Purchase this article with an account.
Alexandra Miere, Vittorio Capuano, Arthur Kessler, Olivia Zambrowski, Camille Jung, Donato Colantuono, Carlotta Pallone, Oudy Semoun, Eric Petit, Eric H Souied; Deep learning-based classification of retinal atrophy using fundus autofluorescence imaging. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2122.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
To automatically classify retinal atrophy according to its etiology, using fundus autofluorescence (FAF) images, using a deep learning model.
In this study, FAF images of patients with advanced dry age-related macular degeneration (AMD), also called geographic atrophy (GA), and genetically confirmed inherited retinal diseases (IRDs) in late atrophic stages [Stargardt disease (STGD1) and Pseudo-Stargardt Pattern Dystrophy (PSPD)] were included. The FAF images were used to train a multi-layer deep convolutional neural network (CNN) to differentiate on FAF between atrophy in the context of AMD (GA) and atrophy secondary to IRDs. Three-hundred fourteen FAF images were included, of which 110 images were of GA eyes and 204 were eyes with genetically confirmed STGD1 or PSPD. In the first approach, the CNN was trained and validated with 251 FAF images. Established augmentation techniques were used and an Adam optimizer was used for training. For the subsequent testing, the built classifiers were then tested with 63 untrained FAF images. The visualization method was integrated gradient visualization. In the second approach, 10-fold cross-validation was used to determine the model’s performance.
In the first approach, the best performance of the model was obtained using 10 epochs, with an accuracy of 0.92 and an area under the curve for Receiver Operating Characteristic (AUC-ROC) of 0.981. Mean accuracy was 87.30 +/- 2.96. In the second approach, a mean accuracy of 0.79 +/-0.06 was obtained.
This study describes the use of a deep learning-based algorithm to automatically classify atrophy on FAF imaging according to its etiology. Accurate differential diagnosis between GA and late-onset IRDs masquerading as GA on FAF can be performed with good accuracy and AUC-ROC values.
This is a 2021 ARVO Annual Meeting abstract.
Examples of correct attributions with integrated gradient visualization. Left panels: Geographic atrophy (GA) fundus autofluorescence images (FAF) correctly classified as 'GA'. Right panels: Atrophy of 'genetic cause' (Stargardt disease) correctly classified as such.
Area under the ROC curve in the two approaches, generated by plotting the true-positive rate and the false-positive rate.
This PDF is available to Subscribers Only