Study of comprihensive vitreology

2017 Fiscal Year Final Research Report

• Project/Area Number: 15H04996
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Ophthalmology
• 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): 丸山 征郎 鹿児島大学, 医歯学総合研究科, 特任教授 (20082282) ; 原 博満 鹿児島大学, 医歯学域医学系, 教授 (20392079) ; 橋口 照人 鹿児島大学, 医歯学域医学系, 教授 (70250917)
• Co-Investigator(Renkei-kenkyūsha): YAMAGUCHI Munekazu 鹿児島大学, 医歯学域医学系, 准教授 (20325814) ; SONODA Shozo 鹿児島大学, 医歯学域附属病院, 講師 (20325806)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 硝子体 / サイトカイン / 画像処理 / 機械学習

Outline of Final Research Achievements

We focused on the relationship of choroid disease and vitreous disease. By binarizing choroidal image with poor regularity, we succeeded in clarifying relationship between the structural change of choroid and pathological condition change, succeeded in more than 10 collaborative research domestically and overseas by this method, and commercialized. Although this method was a simple method of measuring the area of the processed image, it was a pioneering method and many results were obtained. In the research process, we succeeded in extracting features not noticed in ordinary images by analyzing images mathematically. Furthermore, by learning this feature amount by machine learning, a new structural pattern of the choroid could be obtained. The stratification of the choroid was realized by the Support Vector Machine created here. This means that quantification of choroids and automatic measurement become possible, and we have newly started joint research with domestic companies.

Free Research Field

眼科学