Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913854950211584 |
|---|---|
| author | Kim, Harim Wang, Yuhan Ahn, Minkyu Choi, Heeyoul Zhou, Yuyin Hong, Charmgil |
| author_facet | Kim, Harim Wang, Yuhan Ahn, Minkyu Choi, Heeyoul Zhou, Yuyin Hong, Charmgil |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays Kim, Harim Wang, Yuhan Ahn, Minkyu Choi, Heeyoul Zhou, Yuyin Hong, Charmgil Computer Vision and Pattern Recognition Machine Learning 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 |
| title | Harnessing EHRs for Diffusion-based Anomaly Detection on Chest X-rays |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.17311 |