Deep learning cardiac motion analysis for human survival prediction

Abstract

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.

References in corpus (3)

• A Survey on Deep Learning in Medical Image Analysis
• MissForest - nonparametric missing value imputation for mixed-type data
• DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network

Cited by in corpus (10)

• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Deep learning for cardiac image segmentation: A review
• Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis
• An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation
• WarpPINN: Cine-MR image registration with physics-informed neural networks
• Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction
• A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics
• Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders
• CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Network
• CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs