CompDiff enables fair and zero shot medical image generation across demographic intersections through compositional diffusion

Abstract Medical image generators trained on imbalanced data can fail at demographic intersections absent from training. We introduce CompDiff, which encodes age, sex and race separately and composes supervised demographic tokens alongside clinical text. Across chest radiographs and fundus images, CompDiff improves overall and subgroup fidelity relative to prompt conditioning (RoentGen-v2) and loss reweighting (FairDiffusion). It generalises in zero-shot generation to 16 chest X-ray intersections excluded from training, achieving the lowest mean FID-RadImageNet in every intersection. In a blinded reader study of these unseen intersections, two radiologists gave CompDiff the highest mean scores among generators for anatomical realism and agreement with the clinical impression, and selected its images most often as the most realistic. Pretraining with CompDiff images improved downstream classification, while CompDiff audit cohorts reduced estimation error on rare intersections. These findings support compositional demographic conditioning for extending medical image synthesis to underserved populations.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-13
DOI
https://doi.org/10.21203/rs.3.rs-11128264/v1
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

CompDiff enables fair and zero shot medical image generation across demographic intersections through compositional diffusion

Bart Elen, Ahmad Jiblawi, Michel Dumontier, Gökhan Ertaylan et al.
1 links
Research Square
Generative Adversarial Networks and Image Synthesis
preprint

CompDiff enables fair and zero shot medical image generation across demographic intersections through compositional diffusion

Bart Elen, Ahmad Jiblawi, Michel Dumontier, Gökhan Ertaylan, Chang Sun, Mahmoud Ibrahim, Mohammed M. Saleh, Maryam K. Ibrahim
preprint en

Abstract

Abstract Medical image generators trained on imbalanced data can fail at demographic intersections absent from training. We introduce CompDiff, which encodes age, sex and race separately and composes supervised demographic tokens alongside clinical text. Across chest radiographs and fundus images, CompDiff improves overall and subgroup fidelity relative to prompt conditioning (RoentGen-v2) and loss reweighting (FairDiffusion). It generalises in zero-shot generation to 16 chest X-ray intersections excluded from training, achieving the lowest mean FID-RadImageNet in every intersection. In a blinded reader study of these unseen intersections, two radiologists gave CompDiff the highest mean scores among generators for anatomical realism and agreement with the clinical impression, and selected its images most often as the most realistic. Pretraining with CompDiff images improved downstream classification, while CompDiff audit cohorts reduced estimation error on rare intersections. These findings support compositional demographic conditioning for extending medical image synthesis to underserved populations.

Research Square
Maastricht University (NL), Massachusetts General Hospital (US), Flemish Institute for Technological Research (BE), Icahn School of Medicine at Mount Sinai (US)
European Commission, HORIZON EUROPE Framework Programme
Reduced inequalities, Good health and well-being
Generative Adversarial Networks and Image Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon