Nebbia Giacomo, Kumar Sourav, McNamara Stephen Michael, Bridge Christopher, Campbell J Peter, Chiang Michael F, Mandava Naresh, Singh Praveer, Kalpathy-Cramer Jayashree
Ophthalmology Department, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, USA.
NPJ Digit Med. 2025 Jul 22;8(1):469. doi: 10.1038/s41746-025-01801-0.
Foundation models for medical imaging are a prominent research topic, but risks associated with the imaging features they can capture have not been explored. We aimed to assess whether imaging features from foundation models enable patient re-identification and to relate re-identification to demographic features prediction. Our data included Colour Fundus Photos (CFP), Optical Coherence Tomography (OCT) b-scans, and chest x-rays and we reported re-identification rates of 40.3%, 46.3%, and 25.9%, respectively. We reported varying performance on demographic features prediction depending on re-identification status (e.g., AUC-ROC for gender from CFP is 82.1% for re-identified images vs. 76.8% for non-re-identified ones). When training a deep learning model on the re-identification task, we reported performance of 82.3%, 93.9%, and 63.7% at image level on our internal CFP, OCT, and chest x-ray data. We showed that imaging features extracted from foundation models in ophthalmology and radiology include information that can lead to patient re-identification.
医学成像基础模型是一个突出的研究课题，但与它们所能捕捉的成像特征相关的风险尚未得到探索。我们旨在评估基础模型的成像特征是否能够实现患者重新识别，并将重新识别与人口统计学特征预测联系起来。我们的数据包括彩色眼底照片（CFP）、光学相干断层扫描（OCT）B扫描和胸部X光片，我们报告的重新识别率分别为40.3%、46.3%和25.9%。我们报告了根据重新识别状态在人口统计学特征预测方面的不同表现（例如，CFP中性别预测的AUC-ROC，重新识别图像为82.1%，未重新识别图像为76.8%）。在重新识别任务上训练深度学习模型时，我们报告在内部CFP、OCT和胸部X光片数据的图像级别上，性能分别为82.3%、93.9%和63.7%。我们表明，从眼科和放射学基础模型中提取的成像特征包含可能导致患者重新识别的信息。
