| Project/Area Number |
17H06488
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Radiation science
|
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
Toyonaga Takuya 北海道大学, 医学研究院, 客員研究員 (20804149)
|
|---|
| Project Period (FY) |
2017-08-25 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 脳腫瘍 / 低酸素 / ポジトロン断層撮影法 / PET / ダイナミック造影MRI / イメージング / 機械学習 / MRI / FDG / 深層学習 / ディープラーニング / FMISO |
|---|
| Outline of Final Research Achievements |
We designed a study to predict hypoxia in brain tumors using imaging modalities that can be taken with existing equipment and devices used in daily clinical practice.
18F-fluoromisonidazole (FMISO) (PET tracer designed to detect hypoxia region) were used to evaluate in vivo hypoxia in the brain tumors. widely available imaging modalities were used to predict the FMISO uptake, including 18F-FDG PET (FDG: PET tracer commonly used to estimate the glucose metabolism and in the diagnosis of malignancies), MRI and contrast-enhanced MRI. When these image results were analyzed by machine learning algorithm, hypoxia (FMISO uptake) could be predicted with high accuracy.
|
| Academic Significance and Societal Importance of the Research Achievements |
悪性腫瘍における低酸素状態は腫瘍悪性度との関係性が示唆されており、脳腫瘍において低酸素状態を評価することは、術前に悪性度を予測可能にするだけではなく、手術範囲の決定に重要な情報を与える。一方で、低酸素状態の評価に用いる18F-FMISOなどのPET製剤は、ごく限られた施設でしか使用できず、日常的に使用可能な画像検査で低酸素状態を予測できれば臨床的なインパクトは大きい。
今回の検討で18F-FDG PETやMRI画像を用いると、高い精度で低酸素状態が予測可能であることが示せた。今後は本研究を発展させ、より高い精度を示す腫瘍低酸素の予測モデルの開発を目指す。
|
