| Project/Area Number |
18H02957
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 56060:Ophthalmology-related
|
|---|
| Research Institution | Kagoshima University |
|---|
Principal Investigator |
Sakamoto taiji 鹿児島大学, 医歯学域医学系, 教授 (10235179)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
原 博満 鹿児島大学, 医歯学域医学系, 教授 (20392079)
渡邊 睦 鹿児島大学, 理工学域工学系, 教授 (50325768)
橋口 照人 鹿児島大学, 医歯学域医学系, 教授 (70250917)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥17,420,000 (Direct Cost: ¥13,400,000、Indirect Cost: ¥4,020,000)
Fiscal Year 2020: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2019: ¥5,850,000 (Direct Cost: ¥4,500,000、Indirect Cost: ¥1,350,000)
Fiscal Year 2018: ¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000)
|
|---|
| Keywords | 画像解析 / 人工知能 / 脈絡膜血管 / 糖尿病網膜症 / 光干渉断層計 / 硝子体 / 画像診断 / 硝子体免疫 / choroid / image analysis / artificial intelligence / deep learning / symmeery / csc / vitreous body / machine learnining / vascular structure / OCT / Choroid / vessels / 自然免疫 / 硝子体細胞 |
|---|
| Outline of Final Research Achievements |
We established a method to quantitatively evaluate irregular images by using artificial intelligence to analyze choroidal OCT images. By applying this method, we obtained new findings on many points such as pachychoroid and diurnal variation (11 related papers). We established an organization called J-CREST to collect disease data efficiently (15 related papers). We analyzed the status of retinal detachment throughout Japan using the J-RD Registry established by the society (5 related papers). Fundus constituent factors were extracted from fundus photographs to prove gender-related factors. This is a new method in which a human discovered new things by analyzing a subject discovered by artificial intelligence. The new technology developed in this project was provided to companies (domestic companies).
|
| Academic Significance and Societal Importance of the Research Achievements |
眼科学の中で十分に解明されなかった、硝子体や脈絡膜の研究に、人工知能を導入することで、今まで定量が不可能であったこれらの組織に新しい光を当てることができた。その過程で得られた人工知能を用いた技術を、画像解析に応用した。この技術は、商業的価値を産むことが考えられたので、日本企業（トプコン社、ニデック社、キャノン社）と共同研究をすることにより、一部は新製品として市場に出すことに成功した。これは、政府が奨励する産学協同の成功例となったと考える。
|
