Deep Learning Estimation of 10-2 Visual Field Map Based on Macular Optical Coherence Tomography Angiography Measurements.

Autor:	Mahmoudinezhad G; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Moghimi S; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Cheng J; Department of Electrical and Computer Engineering (J.C., L.R., K.A., R.D., N.V.), University of California San Diego, La Jolla, California., Ru L; Department of Electrical and Computer Engineering (J.C., L.R., K.A., R.D., N.V.), University of California San Diego, La Jolla, California., Yang D; Department of Computer Science and Engineering (D.Y.), University of California San Diego, La Jolla, California., Agrawal K; Department of Electrical and Computer Engineering (J.C., L.R., K.A., R.D., N.V.), University of California San Diego, La Jolla, California., Dixit R; Department of Electrical and Computer Engineering (J.C., L.R., K.A., R.D., N.V.), University of California San Diego, La Jolla, California., Beheshtaein S; L3Harris Technologies (S.B.), Torrance, California, USA., Du KH; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Latif K; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Gunasegaran G; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Micheletti E; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Nishida T; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Kamalipour A; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Walker E; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Christopher M; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Zangwill L; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California., Vasconcelos N; Department of Electrical and Computer Engineering (J.C., L.R., K.A., R.D., N.V.), University of California San Diego, La Jolla, California., Weinreb RN; From the Hamilton Glaucoma Center (G.M., S.M., K.H.D., K.L., G.G., E.M., T.N., A.K., E.W., M.C., L.Z., R.N.W.), Shiley Eye Institute, Viterbi Family Department of Ophthalmology, UC San Diego, La Jolla, California. Electronic address: rweinreb@ucsd.edu.
Jazyk:	angličtina
Zdroj:	American journal of ophthalmology [Am J Ophthalmol] 2024 Jan; Vol. 257, pp. 187-200. Date of Electronic Publication: 2023 Sep 19.
DOI:	10.1016/j.ajo.2023.09.014
Abstrakt:	Purpose: To develop deep learning (DL) models estimating the central visual field (VF) from optical coherence tomography angiography (OCTA) vessel density (VD) measurements. Design: Development and validation of a deep learning model. Methods: A total of 1051 10-2 VF OCTA pairs from healthy, glaucoma suspects, and glaucoma eyes were included. DL models were trained on en face macula VD images from OCTA to estimate 10-2 mean deviation (MD), pattern standard deviation (PSD), 68 total deviation (TD) and pattern deviation (PD) values and compared with a linear regression (LR) model with the same input. Accuracy of the models was evaluated by calculating the average mean absolute error (MAE) and the R 2 (squared Pearson correlation coefficients) of the estimated and actual VF values. Results: DL models predicting 10-2 MD achieved R 2 of 0.85 (95% confidence interval [CI], 74-0.92) for 10-2 MD and MAEs of 1.76 dB (95% CI, 1.39-2.17 dB) for MD. This was significantly better than mean linear estimates for 10-2 MD. The DL model outperformed the LR model for the estimation of pointwise TD values with an average MAE of 2.48 dB (95% CI, 1.99-3.02) and R 2 of 0.69 (95% CI, 0.57-0.76) over all test points. The DL model outperformed the LR model for the estimation of all sectors. Conclusions: DL models enable the estimation of VF loss from OCTA images with high accuracy. Applying DL to the OCTA images may enhance clinical decision making. It also may improve individualized patient care and risk stratification of patients who are at risk for central VF damage. (Copyright © 2023 Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu Full Text from ScienceDirect