AI RESEARCH
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
arXiv CS.LG
•
ArXi:2606.01537v1 Announce Type: cross Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present PaCX-MAE, a cross-modal distillation framework that injects physiological priors into chest X-ray (CXR) encoders while remaining strictly unimodal at inference. PaCX-MAE augments in-domain masked autoencoding with a dual contrastive-predictive objective, aligning CXR representations with paired ECG and laboratory embeddings.