Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays

2025/05/22 by Kim, Harim, Wang, Yuhan, Ahn, Minkyu +3
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2505.17311

Abstract

Unsupervised anomaly detection (UAD) in medical imaging is crucial for identifying pathological abnormalities without requiring extensive labeled data. However, existing diffusion-based UAD models rely solely on imaging features, limiting their ability to distinguish between normal anatomical variations and pathological anomalies. To address this, we propose Diff3M, a multi-modal diffusion-based framework that integrates chest X-rays and structured Electronic Health Records (EHRs) for enhanced anomaly detection. Specifically, we introduce a novel image-EHR cross-attention module to incorporate structured clinical context into the image generation process, improving the model's ability to differentiate normal from abnormal features. Additionally, we develop a static masking strategy to enhance the reconstruction of normal-like images from anomalies. Extensive evaluations on CheXpert and MIMIC-CXR/IV demonstrate that Diff3M achieves state-of-the-art performance, outperforming existing UAD methods in medical imaging. Our code is available at this http URL https://github.com/nth221/Diff3M

Citations

• MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs
• MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
• Diffusion Models with Implicit Guidance for Medical Anomaly Detection
• A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI
• Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
• BMAD: Benchmarks for Medical Anomaly Detection
• Unsupervised Anomaly Detection in Medical Images Using Masked Diffusion Model
• CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
• Diffusion Models for Medical Anomaly Detection
• RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR
• Revisiting Deep Learning Models for Tabular Data
• Towards Total Recall in Industrial Anomaly Detection
• PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and\n Localization
• Denoising Diffusion Implicit Models
• Denoising Diffusion Probabilistic Models
• CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and\n Expert Comparison
• GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
• Unsupervised Anomaly Detection with Generative Adversarial Networks to\n Guide Marker Discovery

Related

• Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion model
• Diffusion Models with Implicit Guidance for Medical Anomaly Detection
• Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
• X-ray2CTPA: Leveraging Diffusion Models to Enhance Pulmonary Embolism Classification
• You've Got Two Teachers: Co-evolutionary Image and Report Distillation for Semi-supervised Anatomical Abnormality Detection in Chest X-ray