# Echocardiography Segmentation with Enforced Temporal Consistency

arXiv: https://arxiv.org/abs/2112.02102 · HTML: https://mlsanity.com/paper/2112.02102/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 3 Dec 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [Fader Networks: Manipulating Images by Sliding Attributes](https://mlsanity.com/paper/1706.00409/) (2017)
- [Disentangled Representation Learning in Cardiac Image Analysis](https://mlsanity.com/paper/1903.09467/) (2019)
- [Cardiac Segmentation with Strong Anatomical Guarantees](https://mlsanity.com/paper/2006.08825/) (2020)
- [Global and Local Interpretability for Cardiac MRI Classification](https://mlsanity.com/paper/1906.06188/) (2019)
- [Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE](https://mlsanity.com/paper/2007.04780/) (2020)
- [Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction](https://mlsanity.com/paper/2006.13811/) (2020)
- [A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing](https://mlsanity.com/paper/1405.5208/) (2014)
- [Temporal Consistency Objectives Regularize the Learning of Disentangled Representations](https://mlsanity.com/paper/1908.11330/) (2019)

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

- [Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders](https://mlsanity.com/paper/2203.10417/) (2022)
- [Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos](https://mlsanity.com/paper/2210.11291/) (2022)
- [Extraction of volumetric indices from echocardiography: which deep learning solution for clinical use?](https://mlsanity.com/paper/2305.01997/) (2023)
- [Low Complexity Point Tracking of the Myocardium in 2D Echocardiography](https://mlsanity.com/paper/2503.10431/) (2025)
- [Text-Promptable Propagation for Referring Medical Image Sequence Segmentation](https://mlsanity.com/paper/2502.11093/) (2025)
- [Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification](https://mlsanity.com/paper/2401.07796/) (2024)
- [Echocardiography Segmentation Using Neural ODE-based Diffeomorphic Registration Field](https://mlsanity.com/paper/2306.09687/) (2023)
- [Phase Unwrapping of Color Doppler Echocardiography using Deep Learning](https://mlsanity.com/paper/2306.13695/) (2023)
- [Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning](https://mlsanity.com/paper/2406.17902/) (2024)
- [Left Ventricle Contouring of Apical Three-Chamber Views on 2D Echocardiography](https://mlsanity.com/paper/2207.06330/) (2022)
- [Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels](https://mlsanity.com/paper/2308.07717/) (2023)
- [FFPN: Fourier Feature Pyramid Network for Ultrasound Image Segmentation](https://mlsanity.com/paper/2308.13790/) (2023)
- [SimLVSeg: Simplifying Left Ventricular Segmentation in 2D+Time Echocardiograms with Self- and Weakly-Supervised Learning](https://mlsanity.com/paper/2310.00454/) (2023)
- [Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling](https://mlsanity.com/paper/2403.07818/) (2024)
- [Using Foundation Models as Pseudo-Label Generators for Pre-Clinical 4D Cardiac CT Segmentation](https://mlsanity.com/paper/2505.09564/) (2025)
- [3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices](https://mlsanity.com/paper/2507.02411/) (2025)
- [Hierarchical Spatio-temporal Segmentation Network for Ejection Fraction Estimation in Echocardiography Videos](https://mlsanity.com/paper/2508.18681/) (2025)
- [Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation](https://mlsanity.com/paper/2510.14244/) (2025)
- [GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule](https://mlsanity.com/paper/2512.10252/) (2025)
- [A texture-based framework for foundational ultrasound models](https://mlsanity.com/paper/2602.01444/) (2026)
- [Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?](https://mlsanity.com/paper/2605.28697/) (2026)
- [A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation](https://mlsanity.com/paper/2412.00715/) (2024)
- [Evaluation of state-of-the-art deep learning models in the segmentation of the heart ventricles in parasternal short-axis echocardiograms](https://mlsanity.com/paper/2503.08970/) (2025)
- [BOTM: Echocardiography Segmentation via Bi-directional Optimal Token Matching](https://mlsanity.com/paper/2505.18052/) (2025)
- [Echo-DND: A dual noise diffusion model for robust and precise left ventricle segmentation in echocardiography](https://mlsanity.com/paper/2506.15166/) (2025)
- [Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos](https://mlsanity.com/paper/2603.00881/) (2026)
- [Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching](https://mlsanity.com/paper/2603.06471/) (2026)
- [EchoAgent: Towards Reliable Echocardiography Interpretation with "Eyes","Hands" and "Minds"](https://mlsanity.com/paper/2604.05541/) (2026)
- [EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function](https://mlsanity.com/paper/2605.05447/) (2026)
- [Self-Supervised Temporal Regularization for Landmark-Based Cardiac Segmentation with Automatic AHA Regional Mapping](https://mlsanity.com/paper/2606.31785/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNN) have demonstrated their ability to segment 2D cardiac ultrasound images. However, despite recent successes according to which the intra-observer variability on end-diastole and end-systole images has been reached, CNNs still struggle to leverage temporal information to provide accurate and temporally consistent segmentation maps across the whole cycle. Such consistency is required to accurately describe the cardiac function, a necessary step in diagnosing many cardiovascular diseases. In this paper, we propose a framework to learn the 2D+time apical long-axis cardiac shape such that the segmented sequences can benefit from temporal and anatomical consistency constraints. Our method is a post-processing that takes as input segmented echocardiographic sequences produced by any state-of-the-art method and processes it in two steps to (i) identify spatio-temporal inconsistencies according to the overall dynamics of the cardiac sequence and (ii) correct the inconsistencies. The identification and correction of cardiac inconsistencies relies on a constrained autoencoder trained to learn a physiologically interpretable embedding of cardiac shapes, where we can both detect and fix anomalies. We tested our framework on 98 full-cycle sequences from the CAMUS dataset, which are available alongside this paper. Our temporal regularization method not only improves the accuracy of the segmentation across the whole sequences, but also enforces temporal and anatomical consistency.