2023 Fiscal Year Final Research Report
Developing an Explanatory Medical AI System Using Radiological Images
| Project/Area Number |
21K07656
|
|---|
| 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 | Teikyo University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 人工知能 / 医療データ / 説明可能性 / 放射線画像 |
|---|
| Outline of Final Research Achievements |
This study aims to develop a method to enhance the interpretability of the basis of judgment, which has been a significant barrier to the adoption of medical AI in clinical practice. In this study, we developed a method to control the basis of judgment of a model to an anatomically plausible part. Additionally, we conducted applied research on the National Health Insurance Big Data of Osaka Prefecture data and on the prognostic prediction of heart failure patients.
|
| Free Research Field |
医学物理
|
| Academic Significance and Societal Importance of the Research Achievements |
医学AIの性能は，エキスパートの医師に匹敵するほどまで達している分野もあるなかで，臨床の普及の妨げとなっている判断根拠の不透明さを向上させることで，医療AIの普及や，医療の質の向上に大きく貢献できる．
|
