Open AccessDetection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm
Author(s) -
Tyler Hyungtaek Rim,
Aaron Lee,
Daniel Shu Wei Ting,
Kelvin Yi Chong Teo,
Bjorn Kaijun Betzler,
Zhen Ling Teo,
Tae Keun Yoo,
Geunyoung Lee,
Youngnam Kim,
Alex T.L. Lin,
Seong Eun Kim,
Yih Chung Tham,
Sung Soo Kim,
ChingYu Cheng,
Tien Yin Wong,
Chui Ming Gemmy Cheung
Publication year - 2020
Publication title -
british journal of ophthalmology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.016
H-Index - 153
eISSN - 1468-2079
pISSN - 0007-1161
DOI - 10.1136/bjophthalmol-2020-316984
Subject(s) - macular degeneration , medicine , optical coherence tomography , receiver operating characteristic , artificial intelligence , population , ophthalmology , data set , algorithm , optometry , pattern recognition (psychology) , computer science , environmental health
The ability of deep learning (DL) algorithms to identify eyes with neovascular age-related macular degeneration (nAMD) from optical coherence tomography (OCT) scans has been previously established. We herewith evaluate the ability of a DL model, showing excellent performance on a Korean data set, to generalse onto an American data set despite ethnic differences. In addition, expert graders were surveyed to verify if the DL model was appropriately identifying lesions indicative of nAMD on the OCT scans.