Deep Neural Network-Based Method for Detecting Central Retinal Vein Occlusion Using Ultrawide-Field Fundus Ophthalmoscopy

The aim of this study is to assess the performance of two machine-learning technologies, namely, deep learning (DL) and support vector machine (SVM) algorithms, for detecting central retinal vein occlusion (CRVO) in ultrawide-field fundus images. Images from 125 CRVO patients (n=125 images) and 202 non-CRVO normal subjects (n=238 images) were included in this study. Training to construct the DL model using deep convolutional neural network algorithms was provided using ultrawide-field fundus images. The SVM uses scikit-learn library with a radial basis function kernel. The diagnostic abilities of DL and the SVM were compared by assessing their sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic curve for CRVO. For diagnosing CRVO, the DL model had a sensitivity of 98.4% (95% confidence interval (CI), 94.3–99.8%) and a specificity of 97.9% (95% CI, 94.6–99.1%) with an AUC of 0.989 (95% CI, 0.980–0.999). In contrast, the SVM model had a sensitivity of 84.0% (95% CI, 76.3–89.3%) and a specificity of 87.5% (95% CI, 82.7–91.1%) with an AUC of 0.895 (95% CI, 0.859–0.931). Thus, the DL model outperformed the SVM model in all indices assessed (P < 0.001 for all). Our data suggest that a DL model derived using ultrawide-field fundus images could distinguish between normal and CRVO images with a high level of accuracy and that automatic CRVO detection in ultrawide-field fundus ophthalmoscopy is possible. This proposed DL-based model can also be used in ultrawide-field fundus ophthalmoscopy to accurately diagnose CRVO and improve medical care in remote locations where it is difficult for patients to attend an ophthalmic medical center.

[1]  Enrique F Schisterman,et al.  Youden Index and the optimal threshold for markers with mass at zero , 2008, Statistics in medicine.

[2]  A. Akobeng,et al.  Understanding diagnostic tests 3: receiver operating characteristic curves , 2007, Acta paediatrica.

[3]  Hae-Jeong Park,et al.  Geometric Convolutional Neural Network for Analyzing Surface-Based Neuroimaging Data , 2018, Front. Neuroinform..

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

[5]  Y. Nesterov.  A method for unconstrained convex minimization problem with the rate of convergence o(1/k^2) , 1983 .

[6]  J. Sato,et al.  Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia , 2016, Scientific Reports.

[7]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[8]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[9]  Herbert A. Sturges,et al.  The Choice of a Class Interval , 1926 .

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

[11]  J. Haller,et al.  Intravitreal aflibercept injection for macular edema secondary to central retinal vein occlusion: 1-year results from the phase 3 COPERNICUS study. , 2013, American journal of ophthalmology.

[12]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[13]  U. Schmidt-Erfurth,et al.  Intravitreal Aflibercept Injection for Macular Edema Resulting from Central Retinal Vein Occlusion: One-Year Results of the Phase 3 GALILEO Study. , 2014, Ophthalmology.

[14]  S. Hayreh,et al.  FUNDUS CHANGES IN CENTRAL RETINAL VEIN OCCLUSION , 2015, Retina.

[15]  P. Campochiaro,et al.  Sustained benefits from ranibizumab for macular edema following central retinal vein occlusion: twelve-month outcomes of a phase III study. , 2011, Ophthalmology.

[16]  Tien Yin Wong,et al.  The prevalence of retinal vein occlusion: pooled data from population studies from the United States, Europe, Asia, and Australia. , 2010, Ophthalmology.

[17]  Zhonghua Chen,et al.  Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images , 2017, EJNMMI Research.

[18]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

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

[20]  A. Ho,et al.  Therapies for macular edema associated with central retinal vein occlusion: a report by the American Academy of Ophthalmology. , 2015, Ophthalmology.

[21]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[22]  Xiao Sun,et al.  Multichannel Convolutional Neural Network for Biological Relation Extraction , 2016, BioMed research international.

[23]  B. van Ginneken,et al.  Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis , 2016, Scientific Reports.

[24]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[25]  Yuta Wakayama,et al.  Comparison of medical image classification accuracy among three machine learning methods. , 2018, Journal of X-ray science and technology.

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

[27]  Jitendra Malik,et al.  Analyzing the Performance of Multilayer Neural Networks for Object Recognition , 2014, ECCV.

[28]  T. Wong,et al.  Retinal vein occlusion: an approach to diagnosis, systemic risk factors and management , 2008, Internal medicine journal.

[29]  Sidong Liu,et al.  Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease , 2015, IEEE Transactions on Biomedical Engineering.

[30]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Henry J. Lowe,et al.  Discretization of continuous features in clinical datasets , 2013, J. Am. Medical Informatics Assoc..

[32]  Hideharu Ohsugi,et al.  Accuracy of deep learning, a machine-learning technology, using ultra–wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment , 2017, Scientific Reports.