CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy

Mengyun Qiao (), Shuo Wang, Huaqi Qiu, Antonio de Marvao, Declan P. O’Regan, Daniel Rueckert and Wenjia Bai ()
Additional contact information
Mengyun Qiao: Imperial College London, Department of Brain Sciences
Shuo Wang: School of Basic Medical Sciences, Fudan University and Shanghai Key Laboratory of MICCAI, Digital Medical Research Center
Huaqi Qiu: MRC Laboratory of Medical Sciences, Imperial College London
Antonio de Marvao: King’s College London, The Department of Women and Children’s Health, and British Heart Foundation Centre of Research Excellence, School of Cardiovascular and Metabolic Medicine and Sciences
Declan P. O’Regan: MRC Laboratory of Medical Sciences, Imperial College London
Daniel Rueckert: Biomedical Image Analysis Group (BioMedIA), Department of Computing, Imperial College London
Wenjia Bai: Imperial College London, Department of Computing

Chapter Chapter 15 in Generative Machine Learning Models in Medical Image Computing, 2025, pp 301-321 from Springer

Abstract: Abstract Cardiac image analysis often involves assessing the heart’s anatomy and motion from images and understanding their association with clinical factors like gender, age, and diseases. While image segmentation and motion tracking algorithms address the first issue, modeling the second remains challenging. In this work, we propose a novel conditional generative model to describe the 4D spatio-temporal anatomy of the heart and its interaction with non-imaging clinical factors. By integrating these clinical factors as conditions, our model can investigate their influence on cardiac anatomy. We evaluate the model’s performance on two main tasks: anatomical sequence completion and sequence generation. It achieves high performance in anatomical sequence completion, comparable to or surpassing state-of-the-art generative models. For sequence generation, the model generates realistic synthetic 4D sequential anatomies that align with real data distributions given clinical conditions. The code and trained generative model are available at https://github.com/MengyunQ/CHeart .

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-80965-1_15

Ordering information: This item can be ordered from
http://www.springer.com/9783031809651

DOI: 10.1007/978-3-031-80965-1_15

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().