2021 Fiscal Year Final Research Report
Development of a methodology for predicting radiation therapy prognosis based on a radiomics with variability of patients in the treatment
| Project/Area Number |
18K15625
|
|---|
| 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 (2020-2021)
The University of Tokyo (2018-2019) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | Radiomics / 予後予測 / 放射線治療 / 患者変動 |
|---|
| Outline of Final Research Achievements |
The purpose of the study was to develop a system for predicting radiation therapy prognosis based on a radiomics with patient’s variability in the treatment. Radiomic features with patient’s variability were extracted from multi-modal medical images acquired in and before the radiation therapy. We developed system for predicting radiation therapy prognosis and factors related to the prognosis using the radiomic features with patient’s variability. We have been suggested that the radiomics-based system with the patient’s variability would be feasible for predicting the radiation therapy prognosis.
|
| Free Research Field |
医学物理学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究において治療時の患者変動を含んだRadiomics特徴量と放射線治療予後との関係を学習させてモデリングすることにより治療時患者変動を考慮した上で予後が予測できる可能性を示した．また，本研究で開発したシステムを用いて予測した予後の結果を治療計画時や治療中にフィードバックすることで患者個々の変動や特徴に最適化されたオーダーメイド放射線治療の実現が期待できる．必要なデータは放射線治療を行なう上で取得される医用画像と予後情報のみであるため，提案したシステムで構築したモデルを用いれば他施設でも簡便に予後を予測することが可能で臨床的な意義が高い．
|
