Soft-Label Anonymous Gastric X-ray Image Distillation

TL;DR

This paper introduces a gradient descent-based soft-label image distillation method for anonymizing gastric X-ray images, effectively compressing datasets while protecting patient privacy to enhance medical data sharing.

Contribution

It proposes a novel distillation approach that optimizes images, labels, and learning rates to anonymize and compress medical datasets, improving data sharing efficiency and security.

Findings

Effective dataset compression demonstrated in experiments.

Successful anonymization of medical images to protect privacy.

Enhanced efficiency and security in medical data sharing.

Abstract

This paper presents a soft-label anonymous gastric X-ray image distillation method based on a gradient descent approach. The sharing of medical data is demanded to construct high-accuracy computer-aided diagnosis (CAD) systems. However, the large size of the medical dataset and privacy protection are remaining problems in medical data sharing, which hindered the research of CAD systems. The idea of our distillation method is to extract the valid information of the medical dataset and generate a tiny distilled dataset that has a different data distribution. Different from model distillation, our method aims to find the optimal distilled images, distilled labels and the optimized learning rate. Experimental results show that the proposed method can not only effectively compress the medical dataset but also anonymize medical images to protect the patient's private information. The proposed approach can improve the efficiency and security of medical data sharing.