2023 Fiscal Year Final Research Report
Automated diagnostic algorithm for chest CT of occupational lung disease
Project/Area Number |
22K19650
|
Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
Allocation Type | Multi-year Fund |
Review Section |
Medium-sized Section 58:Society medicine, nursing, and related fields
|
Research Institution | Kochi University |
Principal Investigator |
Suganuma Narufumi 高知大学, 教育研究部医療学系連携医学部門, 教授 (50313747)
|
Co-Investigator(Kenkyū-buntansha) |
鈴木 一廣 順天堂大学, 医学部, 准教授 (20338370)
吉田 真一 高知工科大学, 情報学群, 教授 (30334519)
西森 美貴 高知大学, 医学部附属病院, 特任助教 (30760483)
|
Project Period (FY) |
2022-06-30 – 2024-03-31
|
Keywords | 職業性肺疾患 / 画像診断 / 機械学習 / エキスパートシステム |
Outline of Final Research Achievements |
The ILO International Classification of Radiograph of Pneumoconiosis is used for the diagnosis of occupational lung diseases, and the International Classification of HRCT for Occupational Environmental Respiratory Diseases, which we developed, has been proposed to supplement it. In this study, a research team was formed by experts in occupational lung disease, radiology, and artificial intelligence to tackle this issue. We used GAN and other technologies to develop an algorithm for automatic diagnosis of occupational lung diseases using plain chest X-rays, and developed an algorithm with a certain degree of accuracy. Based on this result, we further developed an automatic diagnosis method for CT images with a large number of images for a single case using two approaches: automatic diagnosis and expert system. Aiming to develop a diagnostic system.
|
Free Research Field |
産業医学
|
Academic Significance and Societal Importance of the Research Achievements |
職業性肺疾患は産業保健上の重要な問題であり、その検診の対象者は我が国では25から50万人を数える。それらの有所見率はかつての15%程度から労働衛生の強化により大幅に減少しているものの2%程度存在し訓練を受けた医師によってのみ正確に診断可能である。しかし、このような訓練を受けた医師が少ない現状があり、機械学習により自動判定が可能となれば、国内でのニーズに止まらず、世界の職業性肺疾患に対する課題解決につながる。
|