[2K5-OS-1a] 医療におけるAIの社会実装に向けて(1/2)

[2K5-OS-1a-01] Editable medical image generation

〇Kazuma Kobayashi^1,2, Yasuyuki Takamizawa³, Sono Ito³, Mototaka Miyake³, Yukihide Kanemitsu³, Ryuji Hamamoto^1,2 (1. National Cancer Center Research Institute, 2. RIKEN Center for Advanced Intelligence Project, 3. National Cancer Center Hospital)

Keywords:Self-supervised learning, Synthetic data, Generative adversarial networks

Synthetic data using generative models have been attracting attention in recent years. One promising application of synthetic data in medical imaging is to generate medical images with particular clinical findings to complement the fundamental difficulty to collect large-scale datasets due to privacy concerns. However, generative adversarial networks have an inherent tendency to overfit the most frequent features in a dataset. Therefore, an elaborated approach is needed to obtain synthetic data for specific clinical findings. In this article, we propose a novel image generation pipeline that can incorporate expert knowledge of clinical medicine by editing generated medical images.