Establishment of artificial intelligence (deep learning) system for histological diagnosis and prediction of malignancy in lung cancer
Project/Area Number |
18K07713
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 52040:Radiological sciences-related
|
Research Institution | Osaka University |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
新岡 宏彦 大阪大学, データビリティフロンティア機構, 特任准教授(常勤) (70552074)
富山 憲幸 大阪大学, 医学系研究科, 教授 (50294070)
本多 修 大阪大学, 医学系研究科, 講師 (80324755)
三宅 淳 大阪大学, 国際医工情報センター, 特任教授 (70344174)
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | 人工知能 / CT / 肺癌 / 病理組織診断 / 浸潤成分 / ニューラルネットワーク / 予後 |
Outline of Final Research Achievements |
In this study, an artificial intelligence system was developed in collaboration with the faculty of engineering to predict histopathological diagnosis and malignant potential based on pathological invasiveness from three-dimensional CT data of lung cancer. By comparing the diagnostic performance between the developed artificial intelligence and with thoracic radiologists, the effect of the artificial intelligence on the diagnostic performance for radiologists was also statistically analyzed. In addition, the diagnostic process of the artificial intelligence, which is regarded as a black box, could be visually understood by displaying the area of interest in color on CT images. This research may lead to the construction of diagnostic imaging assistance systems for radiologists and their technological development.
|
Academic Significance and Societal Importance of the Research Achievements |
肺癌は世界的にも最も致死的な癌の一つであり、早期発見・診断を行い、適切な治療を行う必要がある。臨床の場での肺癌診断の最前線として、画像診断の寄与するところは大きいものの、CT画像のみから病理組織診断や浸潤成分を診断するには限界がある。近年、第三次人工知能(AI)ブームが到来し、医療分野においても人工知能技術の開発は目覚ましい。病理組織診断や病理学的浸潤成分、周囲への浸潤予測など腫瘍の悪性度に関するAIを開発することができれば、CT画像のみから、予後因子との関連性の検討や的確な治療方針の選択に役立てることが可能になると期待される。
|
Report
(4 results)
Research Products
(30 results)
-
[Journal Article] Diagnostic performance for pulmonary adenocarcinoma on CT: comparison of radiologists with and without three-dimensional convolutional neural network.2021
Author(s)
Yanagawa M, Niioka H, Kusumoto M, Awai K, Tsubamoto M, Satoh Y, Miyata T, Yoshida Y, Kikuchi N, Hata A, Yamasaki S, Kido S, Nagahara H, Miyake J, Tomiyama N.
-
Journal Title
European Radiology
Volume: 31
Issue: 4
Pages: 1978-1986
DOI
Related Report
Peer Reviewed
-
[Journal Article] Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma: A preliminary study.2019
Author(s)
Yanagawa M, Niioka H, Hata A, Kikuchi N, Honda O, Kurakami H, Morii E, Noguchi M, Watanabe Y, Miyake J, Tomiyama N
-
Journal Title
Medicine (Baltimore)
Volume: 98
Issue: 25
Pages: e16119-e16119
DOI
Related Report
Peer Reviewed / Open Access / Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-