Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression

OBJECTIVE Glaucoma is the second leading cause of blindness worldwide. Glaucomatous progression can be easily monitored by analyzing the degeneration of retinal ganglion cells (RGCs). Many researchers have screened glaucoma by measuring cup-to-disc ratios from fundus and optical coherence tomography scans. However, this paper presents a novel strategy that pays attention to the RGC atrophy for screening glaucomatous pathologies and grading their severity. METHODS The proposed framework encompasses a hybrid convolutional network that extracts the retinal nerve fiber layer, ganglion cell with the inner plexiform layer and ganglion cell complex regions, allowing thus a quantitative screening of glaucomatous subjects. Furthermore, the severity of glaucoma in screened cases is objectively graded by analyzing the thickness of these regions. RESULTS The proposed framework is rigorously tested on publicly available Armed Forces Institute of Ophthalmology (AFIO) dataset, where it achieved the F1 score of 0.9577 for diagnosing glaucoma, a mean dice coefficient score of 0.8697 for extracting the RGC regions and an accuracy of 0.9117 for grading glaucomatous progression. Furthermore, the performance of the proposed framework is clinically verified with the markings of four expert ophthalmologists, achieving a statistically significant Pearson correlation coefficient of 0.9236. CONCLUSION An automated assessment of RGC degeneration yields better glaucomatous screening and grading as compared to the state-of-the-art solutions. SIGNIFICANCE An RGC-aware system not only screens glaucoma but can also grade its severity and here we present an end-to-end solution that is thoroughly evaluated on a standardized dataset and is clinically validated for analyzing glaucomatous pathologies.

[1]  Tien Yin Wong,et al.  Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma Screening , 2013, IEEE Transactions on Medical Imaging.

[2]  Yali Jia,et al.  Automated segmentation of peripapillary retinal boundaries in OCT combining a convolutional neural network and a multi-weights graph search. , 2019, Biomedical optics express.

[3]  Robert N Weinreb,et al.  The structure and function relationship in glaucoma: implications for detection of progression and measurement of rates of change. , 2012, Investigative ophthalmology & visual science.

[4]  Taimur Hassan,et al.  RAG-FW: A Hybrid Convolutional Framework for the Automated Extraction of Retinal Lesions and Lesion-Influenced Grading of Human Retinal Pathology , 2020, IEEE Journal of Biomedical and Health Informatics.

[5]  Arslan Shaukat,et al.  Improved automated detection of glaucoma by correlating fundus and SD‐OCT image analysis , 2020, Int. J. Imaging Syst. Technol..

[6]  Sina Farsiu,et al.  Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema. , 2015, Biomedical optics express.

[7]  R. Kafieh,et al.  Thickness Mapping of Eleven Retinal Layers Segmented Using the Diffusion Maps Method in Normal Eyes , 2015, Journal of ophthalmology.

[8]  Ahmed E.Abd El-Naby,et al.  Correlation of retinal nerve fiber layer thickness and perimetric changes in primary open-angle glaucoma , 2018 .

[9]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Mona Kamal Abdellatif,et al.  Outer Retinal Layers' Thickness Changes in relation to Age and Choroidal Thickness in Normal Eyes , 2019, Journal of ophthalmology.

[11]  F. Medeiros,et al.  Spectral-Domain Optical Coherence Tomography for Glaucoma Diagnosis , 2015, The open ophthalmology journal.

[12]  Taimur Hassan,et al.  Deep structure tensor graph search framework for automated extraction and characterization of retinal layers and fluid pathology in retinal SD-OCT scans , 2019, Comput. Biol. Medicine.

[13]  Garrison W. Cottrell,et al.  Understanding Convolution for Semantic Segmentation , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[14]  Xu Sun,et al.  Localizing Optic Disc and Cup for Glaucoma Screening via Deep Object Detection Networks , 2018, COMPAY/OMIA@MICCAI.

[15]  Xiaochun Cao,et al.  Disc-Aware Ensemble Network for Glaucoma Screening From Fundus Image , 2018, IEEE Transactions on Medical Imaging.

[16]  Neil O'Leary,et al.  Automated segmentation of optic nerve head structures with optical coherence tomography. , 2014, Investigative ophthalmology & visual science.

[17]  Eleni-Rosalina Andrinopoulou,et al.  Contrast-to-Noise Ratios for Assessing the Detection of Progression in the Various Stages of Glaucoma , 2019, Translational vision science & technology.

