Estimation of Visual Function Using Deep Learning From Ultra-Widefield Fundus Images of Eyes With Retinitis Pigmentosa

Abstract

ImportanceThere is no widespread effective treatment to halt the progression of retinitis pigmentosa. Consequently, adequate assessment and estimation of residual visual function are important clinically.ObjectiveTo examine whether deep learning can accurately estimate the visual function of patients with retinitis pigmentosa by using ultra-widefield fundus images obtained on concurrent visits.Design, Setting, and ParticipantsData for this multicenter, retrospective, cross-sectional study were collected between January 1, 2012, and December 31, 2018. This study included 695 consecutive patients with retinitis pigmentosa who were examined at 5 institutions. Each of the 3 types of input images—ultra-widefield pseudocolor images, ultra-widefield fundus autofluorescence images, and both ultra-widefield pseudocolor and fundus autofluorescence images—was paired with 1 of the 31 types of ensemble models constructed from 5 deep learning models (Visual Geometry Group–16, Residual Network–50, InceptionV3, DenseNet121, and EfficientNetB0). We used 848, 212, and 214 images for the training, validation, and testing data, respectively. All data from 1 institution were used for the independent testing data. Data analysis was performed from June 7, 2021, to December 5, 2022.Main Outcomes and MeasuresThe mean deviation on the Humphrey field analyzer, central retinal sensitivity, and best-corrected visual acuity were estimated. The image type–ensemble model combination that yielded the smallest mean absolute error was defined as the model with the best estimation accuracy. After removal of the bias of including both eyes with the generalized linear mixed model, correlations between the actual values of the testing data and the estimated values by the best accuracy model were examined by calculating standardized regression coefficients and P values.ResultsThe study included 1274 eyes of 695 patients. A total of 385 patients were female (55.4%), and the mean (SD) age was 53.9 (17.2) years. Among the 3 types of images, the model using ultra-widefield fundus autofluorescence images alone provided the best estimation accuracy for mean deviation, central sensitivity, and visual acuity. Standardized regression coefficients were 0.684 (95% CI, 0.567-0.802) for the mean deviation estimation, 0.697 (95% CI, 0.590-0.804) for the central sensitivity estimation, and 0.309 (95% CI, 0.187-0.430) for the visual acuity estimation (all P < .001).Conclusions and RelevanceResults of this study suggest that the visual function estimation in patients with retinitis pigmentosa from ultra-widefield fundus autofluorescence images using deep learning might help assess disease progression objectively. Findings also suggest that deep learning models might monitor the progression of retinitis pigmentosa efficiently during follow-up.

Hyperautofluorescent Ring Pattern in Retinitis Pigmentosa: Clinical Implications and Modifications Over Time

“…This challenge is expected to be addressed soon with the advancement of machine learning algorithms, which have the potential to provide a more impartial assessment of FAF images as technology progresses. 26 , 27 Additionally, our cohort mostly featured patients with autosomal recessive inheritance, including some syndromic cases, for whom we did not conduct separate disease progression analyses due to genotype heterogeneity, whereas patients with XL RP and AD RP were less represented. Moreover, no subanalyses focused on the genetic characterization was attempted owing to the limited number of patients enrolled in the study, which would have hampered a reliable assessment.…”

Artificial Intelligence (AI) for Early Diagnosis of Retinal Diseases

“…Nagasato D et al studied five DL models, Visual Geometry Group-16, Residual Network-50, Inception V3, DenseNet121, and EfficientNetB0, to estimate visual function in patients with RP. These models were validated against ultra-widefield fundus autofluorescence images from 695 patients and were found to accurately estimate the visual acuity and central sensitivity in these patients (p < 0.001) [84]. Liu TYA et al trained their DL algorithm to predict visual impairment in patients with RP.…”

Eyeing a Role for Artificial Intelligence in Clinical Trials

“…In this issue of JAMA Ophthalmology, Nagasato et al 1 describe an artificial intelligence (AI)-based approach to estimate visual function in patients with retinitis pigmentosa (RP) using ultra-widefield (UWF) fundus imaging input data as an objective surrogate. The authors posited that this approach could enhance routine clinical care; UWF imaging, being quicker and easier to obtain than perimetry, might aid conversations between physicians and patients regarding residual functional status and disease progression.…”