2023 Fiscal Year Final Research Report
Personalized medical navigation system using radiogenomics
| Project/Area Number |
21K12707
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 90130:Medical systems-related
|
|---|
| Research Institution | University of Miyazaki (2022-2023)
Kumamoto University (2021) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | Radiomics / Radiogenomics / Radioproteomics / Medical AI |
|---|
| Outline of Final Research Achievements |
We measured radiomic features from brain tumors on MR images and developed a method to estimate 1p19q co-deletion using these features. We also developed a user-driven decision support tool to enable oncologists to utilize the computer results. Regarding lung cancer, we developed a method to predict recurrence by using radiomics features and survival time analysis. We also developed a feature selection method that takes into account proportional hazards. We applied the proposed method to breast cancer and developed a method for predicting patients who will achieve pathologic complete response with preoperative drug therapy. We also developed a new method named Radioproteomics to estimate the activity of immune checkpoint molecules from breast MR images.
|
| Free Research Field |
医療AI，医療データサイエンス
|
| Academic Significance and Societal Importance of the Research Achievements |
画像所見がどのような病理・病態を反映しているかの研究は行われてきたが，画像所見と分子・遺伝的背景の理解は進んでいない．本研究では，がんの「遺伝型」と「表現型」の関係を明らかにし，がんの表現型（画像所見）から，がんの遺伝型を推定する手法を構築した．画像検査によって，分子標的薬の効果が予測できること，再発の可能性を予測できること，免疫チェックポイント阻害剤の効果が予測できることなどの研究成果を得た．本研究によって，画像検査は病変検出や鑑別診断だけではなく，至適治療法の選択や予後予測などに応用できるという潜在的価値を明らかにした点で社会的な意義は大きい．
|
