2020 Fiscal Year Final Research Report
Development of technology to predict and track the position and shape of luminal organs using artificial intelligence
Project/Area Number |
18K15535
|
Research Category |
Grant-in-Aid for Early-Career Scientists
|
Allocation Type | Multi-year Fund |
Review Section |
Basic Section 52040:Radiological sciences-related
|
Research Institution | Hokkaido University |
Principal Investigator |
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Keywords | 人工知能 / セグメンテーション / 適合放射線治療 |
Outline of Final Research Achievements |
When radiotherapy is applied to luminal organs whose position and shape change from day to day, the status of target organ may not match between at the time of treatment planning and the actual time of treatment. In order to realize the optimized radiotherapy according to the position and shape of the target in the daily treatment, this study carried out to develop the technology which enable us to predict and track the position and shape of the organ using artificial intelligence. After machine learning using previously acquired MRI images of 100 patients as teacher data, artificial intelligence successfully delineated the bladder contour with a mean Dice coefficient index of 94.4%.
|
Free Research Field |
放射線治療学
|
Academic Significance and Societal Importance of the Research Achievements |
MRIは放射線被曝なしに画像情報を取得できるため、日々の放射線治療時の臓器の位置や形状を取得する手法として最適である。本研究で、人工知能の機械学習によりMRI画像上で日々の膀胱の位置・形状を高精度に取得できることが示された。この技術は他の管腔臓器においても利用可能であり、MRI撮像機能を搭載した放射線治療装置が既に開発されていることから、本研究はMRIを用いて日々の臓器の位置・形状に最適化した放射線治療(すなわち適合放射線治療)を実現するための礎になる。
|