2023 Fiscal Year Final Research Report
Acquisition and Accumulation of Diagnostic Knowledge Based on Deep Learning of Organ and Disease recognitions in Multi-Dimensional Medical Images
Project/Area Number |
20K11827
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 60080:Database-related
|
Research Institution | Gifu University |
Principal Investigator |
|
Project Period (FY) |
2020-04-01 – 2024-03-31
|
Keywords | 医用画像処理 / 深層学習 / 計算機支援診断 |
Outline of Final Research Achievements |
In this study, we constructed a large-scale medical image database for the development of medical AI aimed at efficiently organizing and integrating diverse information such as metabolic function and lesions in the human body on computers, based on the anatomical structures in images, by collecting a vast amount of multidimensional medical images (CT, MRI, PET) . Additionally, we proposed a mechanism for acquiring, accumulating, and transmitting advanced image diagnostic knowledge, including physicians' tacit knowledge, through the fusion of deep learning and dictionary learning, and established a knowledge base for intelligent image diagnostic support. Through these efforts, we have been advancing research towards establishing a machine learning approach that continuously builds upon existing diagnostic knowledge and practical wisdom, enabling adaptation to various diagnostic tasks and aiming for the evolution towards general-purpose AI.
|
Free Research Field |
医用画像処理
|
Academic Significance and Societal Importance of the Research Achievements |
医用画像の利用により,多くの患者の命が救われてきた.高精度の画像診断には,計算機の支援は必要不可欠である.多次元画像に含まれる膨大な情報から,必要な情報を瞬時に見つけることが重要であり,本研究が目指しているシステムは,以上の現実的な問題を解決できる唯一な方法と考える.医師の診断技術が長期的臨床経験の蓄積であり,貴重な「匠の技」である.しかし,臨床経験には,文字で表現できない暗黙知の部分が多く含まれ,他者との共有が困難かつ次の世代へ引き継げない問題がある.この問題を最終的に解決できれば,名医の「匠の技」を計算機の中に蓄積し続けることが可能となり,医学の発展への大きな波及効果が得られる.
|