Conditional GAN for Prediction of Glaucoma Progression with Macular Optical Coherence Tomography

The estimation of glaucoma progression is a challenging task as the rate of disease progression varies among individuals in addition to other factors such as measurement variability and the lack of standardization in defining progression. Structural tests, such as thickness measurements of the retinal nerve fiber layer or the macula with optical coherence tomography (OCT), are able to detect anatomical changes in glaucomatous eyes. Such changes may be observed before any functional damage. In this work, we built a generative deep learning model using the conditional GAN architecture to predict glaucoma progression over time. The patient's OCT scan is predicted from three or two prior measurements. The predicted images demonstrate high similarity with the ground truth images. In addition, our results suggest that OCT scans obtained from only two prior visits may actually be sufficient to predict the next OCT scan of the patient after six months.

[1]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[2]  Chuan Li,et al.  Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks , 2016, ECCV.

[3]  C. Alexandrescu,et al.  Confocal scanning laser ophthalmoscopy in glaucoma diagnosis and management , 2010, Journal of medicine and life.

[4]  Donald C. Hood,et al.  A framework for comparing structural and functional measures of glaucomatous damage , 2007, Progress in Retinal and Eye Research.

[5]  Richard Dosselmann,et al.  A comprehensive assessment of the structural similarity index , 2011, Signal Image Video Process..

[6]  Christopher Bowd,et al.  A unified framework for glaucoma progression detection using Heidelberg Retina Tomograph images , 2014, Comput. Medical Imaging Graph..

[7]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[8]  Shu Liu,et al.  Evaluation of retinal nerve fiber layer progression in glaucoma: a study on optical coherence tomography guided progression analysis. , 2010, Investigative ophthalmology & visual science.

[9]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  T. Dada,et al.  Test-Retest Variability of Retinal Nerve Fiber Layer Thickness and Macular Ganglion Cell-Inner Plexiform Layer Thickness Measurements Using Spectral-Domain Optical Coherence Tomography , 2015, Journal of glaucoma.

[11]  J. Piltz,et al.  Test-retest variability in glaucomatous visual fields. , 1990, American journal of ophthalmology.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  H. Quigley,et al.  The number of people with glaucoma worldwide in 2010 and 2020 , 2006, British Journal of Ophthalmology.

[14]  G. Dunkelberger,et al.  Retinal ganglion cell atrophy correlated with automated perimetry in human eyes with glaucoma. , 1989, American journal of ophthalmology.

[15]  Kouros Nouri-Mahdavi,et al.  A method to measure and predict rates of regional visual field decay in glaucoma. , 2011, Investigative ophthalmology & visual science.

[16]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[17]  J. Caprioli,et al.  Measuring rates of structural and functional change in glaucoma , 2014, British Journal of Ophthalmology.

[18]  Joel S Schuman,et al.  Diagnostic tools for glaucoma detection and management. , 2008, Survey of ophthalmology.

[19]  G. Tomita,et al.  Baseline thickness of macular ganglion cell complex predicts progression of visual field loss , 2013, Graefe's Archive for Clinical and Experimental Ophthalmology.

[20]  J. G. Babu,et al.  Diagnostic capability of optical coherence tomography (Stratus OCT 3) in early glaucoma. , 2007, Ophthalmology.

[21]  D. Minckler,et al.  Glaucoma , 2018, Methods in Molecular Biology.

[22]  D. Zack,et al.  Retinal ganglion cell death in experimental glaucoma and after axotomy occurs by apoptosis. , 1995, Investigative ophthalmology & visual science.

[23]  Joel S Schuman,et al.  Optic nerve head and retinal nerve fiber layer analysis: a report by the American Academy of Ophthalmology. , 2007, Ophthalmology.

[24]  J. Schuman,et al.  Predicting Development of Glaucomatous Visual Field Conversion Using Baseline Fourier-Domain Optical Coherence Tomography. , 2016, American journal of ophthalmology.

[25]  B. Yoo,et al.  Long-Term Reproducibility of Macular Ganglion Cell Analysis in Clinically Stable Glaucoma Patients. , 2015, Investigative ophthalmology & visual science.

[26]  C. Mardin,et al.  Structural changes of macular inner retinal layers in early normal-tension and high-tension glaucoma by spectral-domain optical coherence tomography , 2018, Graefe's Archive for Clinical and Experimental Ophthalmology.

[27]  Robert N Weinreb,et al.  Risk assessment in the management of patients with ocular hypertension. , 2004, American journal of ophthalmology.

[28]  T. Wong,et al.  Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. , 2014, Ophthalmology.

[29]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[30]  Adrian Stern,et al.  Horizontal Resolution Enhancement of Autostereoscopy Three-Dimensional Displayed Image by Chroma Subpixel Downsampling , 2015, Journal of Display Technology.

[31]  Jung Hwa Na,et al.  The glaucoma detection capability of spectral-domain OCT and GDx-VCC deviation maps in early glaucoma patients with localized visual field defects , 2013, Graefe's Archive for Clinical and Experimental Ophthalmology.

[32]  Esteban Morales,et al.  Macular SD-OCT Outcome Measures: Comparison of Local Structure-Function Relationships and Dynamic Range , 2016, Investigative ophthalmology & visual science.

[33]  S. Wickremasinghe,et al.  A comparison of HRT II and GDx imaging for glaucoma detection in a primary care eye clinic setting , 2003, Eye.

[34]  D. Hood,et al.  Evaluation of the Structure-Function Relationship in Glaucoma Using a Novel Method for Estimating the Number of Retinal Ganglion Cells in the Human Retina. , 2015, Investigative ophthalmology & visual science.

[35]  B. Nan,et al.  Trends in use of ancillary glaucoma tests for patients with open-angle glaucoma from 2001 to 2009. , 2012, Ophthalmology.

[36]  F. Medeiros,et al.  The pathophysiology and treatment of glaucoma: a review. , 2014, JAMA.

[37]  Young Kook Kim,et al.  Rates of Ganglion Cell-Inner Plexiform Layer Thinning in Normal, Open-Angle Glaucoma and Pseudoexfoliation Glaucoma Eyes: A Trend-Based Analysis. , 2019, Investigative ophthalmology & visual science.