Diff3M conditions a diffusion-based chest X-ray anomaly detector on EHR tokens and a checkerboard mask, yielding small AUROC gains over prior medical UAD methods.
Neurocomputing414, 346– 355 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays
Diff3M conditions a diffusion-based chest X-ray anomaly detector on EHR tokens and a checkerboard mask, yielding small AUROC gains over prior medical UAD methods.