X-ray Recognition: Patient identification from X-rays using a contrastive objective
This work addresses privacy risks for patients in medical imaging by demonstrating accurate patient identification from X-rays, which is an incremental extension of prior research on extracting bio-information.
The paper tackled the problem of patient identification from chest X-rays using deep learning, achieving surprisingly accurate recognition results that highlight privacy concerns in medical imaging.
Recent research demonstrates that deep learning models are capable of precisely extracting bio-information (e.g. race, gender and age) from patients' Chest X-Rays (CXRs). In this paper, we further show that deep learning models are also surprisingly accurate at recognition, i.e., distinguishing CXRs belonging to the same patient from those belonging to different patients. These findings suggest potential privacy considerations that the medical imaging community should consider with the proliferation of large public CXR databases.