Deep Learning Estimation of 10-2 and 24-2 Visual Field Metrics Based on Thickness Maps from Macula OCT

• Published in: Ophthalmology (Rochester, Minn.) Vol. 128; no. 11; pp. 1534 - 1548
• Main Authors: Christopher, Mark, Bowd, Christopher, Proudfoot, James A., Belghith, Akram, Goldbaum, Michael H., Rezapour, Jasmin, Fazio, Massimo A., Girkin, Christopher A., De Moraes, Gustavo, Liebmann, Jeffrey M., Weinreb, Robert N., Zangwill, Linda M.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.11.2021
• Subjects: Aged; Benchmarking; Cross-Sectional Studies; Deep Learning; Female; Follow-Up Studies; Glaucoma; Glaucoma - diagnosis; Glaucoma - physiopathology; Humans; Intraocular Pressure; Macula Lutea - diagnostic imaging; Male; Middle Aged; OCT; Structure-function; Tomography, Optical Coherence - methods; Visual field; Visual Fields - physiology; Glaucoma; PSD; OCT; GCIPL; IPL; RNFL; Visual field; CI; GCC; DL; ONH; MDEGP; GPU; CAM; Structure-function; Deep learning; ADAGES; MAE; VF; DIGS; GCL; SD; MD
• ISSN: 0161-6420; 1549-4713; 1549-4713
• DOI: 10.1016/j.ophtha.2021.04.022

To develop deep learning (DL) systems estimating visual function from macula-centered spectral-domain (SD) OCT images. Evaluation of a diagnostic technology. 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). 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. Deep learning models were evaluated using R2 and mean absolute error (MAE) compared with 10-2 and 24-2 VF measurements. Combined DL models estimating 10-2 achieved R2 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 R2 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 (R2 = 0.79) and GCC (R2 = 0.75) had the highest performance estimating 10-2 and 24-2 MD, respectively. Deep learning models improved estimates of functional loss from SD OCT imaging. Accurate estimates can help clinicians to individualize VF testing to patients.