Prediction of the biomarkers of gliomas based on a radiomics analysis

2018 Fiscal Year Final Research Report

• Project/Area Number: 17K16429
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Radiation science
• Research Institution: The University of Tokyo
• Principal Investigator: Takahashi Wataru 東京大学, 医学部附属病院, 助教 (50755668)
• Project Period (FY): 2017-04-01 – 2019-03-31
• Keywords: ラディオミクス

Outline of Final Research Achievements

We analyzed our institutional database for cases of World Health Organization grade II and III gliomas. Previously untreated cases with available isocitrate dehydrogenase (IDH) and 1p/19q status based on multiplex ligation-dependent probe amplification or microsatellite analysis were selected for analysis. Pretreatment T2 weighted-images of all cases were retrospectively evaluated. Radiogenomic features were identified in the Gross tumor volumes. Data were analyzed using L1-norm regularized logistic regression. A leave-one-out cross validation was employed to evaluate the performance of the prediction model. Accuracy, sensitivity, specificity, and area under the receiver operating characteristics curve (AUC) values were calculated as evaluation indices. As a result, the proposed framework was moderately predictive of the 1p/19q codeletion (AUC 0.736). Therefore, we developed a radiogenomics-based framework for non-invasively predicting the 1p/19q codeletion in gliomas.

Free Research Field

放射線治療

Academic Significance and Societal Importance of the Research Achievements

本研究で基盤が確立されたラディオミクスによる遺伝子変異同定モデルを礎に、追加の侵襲なしに多様な予後予測因子を同定するシステムが将来構築されることが期待できる。これによって個々の症例の予後や治療反応性が把握しやすくなるため、治療成績の向上につながる。また、治療非奏功群への不必要な治療介入を回避できるため、副作用の低減および医療費の削減が可能となる。このことはがん治療全体の発展に寄与すると考えられ、本研究の役割は大きい。