# Deep learning cardiac motion analysis for human survival prediction

arXiv: https://arxiv.org/abs/1810.03382 · HTML: https://mlsanity.com/paper/1810.03382/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2018.

## Built on by (most cited first, 30 of 31)

- [Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis](https://mlsanity.com/paper/2202.10553/) (2022)
- [A Deep Variational Approach to Clustering Survival Data](https://mlsanity.com/paper/2106.05763/) (2021)
- [Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior](https://mlsanity.com/paper/2206.03830/) (2022)
- [A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics](https://mlsanity.com/paper/2409.13825/) (2024)
- [MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI](https://mlsanity.com/paper/2208.00034/) (2022)
- [WarpPINN: Cine-MR image registration with physics-informed neural networks](https://mlsanity.com/paper/2211.12549/) (2022)
- [DeepMesh: Mesh-based Cardiac Motion Tracking using Deep Learning](https://mlsanity.com/paper/2309.14306/) (2023)
- [Embedding Gradient-based Optimization in Image Registration Networks](https://mlsanity.com/paper/2112.03915/) (2021)
- [Mesh-based 3D Motion Tracking in Cardiac MRI using Deep Learning](https://mlsanity.com/paper/2209.02004/) (2022)
- [BenchECG and xECG: a benchmark and baseline for ECG foundation models](https://mlsanity.com/paper/2509.10151/) (2025)
- [Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction](https://mlsanity.com/paper/2403.10581/) (2024)
- [Modeling 3D cardiac contraction and relaxation with point cloud deformation networks](https://mlsanity.com/paper/2307.10927/) (2023)
- [An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation](https://mlsanity.com/paper/2101.03169/) (2021)
- [Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes](https://mlsanity.com/paper/2111.06152/) (2021)
- [A Federated Cox Model with Non-Proportional Hazards](https://mlsanity.com/paper/2207.05050/) (2022)
- [Position: Machine Learning for Heart Transplant Allocation Policy Optimization Should Account for Incentives](https://mlsanity.com/paper/2602.04990/) (2026)
- [CNN-based Cardiac Motion Extraction to Generate Deformable Geometric Left Ventricle Myocardial Models from Cine MRI](https://mlsanity.com/paper/2103.16695/) (2021)
- [Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation](https://mlsanity.com/paper/2107.07975/) (2021)
- [Assessment of Left Atrium Motion Deformation Through Full Cardiac Cycle](https://mlsanity.com/paper/2405.17518/) (2024)
- [Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation](https://mlsanity.com/paper/2110.11312/) (2021)
- [Interpretable Prediction of Pulmonary Hypertension in Newborns using Echocardiograms](https://mlsanity.com/paper/2203.13038/) (2022)
- [Recent advancement in Disease Diagnostic using machine learning: Systematic survey of decades, comparisons, and challenges](https://mlsanity.com/paper/2308.01319/) (2023)
- [High-Resolution Maps of Left Atrial Displacements and Strains Estimated with 3D Cine MRI using Online Learning Neural Networks](https://mlsanity.com/paper/2312.09387/) (2023)
- [CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Network](https://mlsanity.com/paper/2508.20734/) (2025)
- [Personalized 4D Whole-Heart Mesh Reconstruction from Cine MRI via Multi-Scale Temporal Modeling and Differentiable Contour Rendering](https://mlsanity.com/paper/2607.01952/) (2026)
- [Survival-oriented embeddings for improving accessibility to complex data structures](https://mlsanity.com/paper/2110.11303/) (2021)
- [TripleSurv: Triplet Time-adaptive Coordinate Loss for Survival Analysis](https://mlsanity.com/paper/2401.02708/) (2024)
- [Predicting Pulmonary Hypertension in Newborns: A Multi-view VAE Approach](https://mlsanity.com/paper/2507.11561/) (2025)
- [MCM: Mamba-based Cardiac Motion Tracking using Sequential Images in MRI](https://mlsanity.com/paper/2507.17678/) (2025)
- [Cycle Inverse-Consistent TransMorph: A Balanced Deep Learning Framework for Brain MRI Registration](https://mlsanity.com/paper/2603.21760/) (2026)

## Abstract (arXiv)

Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using a fully convolutional network trained on anatomical shape priors. This dense motion model formed the input to a supervised denoising autoencoder (4Dsurvival), which is a hybrid network consisting of an autoencoder that learns a task-specific latent code representation trained on observed outcome data, yielding a latent representation optimised for survival prediction. To handle right-censored survival outcomes, our network used a Cox partial likelihood loss function. In a study of 302 patients the predictive accuracy (quantified by Harrell's C-index) was significantly higher (p < .0001) for our model C=0.73 (95% CI: 0.68 - 0.78) than the human benchmark of C=0.59 (95% CI: 0.53 - 0.65). This work demonstrates how a complex computer vision task using high-dimensional medical image data can efficiently predict human survival.