3D high-resolution cardiac segmentation reconstruction from 2d views using conditional variational autoencoders

Biffi C, Cerrolaza JJ, Tarroni G, De Marvao A, Cook SA, O'Regan DP, Rueckert D (2019)

Publication Type: Conference contribution

Publication year: 2019

Journal

Proceedings - International Symposium on Biomedical Imaging

Publisher: IEEE Computer Society

Book Volume: 2019-April

Pages Range: 1643-1646

Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging

Event location: Venice, ITA

ISBN: 9781538636411

DOI: 10.1109/ISBI.2019.8759328

Abstract

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 cines 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 \pm 0.15 and outperformed competing architectures (TL-net, Dice score =82.60\pm 0.23, p=2.2\cdot 10^{-16}).

Involved external institutions

Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB) Medical Research Council GB United Kingdom (GB)

How to cite

APA:

Biffi, C., Cerrolaza, J.J., Tarroni, G., De Marvao, A., Cook, S.A., O'Regan, D.P., & Rueckert, D. (2019). 3D high-resolution cardiac segmentation reconstruction from 2d views using conditional variational autoencoders. In Proceedings - International Symposium on Biomedical Imaging (pp. 1643-1646). Venice, ITA: IEEE Computer Society.

MLA:

Biffi, Carlo, et al. "3D high-resolution cardiac segmentation reconstruction from 2d views using conditional variational autoencoders." Proceedings of the 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, ITA IEEE Computer Society, 2019. 1643-1646.

BibTeX: Download