Improved automated detection of glaucoma by correlating fundus and SD‐OCT image analysis

Abstract

Glaucoma is a multifactorial ocular disease. Ophthalmologists mostly use fundus or optical coherence tomography (OCT) for diagnosis of glaucoma. In this study, a hybrid computer‐aided‐diagnosis (H‐CAD) system has been proposed that integrates both fundus and OCT imaging technologies for reliable diagnosis of glaucoma. Fundus module inspects the outer layer of eye's posterior part. It considers a variety of structural and textural features and makes a decision using support vector machine (SVM). In OCT module, the cup to disc ratio (CDR) has been computed by examining the internal layers of the retina. The cup contour has been extracted from inner‐limiting‐membrane (ILM) layer using a set of novel techniques for the calculation of cup diameter. Similarly, in the disc diameter calculation the retinal‐pigment‐epithelium (RPE) layer termination points have been identified by a number of innovative strategies to locate disc margin. Furthermore, a new criterion based on the mean value of RPE‐layer end points has been proposed for the determination of cup edges. A local‐dataset annotated by four ophthalmologists has been used for evaluation of proposed H‐CAD system. The evaluations and results have shown that the final result of H_CAD system is more trustable than its contemporary automated models.

Performance evaluation of various deep learning based models for effective glaucoma evaluation using optical coherence tomography images

“…The accuracy generated by our proposed system (0.9568) is among the best in the class. However, in [ 29 ] and [ 57 ], the researchers have shown some better results than ours. It is found that the number of subject images on which they have tested their approach is much less than the number of subject images on which the presented approach is tested.…”

“… AUC 0.9143 2018 Lee et al [ 29 ] 91 healthy images and 58 glaucomatous eyes Measuring peripapillary retinal nerve fiber layer(PP-RNFL) thickness,full macular thickness, and ganglion cell-inner plexiform layer (GC-IPL) thickness. Three dimensional optic disc scanning of DRI-OCT. AUC upto 0.968 2020 Thomson et al [ 68 ] 612 glaucomatous images and 542 normal images CNN ROC curve area 0.96 2019 Ran et al [ 50 ] 1822 glaucomatous images and 1007 normal images Data preprocessing and then 3D CNN(ResNet) Primary validation dataset accuracy 91% 2019 Maetschke et al [ 33 ] 847 volumes of glaucoma and 263 volumes of healthy Unsegmented OCT volumes of the optic nerve head using a 3D-CNN AUC 0.94 2020 Wang et al [ 71 ] 2669 infected cases and 1679 normal cases CNN with semi-supervised learning AUC from 0.933 to 0.977 2020 Shehryar et al [ 57 ] 22 images of healthy eyes and 28 images of glaucoma eyes. Hybrid computer-aided-diagnosis (H-CAD) system Accuracy upto 96% Specificity upto 95% Sensitivity upto 94% 2019 Thakoor et al [ 66 ] 737 RNFL probability map images from 322 eyes of 322 patients and 415 eyes of 415 healthy controls .…”

“…Researchers conclude that retinal segmentation preprocessing improves 3-D deep learning algorithms’ performance in detecting referable glaucoma in macular OCT volumes without retinal illness. This study proposed a hybrid computer-aided-diagnosis (H-CAD) system that combines fundus and OCT imaging technologies (Shehryar et al [ 57 ]). The OCT module computes the cup-to-disc-ratio (CDR) by studying the retina’s interior layers.…”

Mobile‐aided screening system for proliferative diabetic retinopathy

“…The SVM is an automatic learning algorithm used for data classification, which is widely used for binary classification. 55,57,58 The principal objective of SVM is to determine an optimal hyperplane that separates the training data into classes, by maximizing the geometric margin between each other. [59][60][61] Many related works 12,13,15 used the SVM classifier to detect the NVD where optimal performances have been achieved.…”

A Self-Training Framework for Glaucoma Grading In OCT B-Scans

“…Nevertheless, despite the rise of these models in many computer vision and medical problems, their application on OCT images for glaucoma assessment still presents several limitations. First, most of the literature focuses on discerning between healthy and glaucoma classes via OCT B-scans [7], [8], SD-OCT volumes [9]- [11] or probability RNFL maps by combining fundus images and OCT samples [12], [13]. Indeed, to the best of our knowledge, only [2] proposes a glaucomabased scenario beyond the healthy-glaucoma classification by including the suspect label.…”