[18]  M. Usman Akram,et al.  Improved automated detection of glaucoma from fundus image using hybrid structural and textural features , 2017, IET Image Process..

[19]  Johan Wiklund,et al.  Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Fei Li,et al.  Joint retina segmentation and classification for early glaucoma diagnosis. , 2019, Biomedical optics express.

[22]  R. Ansari,et al.  A method for detection of retinal layers by optical coherence tomography image segmentation , 2007, 2007 IEEE/NIH Life Science Systems and Applications Workshop.

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

[24]  M. Usman Akram,et al.  Data on OCT and fundus images for the detection of glaucoma , 2020, Data in brief.

[25]  M. Usman Akram,et al.  Detection of Glaucoma Using Cup to Disc Ratio From Spectral Domain Optical Coherence Tomography Images , 2018, IEEE Access.

[26]  Hiroshi Ishikawa,et al.  A feature agnostic approach for glaucoma detection in OCT volumes , 2018, PloS one.

[27]  Tien Yin Wong,et al.  Glaucoma detection based on deep convolutional neural network , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[28]  Shafin Rahman,et al.  An Approach for Automated Segmentation of Retinal Layers In Peripapillary Spectralis SDOCT Images Using Curve Regularisation , 2017 .

[29]  Xinjian Chen,et al.  Comparison of Retinal Thickness Measurements between the Topcon Algorithm and a Graph-Based Algorithm in Normal and Glaucoma Eyes , 2015, PloS one.

[30]  Taimur Hassan,et al.  Review of OCT and fundus images for detection of Macular Edema , 2015, 2015 IEEE International Conference on Imaging Systems and Techniques (IST).

[31]  Giovanni Montesano,et al.  ReLayer: a Free, Online Tool for Extracting Retinal Thickness From Cross-Platform OCT Images , 2019, Translational vision science & technology.

[32]  Robert N Weinreb,et al.  Retinal nerve fiber layer imaging with spectral-domain optical coherence tomography: patterns of retinal nerve fiber layer progression. , 2012, Ophthalmology.

[33]  Taimur Hassan,et al.  Evaluation of Deep Segmentation Models for the Extraction of Retinal Lesions from Multi-modal Retinal Images , 2020, ArXiv.

[34]  J. Hornegger,et al.  Retinal Nerve Fiber Layer Segmentation on FD-OCT Scans of Normal Subjects and Glaucoma Patients , 2010, Biomedical optics express.

[35]  Taimur Hassan,et al.  Exploiting the Transferability of Deep Learning Systems Across Multi-modal Retinal Scans for Extracting Retinopathy Lesions , 2020, 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE).

[36]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[37]  Yuanjie Zheng,et al.  A Generative Model for OCT Retinal Layer Segmentation by Groupwise Curve Alignment , 2018, IEEE Access.

[38]  Masanori Hangai,et al.  Measurement of Retinal Nerve Fiber Layer Thickness and Macular Volume for Glaucoma Detection Using Optical Coherence Tomography , 2007, Japanese Journal of Ophthalmology.

[39]  Zhengyang Wang,et al.  Smoothed dilated convolutions for improved dense prediction , 2018, Data Mining and Knowledge Discovery.

[40]  Felipe A. Medeiros,et al.  Quantification of Retinal Nerve Fibre Layer Thickness on Optical Coherence Tomography with a Deep Learning Segmentation-Free Approach , 2020, Scientific Reports.

[41]  Adeel M. Syed,et al.  Automated segmentation of subretinal layers for the detection of macular edema. , 2016, Applied optics.

[42]  Mitra Sehi,et al.  Detection of Progressive Retinal Nerve Fiber Layer Thickness Loss With Optical Coherence Tomography Using 4 Criteria for Functional Progression , 2010, Journal of glaucoma.

[43]  Taimur Hassan,et al.  Structure Tensor Graph Searches Based Fully Automated Grading and 3D Profiling of Maculopathy From Retinal OCT Images , 2018, IEEE Access.

[44]  Weiwei Zhang,et al.  Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint , 2014, Comput. Biol. Medicine.

[45]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  R. T. Hart,et al.  The optic nerve head as a biomechanical structure: a new paradigm for understanding the role of IOP-related stress and strain in the pathophysiology of glaucomatous optic nerve head damage , 2005, Progress in Retinal and Eye Research.

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