| Project/Area Number |
18K07712
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 52040:Radiological sciences-related
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Oishi Naoya 京都大学, 医学研究科, 特定准教授 (40526878)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
藤原 宏志 京都大学, 情報学研究科, 准教授 (00362583)
鈴木 崇士 京都大学, 医学研究科, 特定助教 (10572224)
杉原 玄一 京都大学, 医学研究科, 助教 (70402261)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 深層学習 / MRI / 脳 / 精神神経疾患 / ノイズ除去 / GPGPU / 医用画像工学 |
|---|
| Outline of Final Research Achievements |
In order to improve the signal-to-noise ratio in neuroimaging research, we have newly developed a deep learning-based high-precision denoising algorithm for brain MRI. For small animals, the usefulness of denoising in morphological MRI of psychiatric model rats was clarified. Furthermore, by extending the method, we succeeded in improving the prognosis prediction performance of patients with neuropsychiatric disorders. Thus, we have clarified the usefulness of the deep learning-based high-precision denoising algorithm developed this time for both basic and clinical applications.
|
| Academic Significance and Societal Importance of the Research Achievements |
柔軟性・拡張性の高い深層学習ベースのノイズ除去アルゴリズムを新規に開発し、精神疾患モデルラットの形態MRIに応用することで従来検出しえなかった微小領域の変化を捉えることに成功した点は学術的意義が高いと考えられる。また、本手法を拡張することでMRIから縮約された情報を抽出させ、精神神経疾患患者の予後予測性能向上を果たした点は将来的な臨床応用という観点で社会的意義も高い。
|
