English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

With the rise and ever-increasing potential of deep learning techniques inrecent years, publicly available medical datasets became a key factor to enablereproducible development of diagnostic algorithms in the medical domain.Medical data contains sensitive patient-related information and is thereforeusually anonymized by removing patient identifiers, e.g., patient names beforepublication. To the best of our knowledge, we are the first to show that awell-trained deep learning system is able to recover the patient identity fromchest X-ray data. We demonstrate this using the publicly available large-scaleChestX-ray14 dataset, a collection of 112,120 frontal-view chest X-ray imagesfrom 30,805 unique patients. Our verification system is able to identifywhether two frontal chest X-ray images are from the same person with an AUC of0.9940 and a classification accuracy of 95.55%. We further highlight that theproposed system is able to reveal the same person even ten and more years afterthe initial scan. When pursuing a retrieval approach, we observe an mAP@R of0.9748 and a precision@1 of 0.9963. Furthermore, we achieve an AUC of up to0.9870 and a precision@1 of up to 0.9444 when evaluating our trained networkson external datasets such as CheXpert and the COVID-19 Image Data Collection.Based on this high identification rate, a potential attacker may leakpatient-related information and additionally cross-reference images to obtainmore information. Thus, there is a great risk of sensitive content falling intounauthorized hands or being disseminated against the will of the concernedpatients. Especially during the COVID-19 pandemic, numerous chest X-raydatasets have been published to advance research. Therefore, such data may bevulnerable to potential attacks by deep learning-based re-identificationalgorithms.

Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data