We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Estimation of Visual Function Using Deep Learning From Ultra-Widefield Fundus Images of Eyes With Retinitis Pigmentosa.
- Authors
Nagasato, Daisuke; Sogawa, Takahiro; Tanabe, Mao; Tabuchi, Hitoshi; Numa, Shogo; Oishi, Akio; Ohashi Ikeda, Hanako; Tsujikawa, Akitaka; Maeda, Tadao; Takahashi, Masayo; Ito, Nana; Miura, Gen; Shinohara, Terumi; Egawa, Mariko; Mitamura, Yoshinori
- Abstract
Key Points: Question: Can artificial intelligence estimate the visual function of eyes with retinitis pigmentosa from ultra-widefield fundus images? Findings: In this multicenter cross-sectional study of 1274 eyes of 695 patients with retinitis pigmentosa, the standardized regression coefficient was 0.309 in estimating visual acuity based on ultra-widefield fundus autofluorescence images using a deep learning model, 0.684 in estimating the mean deviation on the Humphrey field analyzer, and 0.697 in estimating central retinal sensitivity. Meaning: Findings suggest that this estimation method of visual function using artificial intelligence with ultra-widefield fundus autofluorescence images assists in objectively evaluating the progression of retinitis pigmentosa. Importance: There is no widespread effective treatment to halt the progression of retinitis pigmentosa. Consequently, adequate assessment and estimation of residual visual function are important clinically. Objective: To 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 Participants: Data 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 Measures: The 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. Results: The 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 Relevance: Results 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. This cross-sectional study investigates whether deep learning can estimate the visual function of eyes with retinitis pigmentosa from ultra-widefield fundus images.
- Publication
JAMA Ophthalmology, 2023, Vol 141, Issue 4, p305
- ISSN
2168-6165
- Publication type
Article
- DOI
10.1001/jamaophthalmol.2022.6393