| Project/Area Number |
18K15650
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 52040:Radiological sciences-related
|
|---|
| Research Institution | Kansai Medical University |
|---|
Principal Investigator |
ANETAI Yusuke 関西医科大学, 医学部, 助教 (70809376)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2021: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2020: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | 特徴量抽出 / 球面調和関数 / 球面投影 / 微分幾何 / 多様体学習 / 線量分布 / 放射線治療品質の可視化 / 微分幾何学 / 医学物理 / 医用工学 / 機械学習 / 放射線治療計画 / 最適化 |
|---|
| Outline of Final Research Achievements |
In radiotherapy, radiotherapeutic planning is very important process for the treatment. In particular, intensity modulated radiation therapy (IMRT) requires a convergent of radiation dose to the tumor with a reduction of harmful higher dose to normal tissues; therefore, the complex of dose distribution reflects patient-specific conditions (location of the tumor and normal tissues etc.) with facility-specific clinical goals and causes variations between planners. The oncologists can review this dose distribution; however, this process for the distribution is usually qualitative process not quantity. We therefore aimed to quantify the dose distribution itself and successfully achieved to represent numerical information as a feature tensor.
|
| Academic Significance and Societal Importance of the Research Achievements |
線量分布は断面ごとの情報として離散的（１つ１つ独立した状態）に扱われる．そこで，この断面に配置された分布情報を球面に射影し，その複雑な形状を球面調和関数の展開係数へ紐づけて数値化していくことで，特徴を抽出したテンソルあるいはそれを圧縮したスコアとして扱うことができる．この手法は実用的に全線量分布の特徴を定量的にとらえるだけでなく，球面射影と係数化によって高次元（この場合は位置と線量の四次元）の情報を圧縮し効率的に扱った良い例である．このようにして線量分布のような複雑な形状情報を分類することが可能となった．
|
