CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Qiang, Meng, Qingjie, Qiao, Mengyun, Matthews, Paul M., O'Regan, Declan P., Bai, Wenjia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916937574907904
author Ma, Qiang
Meng, Qingjie
Qiao, Mengyun
Matthews, Paul M.
O'Regan, Declan P.
Bai, Wenjia
author_facet Ma, Qiang
Meng, Qingjie
Qiao, Mengyun
Matthews, Paul M.
O'Regan, Declan P.
Bai, Wenjia
contents Learning 3D+t shape completion and generation from multi-view cardiac magnetic resonance (CMR) images requires a large amount of high-resolution 3D whole-heart segmentations (WHS) to capture shape priors. In this work, we leverage flow matching techniques to learn deep generative flows for augmentation, completion, and generation of 3D+t shapes of four cardiac chambers represented implicitly by segmentations. Firstly, we introduce a latent rectified flow to generate 3D cardiac shapes for data augmentation, learnt from a limited number of 3D WHS data. Then, a label completion network is trained on both real and synthetic data to reconstruct 3D+t shapes from sparse multi-view CMR segmentations. Lastly, we propose CardiacFlow, a novel one-step generative flow model for efficient 3D+t four-chamber cardiac shape generation, conditioned on the periodic Gaussian kernel encoding of time frames. The experiments on the WHS datasets demonstrate that flow-based data augmentation reduces geometric errors by 16% in 3D shape completion. The evaluation on the UK Biobank dataset validates that CardiacFlow achieves superior generation quality and periodic consistency compared to existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05754
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching
Ma, Qiang
Meng, Qingjie
Qiao, Mengyun
Matthews, Paul M.
O'Regan, Declan P.
Bai, Wenjia
Image and Video Processing
Learning 3D+t shape completion and generation from multi-view cardiac magnetic resonance (CMR) images requires a large amount of high-resolution 3D whole-heart segmentations (WHS) to capture shape priors. In this work, we leverage flow matching techniques to learn deep generative flows for augmentation, completion, and generation of 3D+t shapes of four cardiac chambers represented implicitly by segmentations. Firstly, we introduce a latent rectified flow to generate 3D cardiac shapes for data augmentation, learnt from a limited number of 3D WHS data. Then, a label completion network is trained on both real and synthetic data to reconstruct 3D+t shapes from sparse multi-view CMR segmentations. Lastly, we propose CardiacFlow, a novel one-step generative flow model for efficient 3D+t four-chamber cardiac shape generation, conditioned on the periodic Gaussian kernel encoding of time frames. The experiments on the WHS datasets demonstrate that flow-based data augmentation reduces geometric errors by 16% in 3D shape completion. The evaluation on the UK Biobank dataset validates that CardiacFlow achieves superior generation quality and periodic consistency compared to existing baselines.
title CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching
topic Image and Video Processing
url https://arxiv.org/abs/2509.05754