Noninvasive cell differentiation discrimination using depth learning
| Project/Area Number |
16K12526
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Life / Health / Medical informatics
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
Hirohiko Niioka 大阪大学, データビリティフロンティア機構, 特任准教授(常勤) (70552074)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
田川 聖一 大阪大学, 産業科学研究所, その他 (60592764)
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 深層学習 / ディープラーニング / 人工知能 / 再生医療 / 細胞分化 / 顕微鏡 / 内視鏡 / ラマン分光 / 画像解析 / 位相差顕微鏡 / ラマン顕微鏡 / スペクトル解析 / 機械学習 / 生物・生体工学 / 再生医学 |
|---|
| Outline of Final Research Achievements |
We have constructed a technique that judge the differentiation of cells and cell types noninvasively without using fluorescent molecules etc. by using depth learning. The date when differentiation of C2C12 (myoblast) starts is defined as Day 0. The phase contrast microscopy image data of Day 0, Day 3, Day 6 was classified with CNN (Convolutional Neural Network), and the accuracy of 91.8% was achieved. In addition, DNN (Deep Neural Network) succeeded in classifying Raman spectral data derived from three kinds of biological tissues with an accuracy of 86.2%. Furthermore, by using anti-Stokes Raman scattering (CARS), data acquisition time was greatly improved.
|
Report
(3 results)
Research Products
(27 results)
