| Presentation | 2020-01-29 [Short Paper] Retinal nerve fiber layer analysis on fundus images using CNN trained with OCT data Ryusuke Watanabe, Chisako Muramatsu, Akira Sawada, Xiangrong Zhou, Yuji Hatanaka, Takeshi Hara, Tetsuya Yamamoto, Hiroshi Fujita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Glaucoma is the first leading cause of blindness in Japan. However, glaucoma only has a few warning signs or symptoms. Thus, screening is important to detect glaucoma in early stages. Fundus examination, in which fundus photographs are used, is one of the screening methods for the detection of nerve fiber layer defect (NFLD). In contrast, optic coherence tomography (OCT) examination is not a screening, but a diagnostic exam. Therefore, we investigated the deep learning system using both fundus photographs and OCT examination results to perform a better analysis on the fundus photographs alone. As a result, we could obtain 77% classification accuracy for normal/abnormal regions on fundus images using CNN trained with OCT data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Glaucoma / Retinal Nerve Fiber Layer (RNFL) / Nerve Fiber Layer Defect (NFLD) / Fundus Image / OCT |
| Paper # | MI2019-80 |
| Date of Issue | 2020-01-22 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2020/1/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OKINAWAKEN SEINENKAIKAN |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Engineering, Analysis, Recognition, etc. |
| Chair | Yoshiki Kawata(Tokushima Univ.) |
| Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
| Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
| Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Short Paper] Retinal nerve fiber layer analysis on fundus images using CNN trained with OCT data |
| Sub Title (in English) | |
| Keyword(1) | Glaucoma |
| Keyword(2) | Retinal Nerve Fiber Layer (RNFL) |
| Keyword(3) | Nerve Fiber Layer Defect (NFLD) |
| Keyword(4) | Fundus Image |
| Keyword(5) | OCT |
| 1st Author's Name | Ryusuke Watanabe |
| 1st Author's Affiliation | Gifu University(Gifu Univ.) |
| 2nd Author's Name | Chisako Muramatsu |
| 2nd Author's Affiliation | Shiga University(Shiga Univ.) |
| 3rd Author's Name | Akira Sawada |
| 3rd Author's Affiliation | Gifu University(Gifu Univ.) |
| 4th Author's Name | Xiangrong Zhou |
| 4th Author's Affiliation | Gifu University(Gifu Univ.) |
| 5th Author's Name | Yuji Hatanaka |
| 5th Author's Affiliation | University of Shiga Prefecture(USP) |
| 6th Author's Name | Takeshi Hara |
| 6th Author's Affiliation | Gifu University(Gifu Univ.) |
| 7th Author's Name | Tetsuya Yamamoto |
| 7th Author's Affiliation | Gifu University(Gifu Univ.) |
| 8th Author's Name | Hiroshi Fujita |
| 8th Author's Affiliation | Gifu University(Gifu Univ.) |
| Date | 2020-01-29 |
| Paper # | MI2019-80 |
| Volume (vol) | vol.119 |
| Number (no) | MI-399 |
| Page | pp.pp.71-72(MI), |
| #Pages | 2 |
| Date of Issue | 2020-01-22 (MI) |