[2K5-OS-1a] 医療におけるAIの社会実装に向けて(1/2)

[2K5-OS-1a-05] Application of Automatically Generated Image Database in Pre-training Model for Cystoscopic Image Classification

〇Ryuunosuke Kounosu¹, Hirokazu Nosato², Yuu Nakajima¹ (1. Toho University, 2. National Institute of Advanced Industrial Science and Technology)

Keywords:AI, transfer learning, cystoscopy, deep learning, automatically generated image database

When applying artificial intelligence to medical imaging, deep learning models pre-trained on ImageNet are commonly used. However, ImageNet cannot be used for commercial purposes, making it difficult to put to practical use even if excellent diagnostic support is achieved. Therefore, we propose a method to apply a deep learning model pre-trained on the FractalDB dataset, an automatically generated image dataset, to medical imaging. In this paper, we use cystoscopy images to validate the effectiveness against medical images of proposed pre-training method. As a result, the classification model using FractalDB-1k, which has 1000 classes among FractalDB, as a pre-training model outperformed the classification model trained only on cystoscopy images in terms of Accuracy, Sensitivity, Specificity, F1-Score, Precision, and AUC.