Application of Photodynamic Diagnosis (PDD) and Development of Disease Prediction AI for Endoscopy

2022 Fiscal Year Final Research Report

• Project/Area Number: 21K15924
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 53010:Gastroenterology-related
• Research Institution: Tottori University
• Principal Investigator: FUJII Masashi 鳥取大学, 医学部, 特任教員 (40762258)
• Project Period (FY): 2021-04-01 – 2023-03-31
• Keywords: AIモデル / 内視鏡画像 / 病理組織検査

Outline of Final Research Achievements

In the field of gastrointestinal endoscopy, AI technology has made it possible to detect and classify lesions, but the learning process requires a tremendous amount of effort. Therefore, there is a need for techniques that can streamline and automate the training of AI models. In this study, we conducted fundamental research on multiple techniques for automatically generating annotated data for endoscopic image AI. Specifically, we focused on the following: 1) automatic annotation using Photodynamic Diagnosis (PDD) of endoscopic images and pathological histological results, 2) research on AI models for automatic identification of endoscopic image locations, and 3) research on models that output the relationship between endoscopic images and endoscopic operations. Through these studies, we have achieved basic technology for generating annotated data efficiently and automatically, which enables us to perform relearning in an automated or efficient manner.

Free Research Field

消化器内視鏡

Academic Significance and Societal Importance of the Research Achievements

この研究成果は、AIモデルを用いた医療技術について、成長を加速させることができる。消化器内視鏡技術においては、技術をさらに向上させるだけでなく、海外への展開へのハードルを下げることができる。これにより、世界中の人たちが、消化器内視鏡の医療技術の恩恵を享受することができ、消化器がんの早期発見早期治療の一助となる。また、今後の医療安全管理や自動医療、次世代医学教育など、様々な分野に応用が期待できる。