Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing

TL;DR

This paper introduces a soft-label dataset distillation technique that compresses large medical image datasets and trained models, enabling efficient and privacy-preserving medical data sharing with maintained diagnostic performance.

Contribution

It proposes a novel method to generate compressed, anonymized medical images and extract essential model weights, significantly reducing data and model size for sharing.

Findings

Compresses tens of thousands of images into a few soft-label images

Reduces trained model size to a few hundredths of the original

Maintains high detection performance with fewer compressed images

Abstract

Background and objective: Sharing of medical data is required to enable the cross-agency flow of healthcare information and construct high-accuracy computer-aided diagnosis systems. However, the large sizes of medical datasets, the massive amount of memory of saved deep convolutional neural network (DCNN) models, and patients' privacy protection are problems that can lead to inefficient medical data sharing. Therefore, this study proposes a novel soft-label dataset distillation method for medical data sharing. Methods: The proposed method distills valid information of medical image data and generates several compressed images with different data distributions for anonymous medical data sharing. Furthermore, our method can extract essential weights of DCNN models to reduce the memory required to save trained models for efficient medical data sharing. Results: The proposed method can compress tens of thousands of images into several soft-label images and reduce the size of a trained model to a few hundredths of its original size. The compressed images obtained after distillation have been visually anonymized; therefore, they do not contain the private information of the patients. Furthermore, we can realize high-detection performance with a small number of compressed images. Conclusions: The experimental results show that the proposed method can improve the efficiency and security of medical data sharing.