# Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation

arXiv: https://arxiv.org/abs/2107.00977 · HTML: https://mlsanity.com/paper/2107.00977/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 2 Jul 2021.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences](https://mlsanity.com/paper/1806.04066/) (2018)

## Built on by (most cited first, 30 of 34)

- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review](https://mlsanity.com/paper/2301.03505/) (2023)
- [Transformers in Medical Image Analysis: A Review](https://mlsanity.com/paper/2202.12165/) (2022)
- [Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis](https://mlsanity.com/paper/2303.12644/) (2023)
- [D'ARTAGNAN: Counterfactual Video Generation](https://mlsanity.com/paper/2206.01651/) (2022)
- [EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networks](https://mlsanity.com/paper/2208.14003/) (2022)
- [Adaptive Contrast for Image Regression in Computer-Aided Disease Assessment](https://mlsanity.com/paper/2112.11700/) (2021)
- [EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography](https://mlsanity.com/paper/2209.04242/) (2022)
- [Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound](https://mlsanity.com/paper/2207.02549/) (2022)
- [Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos](https://mlsanity.com/paper/2210.11291/) (2022)
- [GEMTrans: A General, Echocardiography-based, Multi-Level Transformer Framework for Cardiovascular Diagnosis](https://mlsanity.com/paper/2308.13217/) (2023)
- [CoReEcho: Continuous Representation Learning for 2D+time Echocardiography Analysis](https://mlsanity.com/paper/2403.10164/) (2024)
- [Latent Motion Profiling for Annotation-free Cardiac Phase Detection in Adult and Fetal Echocardiography Videos](https://mlsanity.com/paper/2507.05154/) (2025)
- [EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation](https://mlsanity.com/paper/2503.22357/) (2025)
- [BabyNet: Residual Transformer Module for Birth Weight Prediction on Fetal Ultrasound Video](https://mlsanity.com/paper/2205.09382/) (2022)
- [Memory transformers for full context and high-resolution 3D Medical Segmentation](https://mlsanity.com/paper/2210.05313/) (2022)
- [Hierarchical Vision Transformers for Cardiac Ejection Fraction Estimation](https://mlsanity.com/paper/2304.00177/) (2023)
- [EchoNarrator: Generating natural text explanations for ejection fraction predictions](https://mlsanity.com/paper/2410.23744/) (2024)
- [Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification](https://mlsanity.com/paper/2411.04956/) (2024)
- [ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography](https://mlsanity.com/paper/2512.03339/) (2025)
- [Cardiac valve event timing in echocardiography using deep learning and triplane recordings](https://mlsanity.com/paper/2403.10156/) (2024)
- [EchoDFKD: Data-Free Knowledge Distillation for Cardiac Ultrasound Segmentation using Synthetic Data](https://mlsanity.com/paper/2409.07566/) (2024)
- [Orientation-Robust Latent Motion Trajectory Learning for Annotation-free Cardiac Phase Detection in Fetal Echocardiography](https://mlsanity.com/paper/2602.06761/) (2026)
- [Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Video](https://mlsanity.com/paper/2602.08202/) (2026)
- [FrameONE: Hierarchical Motion Modeling for Universal Multi-View Echocardiographic Keyframe Detection](https://mlsanity.com/paper/2607.00748/) (2026)
- [ConFormer: A Novel Collection of Deep Learning Models to Assist Cardiologists in the Assessment of Cardiac Function](https://mlsanity.com/paper/2312.08567/) (2023)
- [Echo-E3Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation](https://mlsanity.com/paper/2503.17543/) (2025)
- [Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos](https://mlsanity.com/paper/2503.20258/) (2025)
- [Heart Failure Prediction using Modal Decomposition and Masked Autoencoders for Scarce Echocardiography Databases](https://mlsanity.com/paper/2504.07606/) (2025)
- [Acoustic Index: A Novel AI-Driven Parameter for Cardiac Disease Risk Stratification Using Echocardiography](https://mlsanity.com/paper/2507.13542/) (2025)

## 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.