PMID- 33901527 OWN - NLM STAT- MEDLINE DCOM- 20211122 LR - 20230517 IS - 1549-4713 (Electronic) IS - 0161-6420 (Linking) VI - 128 IP - 11 DP - 2021 Nov TI - Deep Learning Estimation of 10-2 and 24-2 Visual Field Metrics Based on Thickness Maps from Macula OCT. PG - 1534-1548 LID - S0161-6420(21)00316-X [pii] LID - 10.1016/j.ophtha.2021.04.022 [doi] AB - PURPOSE: To develop deep learning (DL) systems estimating visual function from macula-centered spectral-domain (SD) OCT images. DESIGN: Evaluation of a diagnostic technology. PARTICIPANTS: A total of 2408 10-2 visual field (VF) SD OCT pairs and 2999 24-2 VF SD OCT pairs collected from 645 healthy and glaucoma subjects (1222 eyes). METHODS: Deep learning models were trained on thickness maps from Spectralis macula SD OCT to estimate 10-2 and 24-2 VF mean deviation (MD) and pattern standard deviation (PSD). Individual and combined DL models were trained using thickness data from 6 layers (retinal nerve fiber layer [RNFL], ganglion cell layer [GCL], inner plexiform layer [IPL], ganglion cell-IPL [GCIPL], ganglion cell complex [GCC] and retina). Linear regression of mean layer thicknesses were used for comparison. MAIN OUTCOME MEASURES: Deep learning models were evaluated using R(2) and mean absolute error (MAE) compared with 10-2 and 24-2 VF measurements. RESULTS: Combined DL models estimating 10-2 achieved R(2) of 0.82 (95% confidence interval [CI], 0.68-0.89) for MD and 0.69 (95% CI, 0.55-0.81) for PSD and MAEs of 1.9 dB (95% CI, 1.6-2.4 dB) for MD and 1.5 dB (95% CI, 1.2-1.9 dB) for PSD. This was significantly better than mean thickness estimates for 10-2 MD (0.61 [95% CI, 0.47-0.71] and 3.0 dB [95% CI, 2.5-3.5 dB]) and 10-2 PSD (0.46 [95% CI, 0.31-0.60] and 2.3 dB [95% CI, 1.8-2.7 dB]). Combined DL models estimating 24-2 achieved R(2) of 0.79 (95% CI, 0.72-0.84) for MD and 0.68 (95% CI, 0.53-0.79) for PSD and MAEs of 2.1 dB (95% CI, 1.8-2.5 dB) for MD and 1.5 dB (95% CI, 1.3-1.9 dB) for PSD. This was significantly better than mean thickness estimates for 24-2 MD (0.41 [95% CI, 0.26-0.57] and 3.4 dB [95% CI, 2.7-4.5 dB]) and 24-2 PSD (0.38 [95% CI, 0.20-0.57] and 2.4 dB [95% CI, 2.0-2.8 dB]). The GCIPL (R(2) = 0.79) and GCC (R(2) = 0.75) had the highest performance estimating 10-2 and 24-2 MD, respectively. CONCLUSIONS: Deep learning models improved estimates of functional loss from SD OCT imaging. Accurate estimates can help clinicians to individualize VF testing to patients. CI - Copyright (c) 2021 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved. FAU - Christopher, Mark AU - Christopher M AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Bowd, Christopher AU - Bowd C AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Proudfoot, James A AU - Proudfoot JA AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Belghith, Akram AU - Belghith A AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Goldbaum, Michael H AU - Goldbaum MH AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Rezapour, Jasmin AU - Rezapour J AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California; Department of Ophthalmology, University Medical Center Mainz, Mainz, Germany. FAU - Fazio, Massimo A AU - Fazio MA AD - School of Medicine, University of Alabama-Birmingham, Birmingham, Alabama. FAU - Girkin, Christopher A AU - Girkin CA AD - School of Medicine, University of Alabama-Birmingham, Birmingham, Alabama. FAU - De Moraes, Gustavo AU - De Moraes G AD - Bernard and Shirlee Brown Glaucoma Research Laboratory, Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Medical Center, New York, New York. FAU - Liebmann, Jeffrey M AU - Liebmann JM AD - Bernard and Shirlee Brown Glaucoma Research Laboratory, Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Medical Center, New York, New York. FAU - Weinreb, Robert N AU - Weinreb RN AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. FAU - Zangwill, Linda M AU - Zangwill LM AD - Hamilton Glaucoma Center, Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California, San Diego, La Jolla, California. Electronic address: lzangwill@ucsd.edu. LA - eng GR - K99 EY030942/EY/NEI NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural PT - Research Support, Non-U.S. Gov't DEP - 20210423 PL - United States TA - Ophthalmology JT - Ophthalmology JID - 7802443 SB - IM MH - Aged MH - Benchmarking MH - Cross-Sectional Studies MH - *Deep Learning MH - Female MH - Follow-Up Studies MH - Glaucoma/*diagnosis/physiopathology MH - Humans MH - *Intraocular Pressure MH - Macula Lutea/*diagnostic imaging MH - Male MH - Middle Aged MH - Tomography, Optical Coherence/*methods MH - Visual Fields/*physiology OTO - NOTNLM OT - Deep learning OT - Glaucoma OT - OCT OT - Structure-function OT - Visual field EDAT- 2021/04/27 06:00 MHDA- 2021/11/23 06:00 CRDT- 2021/04/26 20:11 PHST- 2020/07/01 00:00 [received] PHST- 2021/03/16 00:00 [revised] PHST- 2021/04/19 00:00 [accepted] PHST- 2021/04/27 06:00 [pubmed] PHST- 2021/11/23 06:00 [medline] PHST- 2021/04/26 20:11 [entrez] AID - S0161-6420(21)00316-X [pii] AID - 10.1016/j.ophtha.2021.04.022 [doi] PST - ppublish SO - Ophthalmology. 2021 Nov;128(11):1534-1548. doi: 10.1016/j.ophtha.2021.04.022. Epub 2021 Apr 23.