Georgios Lazaridis1, Giovanni Montesano2, Saman Sadeghi Afgeh3, Jibran Mohamed-Noriega4, Sebastien Ourselin5, Marco Lorenzi6, David F Garway-Heath7. 1. From the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology (G.L., G.M., J.M.-N., D.F.G.-H.), London, United Kingdom; Centre for Medical Image Computing, University College London (G.L.), London, United Kingdom. Electronic address: rmaplaz@ucl.ac.uk. 2. From the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology (G.L., G.M., J.M.-N., D.F.G.-H.), London, United Kingdom; Optometry and Visual Sciences, City, University of London, London, United Kingdom. 3. Data Science Institute, City University (S.S.A.), London, United Kingdom. 4. From the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology (G.L., G.M., J.M.-N., D.F.G.-H.), London, United Kingdom; Departamento de Oftalmología, Hospital Universitario (J.M.-N.), UANL, México. 5. School of Biomedical Engineering and Imaging Sciences, King's College London (S.O.), London, United Kingdom and. 6. Université Côte d'Azur, Inria Sophia Antipolis, Epione Research Project (M.L.), Valbonne, France. 7. From the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology (G.L., G.M., J.M.-N., D.F.G.-H.), London, United Kingdom.
Abstract
PURPOSE: To develop and validate a deep learning method of predicting visual function from spectral domain optical coherence tomography (SD-OCT)-derived retinal nerve fiber layer thickness (RNFLT) measurements and corresponding SD-OCT images. DESIGN: Development and evaluation of diagnostic technology. METHODS: Two deep learning ensemble models to predict pointwise VF sensitivity from SD-OCT images (model 1: RNFLT profile only; model 2: RNFLT profile plus SD-OCT image) and 2 reference models were developed. All models were tested in an independent test-retest data set comprising 2181 SD-OCT/VF pairs; the median of ∼10 VFs per eye was taken as the best available estimate (BAE) of the true VF. The performance of single VFs predicting the BAE VF was also evaluated. The training data set comprised 954 eyes of 220 healthy and 332 glaucomatous participants, and the test data set, 144 eyes of 72 glaucomatous participants. The main outcome measures included the pointwise prediction mean error (ME), mean absolute error (MAE), and correlation of predictions with the BAE VF sensitivity. RESULTS: The median mean deviation was -4.17 dB (-14.22 to 0.88). Model 2 had excellent accuracy (ME 0.5 dB, SD 0.8) and overall performance (MAE 2.3 dB, SD 3.1), and significantly (paired t test) outperformed the other methods. For single VFs predicting the BAE VF, the pointwise MAE was 1.5 dB (SD 0.7). The association between SD-OCT and single VF predictions of the BAE pointwise VF sensitivities was R2 = 0.78 and R2 = 0.88, respectively. CONCLUSIONS: Our method outperformed standard statistical and deep learning approaches. Predictions of BAEs from OCT images approached the accuracy of single real VF estimates of the BAE.
PURPOSE: To develop and validate a deep learning method of predicting visual function from spectral domain optical coherence tomography (SD-OCT)-derived retinal nerve fiber layer thickness (RNFLT) measurements and corresponding SD-OCT images. DESIGN: Development and evaluation of diagnostic technology. METHODS: Two deep learning ensemble models to predict pointwise VF sensitivity from SD-OCT images (model 1: RNFLT profile only; model 2: RNFLT profile plus SD-OCT image) and 2 reference models were developed. All models were tested in an independent test-retest data set comprising 2181 SD-OCT/VF pairs; the median of ∼10 VFs per eye was taken as the best available estimate (BAE) of the true VF. The performance of single VFs predicting the BAE VF was also evaluated. The training data set comprised 954 eyes of 220 healthy and 332 glaucomatous participants, and the test data set, 144 eyes of 72 glaucomatous participants. The main outcome measures included the pointwise prediction mean error (ME), mean absolute error (MAE), and correlation of predictions with the BAE VF sensitivity. RESULTS: The median mean deviation was -4.17 dB (-14.22 to 0.88). Model 2 had excellent accuracy (ME 0.5 dB, SD 0.8) and overall performance (MAE 2.3 dB, SD 3.1), and significantly (paired t test) outperformed the other methods. For single VFs predicting the BAE VF, the pointwise MAE was 1.5 dB (SD 0.7). The association between SD-OCT and single VF predictions of the BAE pointwise VF sensitivities was R2 = 0.78 and R2 = 0.88, respectively. CONCLUSIONS: Our method outperformed standard statistical and deep learning approaches. Predictions of BAEs from OCT images approached the accuracy of single real VF estimates of the BAE.
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