Project/Area Number |
17K12740
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Intelligent informatics
|
Research Institution | Kagoshima National College of Technology |
Principal Investigator |
Shota FURUKAWA 鹿児島工業高等専門学校, 情報工学科, 准教授 (50794989)
|
Project Period (FY) |
2017-04-01 – 2020-03-31
|
Project Status |
Completed (Fiscal Year 2019)
|
Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2017: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
Keywords | 眼底画像 / 静脈口径比 / 血管交叉部 / 畳み込みニューラルネット / 血管抽出 / 動静脈交叉部 / Data Augmentation / 交叉部検出 / 二色性反射モデル / 血柱反射 / OCT / 脈波解析 |
Outline of Final Research Achievements |
The vein diameter ratio, an indicator of atherosclerosis, can be obtained from blood vessel intersections of the eye fundus vessels. However, this vein diameter ratio has been assessed subjectively by medical doctors and has not been quantitatively evaluated. In this study, in order to realize a screening system for predicting atherosclerosis, we present a method for extracting blood vessels from eye fundus images and their intersection points. In the blood vessels extraction method, we present two methods. One method is focused on only the blood vessel intersections to reduce the effect of noise. Another is based on the CNN method. To realize highly accurate detection of the blood vessel intersections point, we adopted the CNN, which was also used in the blood vessel extraction method.
|
Academic Significance and Societal Importance of the Research Achievements |
本研究では,眼底画像から自動で血管領域と血管交叉部を検出する手法を開発した.眼底検査では,医師が眼底画像を一枚ごとに診断する必要があるため,医師の負担が大きい.さらに,網膜の血管には微細な血管も存在するため,眼底画像から全ての交叉点を見つけることは熟練した医師であっても容易ではない.そのため,短時間での診断においては血管交叉点の検出漏れが発生する恐れがある.本研究で開発した手法は自動で眼底血管とその交叉部を検出することで,医師の負担を軽減する事が可能だと考えられる.
|