| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2016: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Outline of Final Research Achievements |
We constructed a mass spectral database of human non-tumor and cerebral tumor tissues with labels of tumor grades (grade I-IV) and patient information. To confirm the discrimination ability of learning machine (logistic regression)-based diagnostic algorithm, stored data were divided into the sub groups, and leave-one-out cross-validation was performed. As a result, the discrimination accuracy for non-tumor/tumor or tumor grade were over 80%. This result suggest that our system is useful for diagnosis of human cerebral tumor. In addition, we constructed the real-time and remote sampling probe. It enables us to perform intraoperative diagnosis without extirpation of tissues.
|
