How to Build an AI-Powered Medical Image De-Identification Pipeline for Clinical Research
This article systematically introduces how to build an AI-powered medical image de-identification pipeline that removes PHI from both DICOM metadata and burned-in pixel text via OCR + NER + DICOM processing, ensuring HIPAA compliance.
入选理由:使用EasyOCR检测DICOM图像像素中烧录的文本(burned-in text),再用Stanford NER模型(stanford-deidentifier-base)分类PHI与非PHI。
