# 3D High-Resolution Cardiac Segmentation Reconstruction from 2D Views using Conditional Variational Autoencoders

arXiv: https://arxiv.org/abs/1902.11000 · HTML: https://mlsanity.com/paper/1902.11000/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 6 of 6)

- [DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method](https://mlsanity.com/paper/2206.07163/) (2022)
- [MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI](https://mlsanity.com/paper/2208.00034/) (2022)
- [Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI with Explicit Cardiac Motion Modeling](https://mlsanity.com/paper/2507.15194/) (2025)
- [Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep Learning Models: A Review](https://mlsanity.com/paper/2210.14909/) (2022)
- [Personalized 4D Whole Heart Geometry Reconstruction from Cine MRI for Cardiac Digital Twins](https://mlsanity.com/paper/2507.15203/) (2025)
- [Fighting MRI Anisotropy: Learning Multiple Cardiac Shapes From a Single Implicit Neural Representation](https://mlsanity.com/paper/2602.11436/) (2026)

## Abstract (arXiv)

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.