Accurate segmentation of heart structures imaged by cardiac MR is key for the quantitative analysis of pathology. High-resolution 3D MR sequences enable whole-heart structural imaging but are time-consuming, expensive to acquire and they often require long breath holds that are not suitable for patients. Consequently, multiplanar breath-hold 2D cine sequences are standard practice but are disadvantaged by lack of whole-heart coverage and low through-plane resolution. To address this, we propose a conditional variational autoencoder architecture able to learn a generative model of 3D high-resolution left ventricular (LV) segmentations which is conditioned on three 2D LV segmentations of one short-axis and two long-axis images. By only employing these three 2D segmentations, our model can efficiently reconstruct the 3D high-resolution LV segmentation of a subject. When evaluated on 400 unseen healthy volunteers, our model yielded an average Dice score of 87.92±0.15 and outperformed competing architectures.
@article{arxiv.1902.11000,
title = {3D High-Resolution Cardiac Segmentation Reconstruction from 2D Views using Conditional Variational Autoencoders},
author = {Carlo Biffi and Juan J. Cerrolaza and Giacomo Tarroni and Antonio de Marvao and Stuart A. Cook and Declan P. O'Regan and Daniel Rueckert},
journal= {arXiv preprint arXiv:1902.11000},
year = {2019}
}
Comments
Accepted in IEEE International Symposium on Biomedical Imaging (ISBI 2019)