Deep learning based detection of cone photoreceptors with multimodal adaptive optics scanning light ophthalmoscope images of achromatopsia. Biomed Opt Express 2018 Aug 01;9(8):3740-3756
Date
10/20/2018Pubmed ID
30338152Pubmed Central ID
PMC6191607DOI
10.1364/BOE.9.003740Scopus ID
2-s2.0-85051282266 (requires institutional sign-in at Scopus site) 49 CitationsAbstract
Fast and reliable quantification of cone photoreceptors is a bottleneck in the clinical utilization of adaptive optics scanning light ophthalmoscope (AOSLO) systems for the study, diagnosis, and prognosis of retinal diseases. To-date, manual grading has been the sole reliable source of AOSLO quantification, as no automatic method has been reliably utilized for cone detection in real-world low-quality images of diseased retina. We present a novel deep learning based approach that combines information from both the confocal and non-confocal split detector AOSLO modalities to detect cones in subjects with achromatopsia. Our dual-mode deep learning based approach outperforms the state-of-the-art automated techniques and is on a par with human grading.
Author List
Cunefare D, Langlo CS, Patterson EJ, Blau S, Dubra A, Carroll J, Farsiu SAuthors
Joseph J. Carroll PhD Director, Professor in the Ophthalmology and Visual Sciences department at Medical College of WisconsinChristopher Langlo MD, PhD Assistant Professor in the Ophthalmology and Visual Sciences department at Medical College of Wisconsin
