Abstract
Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful totherequestedconditioning.WepresentCONFLUX,alatentdiffusion model for chest computed tomography (CT): a 3D variational autoencoder compresses each volume, and a rectified-flow transformer generates in the latent space. Generation is conditioned on structured radiological metadata (18 abnormality findings, sex, age, and reconstruction kernel) through adaptive layer normalization. The model leads strong volumetric baselines on tri-planar FrØchet distance (FID 32.3 vs. 74.6 for MAISI) while exposing direct control over clinical attributes. To strengthen that control we add an online reinforcement-learning posttraining stage (group-relative policy optimization) that rewards how reliably a classifier recovers the requested findings from each generated volume. Judged by a separate, independent classifier, post-training removes 47% of the shortfall relative to real-scan reliability. We release the model and a ∼200k synthetic chest-CT dataset with conditioning metadata spanning a wide variety of clinical findings. • •
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_019.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/SASHIMI_019_supp.pdf
Link to Open Review
Open Review Page: https://openreview.net/forum?id=w2Xcf9ZDGj
BibTex
@InProceedings{VanMax_CONFLUX_MICCAISAT2026,
author = { Van Puyvelde, Max AND Gulluk, H. Ibrahim AND Van Criekinge, Wim AND Gevaert, Olivier},
title = { { CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17258},
month = {pending},
page = {pending}
}
