A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images.

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.

[1]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[2]  James M. Brown,et al.  Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks , 2018, JAMA ophthalmology.

[3]  Xixi Yan,et al.  Development and validation of a deep‐learning algorithm for the detection of neovascular age‐related macular degeneration from colour fundus photographs , 2019, Clinical & experimental ophthalmology.

[4]  A. Cavallerano,et al.  Retinal detachment. , 1992, Optometry clinics : the official publication of the Prentice Society.

[5]  Jonathan Krause,et al.  Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy , 2017, Ophthalmology.

[6]  D. Charteris,et al.  The epidemiology of rhegmatogenous retinal detachment: geographical variation and clinical associations , 2009, British Journal of Ophthalmology.

[7]  Neil J. Joshi,et al.  Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks , 2017, JAMA ophthalmology.

[8]  Jonathan Krause,et al.  Deep Learning and Glaucoma Specialists: The Relative Importance of Optic Disc Features to Predict Glaucoma Referral in Fundus Photographs. , 2019, Ophthalmology (Rochester, Minn.).

[9]  M. Chen,et al.  Spectral-domain optical coherence tomography of peripheral lattice degeneration of myopic eyes before and after laser photocoagulation. , 2019, Journal of the Formosan Medical Association = Taiwan yi zhi.

[10]  Jennifer I. Lim,et al.  Posterior Vitreous Detachment, Retinal Breaks, and Lattice Degeneration Preferred Practice Pattern®. , 2019, Ophthalmology.

[11]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[12]  A. Wright,et al.  The predisposing pathology and clinical characteristics in the Scottish retinal detachment study. , 2011, Ophthalmology.

[13]  SriniVas R Sadda,et al.  ULTRA-WIDEFIELD FUNDUS IMAGING: A Review of Clinical Applications and Future Trends , 2016, Retina.

[14]  T. Wong,et al.  Peripheral retinal changes in highly myopic young Asian eyes , 2018, Acta ophthalmologica.

[15]  C. Wilkinson.  Evidence-based analysis of prophylactic treatment of asymptomatic retinal breaks and lattice degeneration. , 2000, Ophthalmology.

[16]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[17]  C. Wilkinson.  Interventions for asymptomatic retinal breaks and lattice degeneration for preventing retinal detachment. , 2001, The Cochrane database of systematic reviews.

[18]  S. Schwartz,et al.  The fellow eye of patients with rhegmatogenous retinal detachment. , 2004, Ophthalmology.

[19]  Rajiv Raman,et al.  Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India. , 2019, JAMA ophthalmology.

[20]  Shih-Hwa Chiou,et al.  Artificial intelligence-based decision-making for age-related macular degeneration , 2019, Theranostics.

[21]  E. Finkelstein,et al.  Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes , 2017, JAMA.

[22]  Stuart Keel,et al.  Visualizing Deep Learning Models for the Detection of Referable Diabetic Retinopathy and Glaucoma , 2019, JAMA ophthalmology.

[23]  Rishab Gargeya,et al.  Automated Identification of Diabetic Retinopathy Using Deep Learning. , 2017, Ophthalmology.

[24]  C. P. Wilkinson,et al.  Evidence-based medicine regarding the prevention of retinal detachment. , 1999, Transactions of the American Ophthalmological Society.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  J. Pastor,et al.  Patients: the Retina 1 Projectt Report 2 Retinal Detachments in Phakic and Pseudophakic Surgical Outcomes for Primary Rhegmatogenous Rapid Responses , 2022 .