| Project/Area Number |
16K19226
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Medical Physics and Radiological Technology
|
|---|
| Research Institution | Niigata University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 強度変調放射線治療 / 機械学習 / ラジオミクス / IMRT / 放射線 / Ｘ線 |
|---|
| Outline of Final Research Achievements |
Intensity-modulated radiation therapy (IMRT) is a technique of radiation therapy with a relatively large dose uncertainty. IMRT dose verification is performed to assure that the radiation dose is accurately irradiated. The most commonly used “gamma analysis” method in IMRT dose verification has a problem that it is difficult to identify the cause of the error (failure mode). In this study, we constructed a machine learning model that uses the radiomic features, a widely used method in extracting features from medical images, as learning data set. The model showed high discrimination accuracy for all four analyzed IMRT failure modes. In the future, it may be necessary to verify the accuracy of the machine learning models with actual measured data as learning data set.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は、CTやMRI等の医用画像の特徴量抽出に用いられる事の多かったラジオミクスの手法を、線量分布の特徴量抽出に適用することで有用な情報を引き出そうとする点で新規性が高い。また、本研究はIMRTの患者個別の線量検証における不具合を簡便に検出できるようになることを目指しているため、IMRTの実施に先立っての安全性の担保を以前より簡易的にかつ短時間で実施できるようになることが見込まれる。従って、IMRTの更なる普及や治療可能な患者数の飛躍的な増大につながることが期待される。
|
