Synthetic Cardiac MRI Image Generation using Deep Generative Models

TL;DR

This paper reviews recent deep generative models for synthetic cardiac MRI, emphasizing their ability to produce anatomically accurate images, preserve privacy, and improve downstream clinical tasks.

Contribution

It provides a comprehensive comparison of existing CMRI generation methods focusing on fidelity, utility, and privacy, highlighting current limitations and future directions.

Findings

Generative models improve data diversity for training segmentation algorithms.

Anatomically constrained synthesis enhances structural fidelity.

Privacy-preserving techniques mitigate risks of data leakage.

Abstract

Synthetic cardiac MRI (CMRI) generation has emerged as a promising strategy to overcome the scarcity of annotated medical imaging data. Recent advances in GANs, VAEs, diffusion probabilistic models, and flow-matching techniques aim to generate anatomically accurate images while addressing challenges such as limited labeled datasets, vendor variability, and risks of privacy leakage through model memorization. Maskconditioned generation improves structural fidelity by guiding synthesis with segmentation maps, while diffusion and flowmatching models offer strong boundary preservation and efficient deterministic transformations. Cross-domain generalization is further supported through vendor-style conditioning and preprocessing steps like intensity normalization. To ensure privacy, studies increasingly incorporate membership inference attacks, nearest-neighbor analyses, and differential privacy mechanisms. Utility evaluations commonly measure downstream segmentation performance, with evidence showing that anatomically constrained synthetic data can enhance accuracy and robustness across multi-vendor settings. This review aims to compare existing CMRI generation approaches through the lenses of fidelity, utility, and privacy, highlighting current limitations and the need for integrated, evaluation-driven frameworks for reliable clinical workflows.