Hsin-Hao Yu1, Stefan R Maetschke2, Bhavna J Antony2, Hiroshi Ishikawa3, Gadi Wollstein3, Joel S Schuman4, Rahil Garnavi2. 1. IBM Research Australia, Melbourne, Victoria, Australia. Electronic address: hsin-hao.yu@au1.ibm.com. 2. IBM Research Australia, Melbourne, Victoria, Australia. 3. Department of Ophthalmology, NYU Langone Health, New York, New York; Department of Biomedical Engineering, NYU Tandon School of Engineering, New York, New York; Center for Neural Science, NYU, New York, New York. 4. Department of Ophthalmology, NYU Langone Health, New York, New York; Department of Biomedical Engineering, NYU Tandon School of Engineering, New York, New York; Center for Neural Science, NYU, New York, New York; Department of Physiology and Neuroscience, NYU Langone Health, New York, New York; Department of Electrical and Computer Engineering, NYU Tandon School of Engineering, New York, New York.
Abstract
PURPOSE: To evaluate the accuracy at which visual field global indices could be estimated from OCT scans of the retina using deep neural networks and to quantify the contributions to the estimates by the macula (MAC) and the optic nerve head (ONH). DESIGN: Observational cohort study. PARTICIPANTS: A total of 10 370 eyes from 109 healthy patients, 697 glaucoma suspects, and 872 patients with glaucoma over multiple visits (median = 3). METHODS: Three-dimensional convolutional neural networks were trained to estimate global visual field indices derived from automated Humphrey perimetry (SITA 24-2) tests (Zeiss, Dublin, CA), using OCT scans centered on MAC, ONH, or both (MAC + ONH) as inputs. MAIN OUTCOME MEASURES: Spearman's rank correlation coefficients, Pearson's correlation coefficient, and absolute errors calculated for 2 indices: visual field index (VFI) and mean deviation (MD). RESULTS: The MAC + ONH achieved 0.76 Spearman's correlation coefficient and 0.87 Pearson's correlation for VFI and MD. Median absolute error was 2.7 for VFI and 1.57 decibels (dB) for MD. Separate MAC or ONH estimates were significantly less correlated and less accurate. Accuracy was dependent on the OCT signal strength and the stage of glaucoma severity. CONCLUSIONS: The accuracy of global visual field indices estimate is improved by integrating information from MAC and ONH in advanced glaucoma, suggesting that structural changes of the 2 regions have different time courses in the disease severity spectrum.
PURPOSE: To evaluate the accuracy at which visual field global indices could be estimated from OCT scans of the retina using deep neural networks and to quantify the contributions to the estimates by the macula (MAC) and the optic nerve head (ONH). DESIGN: Observational cohort study. PARTICIPANTS: A total of 10 370 eyes from 109 healthy patients, 697 glaucoma suspects, and 872 patients with glaucoma over multiple visits (median = 3). METHODS: Three-dimensional convolutional neural networks were trained to estimate global visual field indices derived from automated Humphrey perimetry (SITA 24-2) tests (Zeiss, Dublin, CA), using OCT scans centered on MAC, ONH, or both (MAC + ONH) as inputs. MAIN OUTCOME MEASURES: Spearman's rank correlation coefficients, Pearson's correlation coefficient, and absolute errors calculated for 2 indices: visual field index (VFI) and mean deviation (MD). RESULTS: The MAC + ONH achieved 0.76 Spearman's correlation coefficient and 0.87 Pearson's correlation for VFI and MD. Median absolute error was 2.7 for VFI and 1.57 decibels (dB) for MD. Separate MAC or ONH estimates were significantly less correlated and less accurate. Accuracy was dependent on the OCT signal strength and the stage of glaucoma severity. CONCLUSIONS: The accuracy of global visual field indices estimate is improved by integrating information from MAC and ONH in advanced glaucoma, suggesting that structural changes of the 2 regions have different time courses in the disease severity spectrum.
Authors: Mauro T Leite; Linda M Zangwill; Robert N Weinreb; Harsha L Rao; Luciana M Alencar; Felipe A Medeiros Journal: J Glaucoma Date: 2012-01 Impact factor: 2.503
Authors: Christopher Bowd; Linda M Zangwill; Felipe A Medeiros; Ivan M Tavares; Esther M Hoffmann; Rupert R Bourne; Pamela A Sample; Robert N Weinreb Journal: Invest Ophthalmol Vis Sci Date: 2006-07 Impact factor: 4.799
Authors: Akram Belghith; Felipe A Medeiros; Christopher Bowd; Jeffrey M Liebmann; Christopher A Girkin; Robert N Weinreb; Linda M Zangwill Journal: Invest Ophthalmol Vis Sci Date: 2016-07-01 Impact factor: 4.799
Authors: Eduardo B Mariottoni; Shounak Datta; David Dov; Alessandro A Jammal; Samuel I Berchuck; Ivan M Tavares; Lawrence Carin; Felipe A Medeiros Journal: Transl Vis Sci Technol Date: 2020-03-30 Impact factor: 3.283
Authors: Yuka Kihara; Giovanni Montesano; Andrew Chen; Nishani Amerasinghe; Chrysostomos Dimitriou; Aby Jacob; Almira Chabi; David P Crabb; Aaron Y Lee Journal: Ophthalmology Date: 2022-02-21 Impact factor: 14.277
Authors: Xiaoqin Huang; Jian Sun; Juleke Majoor; Koenraad Arndt Vermeer; Hans Lemij; Tobias Elze; Mengyu Wang; Michael Vincent Boland; Louis Robert Pasquale; Vahid Mohammadzadeh; Kouros Nouri-Mahdavi; Chris Johnson; Siamak Yousefi Journal: Transl Vis Sci Technol Date: 2021-08-02 Impact factor: 3.283
Authors: Joel S Schuman; Maria De Los Angeles Ramos Cadena; Rebecca McGee; Lama A Al-Aswad; Felipe A Medeiros Journal: Ophthalmol Glaucoma Date: 2021-12-22
Authors: Ruben Hemelings; Bart Elen; João Barbosa-Breda; Erwin Bellon; Matthew B Blaschko; Patrick De Boever; Ingeborg Stalmans Journal: Transl Vis Sci Technol Date: 2022-08-01 Impact factor: 3.048
Authors: Shounak Datta; Eduardo B Mariottoni; David Dov; Alessandro A Jammal; Lawrence Carin; Felipe A Medeiros Journal: Sci Rep Date: 2021-06-15 Impact factor: 4.379