%0 Journal Article
%T A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images
%A Li, Zhongwen
%A Guo, Chong
%A Nie, Danyao
%A Lin, Duoru
%A Zhu, Yi
%A Chen, Chuan
%A Zhang, Li
%A Xu, Fabao
%A Jin, Chenjin
%A Zhang, Xiayin
%A Xiao, Hui
%A Zhang, Kai
%A Zhao, Lanqin
%A Yu, Shanshan
%A Zhang, Guoming
%A Wang, Jiantao
%A Lin, Haotian
%J Annals of Translational Medicine
%D 2019
%B 2019
%9 
%! A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images
%K 
%X Background: Lattice degeneration and/or retinal breaks, defined as notable peripheral retinal lesions (NPRLs), are prone to evolving into rhegmatogenous retinal detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed to develop and evaluate a deep learning (DL) system for automated identifying NPRLs based on ultra-widefield fundus (UWF) images.  Methods: A total of 5,606 UWF images from 2,566 participants were used to train and verify a DL system. All images were classified by 3 experienced ophthalmologists. The reference standard was determined when an agreement was achieved among all 3 ophthalmologists, or adjudicated by another retinal specialist if disagreements existed. An independent test set of 750 images was applied to verify the performance of 12 DL models trained using 4 different DL algorithms (InceptionResNetV2, InceptionV3, ResNet50, and VGG16) with 3 preprocessing techniques (original, augmented, and histogram-equalized images). Heatmaps were generated to visualize the process of the best DL system in the identification of NPRLs.  Results: In the test set, the best DL system for identifying NPRLs achieved an area under the curve (AUC) of 0.999 with a sensitivity and specificity of 98.7% and 99.2%, respectively. The best preprocessing method in each algorithm was the application of original image augmentation (average AUC =0.996). The best algorithm in each preprocessing method was InceptionResNetV2 (average AUC =0.996). In the test set, 150 of 154 true-positive cases (97.4%) displayed heatmap visualization in the NPRL regions.  Conclusions: A DL system has high accuracy in identifying NPRLs based on UWF images. This system may help to prevent the development of rhegmatogenous retinal detachment by early detection of NPRLs.
%U https://atm.amegroups.org/article/view/32004
%V 7
%N 22
%P 618
%@ 2305-5847