| Project/Area Number |
15K06145
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Control engineering/System engineering
|
|---|
| Research Institution | The University of Tokushima |
|---|
Principal Investigator |
UENO Junji 徳島大学, 大学院医歯薬学研究部(医学系), 教授 (60116788)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
近藤 正 徳島大学, 大学院医歯薬学研究部(医学系), 名誉教授 (80205559)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | ニューラルネットワーク / ＧＭＤＨ / ＭＤＣＴ / 医用画像診断 / CAD / GMDH / MDCT |
|---|
| Outline of Final Research Achievements |
We proposed the hybrid artificial neural network algorisms of the convolutional neural network (CNN) and the deep GMDH-type neural networks. The deep GMDH-type neural networks can automatically organize the deep neural network architectures which have many hidden layers. These hybrid artificial neural network algorisms were applied to the medical image diagnosis of the liver cancer and the medical image recognitions of the abdominal organs such as spleen. The recognition results were compared with those of the conventional sigmoid function type neural network using the backpropagation algorithm as the learning calculations. It was shown that these proposed algorithms were useful for the medical image recognitions and the medical image diagnosis of the abdominal organs.
|
