Publications by authors named "Arthur Kessler"
(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease ("pseudo-Stargardt pattern dystrophy", PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing -related STGD1 from the -related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs).
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to classify retinal atrophy using fundus autofluorescence (FAF) images with a deep learning model, focusing on conditions like advanced age-related macular degeneration (AMD) and inherited retinal diseases (IRDs).
- A total of 314 FAF images were analyzed, with a multi-layer deep convolutional neural network (CNN) trained to differentiate between atrophy caused by AMD and by IRDs, achieving an accuracy of 92% for the trained model.
- The results indicate that the deep learning algorithm can effectively differentiate between types of retinal atrophy, showing promise for accurate diagnosis in clinical settings.