Dataset Distillation for Medical Dataset Sharing
This addresses privacy and cost problems for hospitals in medical data sharing, but it is incremental as it applies an existing dataset distillation technique to a new domain.
The paper tackles the challenge of sharing medical datasets between hospitals due to privacy and cost issues by proposing a dataset distillation method that synthesizes a small dataset, achieving high detection performance on a COVID-19 chest X-ray image dataset with scarce anonymized images.
Sharing medical datasets between hospitals is challenging because of the privacy-protection problem and the massive cost of transmitting and storing many high-resolution medical images. However, dataset distillation can synthesize a small dataset such that models trained on it achieve comparable performance with the original large dataset, which shows potential for solving the existing medical sharing problems. Hence, this paper proposes a novel dataset distillation-based method for medical dataset sharing. Experimental results on a COVID-19 chest X-ray image dataset show that our method can achieve high detection performance even using scarce anonymized chest X-ray images.