Medical Segmentationcited by 3
  5. 2023Hierarchical Vision Transformers for Cardiac Ejection Fraction Estimationcited by 3
  6. 2024EchoNarrator: Generating natural text explanations for ejection fraction predictionscited by 2
  7. 2024Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identificationcited by 2
  8. 2025ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiographycited by 2
  9. 2024Cardiac valve event timing in echocardiography using deep learning and triplane recordingscited by 1
  10. 2024EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Datacited by 1
  11. 2026Orientation-Robust Latent Motion Trajectory Learning for Annotation-free Cardiac Phase Detection in Fetal Echocardiographycited by 1
  12. 2026Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Videocited by 1
  13. 2026FrameONE: Hierarchical Motion Modeling for Universal Multi-View Echocardiographic Keyframe Detectioncited by 1
  14. 2023ConFormer: A Novel Collection of Deep Learning Models to Assist Cardiologists in the Assessment of Cardiac Functioncited by 0
  15. 2025Echo-E3Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimationcited by 0
  16. 2025Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videoscited by 0
  17. 2025Heart Failure Prediction using Modal Decomposition and Masked Autoencoders for Scarce Echocardiography Databasescited by 0
  18. 2025Acoustic Index: A Novel AI-Driven Parameter for Cardiac Disease Risk Stratification Using Echocardiographycited by 0
  19. 2025Anatomically Constrained Transformers for Echocardiogram Analysiscited by 0
  20. 2026A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Predictioncited by 0
  21. 2026Self-Supervised Cardiac Phase Detection via Single-Parameter Latent Orbitscited by 0
  22. 2026The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regressioncited by 0