Publications

Research on efficient medical image generation, diversity, and patient-data memorization.

Papers and conference abstracts on generative medical imaging. Grouped by citation year; publication details distinguish online and conference dates.

2027

MICCAI 2026 · Conference paper

CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis

Marvin Seyfarth, Sarah Kaye Müller, Arman Ghanaat, Isabelle Ayx, Fabian Fastenrath, Philipp Wild, Alexander Hertel, Theano Papavassiliu, Salman Ul Hassan Dar, Sandy Engelhardt.

A fully 4D latent-diffusion framework for short-axis cine CMR synthesis.

Paper Code

MICCAI 2026 · Conference paper

VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers

Marvin Seyfarth, Salman Ul Hassan Dar, Yannik Frisch, Philipp Wild, Norbert Frey, Florian André, Sandy Engelhardt.

Transformer-based 3D medical-image synthesis with mask-based spatial control.

Paper Code

2026

BVM 2026 · Conference paper

Rethinking Diversity Metrics in Medical Imaging with Wasserstein Distance

Marvin Seyfarth, Salman U. H. Dar, Sandy Engelhardt.

A feature-space diversity metric for medical-image datasets.

Paper

ESC Digital & AI Summit · Conference abstract

Latent diffusion for single-pass full 4D cine cardiac magnetic resonance imaging synthesis with spatiotemporal autoencoding

M Seyfarth, S K Mueller, S U H Dar, S Engelhardt.

Single-pass full 4D cine cardiac MRI synthesis with spatiotemporal autoencoding.

Paper

ESC Digital & AI Summit · Conference abstract

Beyond visual realism: assessing coronary artery dominance diversity in AI-generated synthetic coronary computed tomography angiography images

A Ghanaat, M Seyfarth, I Ayx, S O Schoenberg, S Engelhardt, S U H Dar.

Assessing coronary-artery dominance diversity in synthetic coronary CTA.

Paper

Nature Biomedical Engineering · Journal article

Unconditional latent diffusion models memorize patient imaging data

Salman Ul Hassan Dar, Marvin Seyfarth, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, Robert Malte Siepmann, Fabian Christopher Laqua, Jannik Kahmann, Norbert Frey, Bettina Baeßler, Sebastian Foersch, Daniel Truhn, Jakob Nikolas Kather, Sandy Engelhardt.

An assessment of patient-data memorization in unconditional latent diffusion models.

Paper Code

SASHIMI 2025 · Conference paper

MedLoRD: A Medical Low-Resource Diffusion Model for High-Resolution 3D CT Image Synthesis

Marvin Seyfarth, Salman Ul Hassan Dar, Isabelle Ayx, Matthias Alexander Fink, Stefan O. Schoenberg, Hans-Ulrich Kauczor, Sandy Engelhardt.

High-resolution 3D CT image synthesis under limited computational resources.

Paper Code

2025

SASHIMI 2024 · Conference paper

Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis

Marvin Seyfarth, Salman Ul Hassan Dar, Sandy Engelhardt.

An analysis of carbon emissions in 2D and 3D latent diffusion synthesis.

Paper