| Project/Area Number |
18K15567
|
|---|
| 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 |
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 適応放射線治療 / 人工知能 / 機械学習 / 最適化 / 頭頸部癌 / 医学物理 / 医学物理学 / 頭頚部癌 |
|---|
| Outline of Final Research Achievements |
We developed and verified machine learning-based prediction models of patient deformation during radiotherapy for head and neck cancer.
Data from 120 patients with nasopharynx, oropharynx, hypopharynx, or laryngeal cancer were collected. Patient deformation during radiotherapy was calculated by calculating the displacement vector field between cone-beam CT images at the first and subsequent fractions. The calculated deformation and patient characteristics were used as input parameters to machine learning. Various machine learning algorithms were tested to predict patient deformation. The prediction accuracies of the developed models were verified by comparing the actual patient data.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で行った体形変化予測モデルの構築は、治療成績向上につながる患者個別化した適応放射線治療につながる。更に、適応によるメリットが少ない患者では、治療効果には影響を及ぼさない不要な適応を避けることも可能となる。適応放射線治療の臨床導入負荷を低減させることにつながり、同治療の普及に貢献する。
|
