Glaucoma Classification Research Articles

REFUGEChallenge: A unified framework for evaluating automatedmethods for glaucomaassessment from fundus photographs.

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modality to screen for retinal disorders. However, its application to glaucoma has been limited to the computation of a few related biomarkers such as the vertical cup-to-disc ratio. Deep learning approaches, although widely applied for medical image analysis, have not been extensively used for glaucoma assessment due to the limited size of the available data sets. Furthermore, the lack of a standardize benchmark strategy makes difficult to compare existing methods in a uniform way. In order to overcome these issues we set up the Retinal Fundus Glaucoma Challenge, REFUGE (https://refuge.grand-challenge.org), held in conjunction with MICCAI 2018. The challenge consisted of two primary tasks, namely optic disc/cup segmentation and glaucoma classification. As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one. We have also built an evaluation framework to ease and ensure fairness in the comparison of different models, encouraging the development of novel techniques in the field. 12 teams qualified and participated in the online challenge. This paper summarizes their methods and analyzes their corresponding results. In particular, we observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task. Furthermore, the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.

Glaucoma screening pipeline based on clinical measurements and hidden features

Glaucoma refers to a chronic disease of the eye that leads to vision loss that is irreversible, which is called ‘silent theft of sight’. Thus, an automatic glaucoma screening pipeline from optic disc (OD) localisation to glaucoma risk prediction is proposed in this study. The proposed pipeline consists of three main phases. Firstly, the OD is localised by morphological processing and sliding window methods. Secondly, a novel neural network which is in U-shape and convolutional introduces concatenating path and fusion loss function is developed to split OD and optic cup (OC) at the same time. Thirdly, both clinical measurements including optic cup-to-disc ratio (CDR), neuroretinal rim related features, and hidden features including statistical moments, entropy and energy are combined to train glaucoma classifiers. According to the results of the experiment, the proposed segmentation network achieves the best performance on both OD and OC segmentation and the proposed CDR calculation method is capable of achieving the performance similar to that of ophthalmologist on CDR measurement. Besides, the authors’ glaucoma classification model can obtain the best performance on sensitivity and area under the curve score in comparison with the existing methods.

An hybrid feature space from texture information and transfer learning for glaucoma classification

Glaucoma is a progressive eye disease due to the increase in intraocular pressure. Accurate early detection may prevent vision loss. Most algorithms in the literature are not feasible for use in screening programs since they are not able to handle a wide diversity of images. We conducted an extensive study to determine the best set of features for image representation. Our feature extraction methodology included the following descriptors: LBP, GLCM, HOG, Tamura, GLRLM, morphology, and seven CNN architectures, that results in 30.682 features. Then, we used the gain ratio to order the features by importance and select the best set for glaucoma classification. Our tests were performed using 1675 images of DRISHTI, RIM-ONE, HRF, JSIEC, and ACRIMA databases. We concluded that a combination of the GLCM and pre-trained CNN’s has the potential to be used in a computer aid system for glaucoma detection. Our approach achieved an accuracy of 93.61%.

Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning

BackgroundWith the advancement of powerful image processing and machine learning techniques, Computer Aided Diagnosis has become ever more prevalent in all fields of medicine including ophthalmology. These methods continue to provide reliable and standardized large scale screening of various image modalities to assist clinicians in identifying diseases. Since optic disc is the most important part of retinal fundus image for glaucoma detection, this paper proposes a two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous.MethodsThe first stage is based on Regions with Convolutional Neural Network (RCNN) and is responsible for localizing and extracting optic disc from a retinal fundus image while the second stage uses Deep Convolutional Neural Network to classify the extracted disc into healthy or glaucomatous. Unfortunately, none of the publicly available retinal fundus image datasets provides any bounding box ground truth required for disc localization. Therefore, in addition to the proposed solution, we also developed a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization.ResultsThe proposed method is evaluated on seven publicly available datasets for disc localization and on ORIGA dataset, which is the largest publicly available dataset with healthy and glaucoma labels, for glaucoma classification. The results of automatic localization mark new state-of-the-art on six datasets with accuracy reaching 100% on four of them. For glaucoma classification we achieved Area Under the Receiver Operating Characteristic Curve equal to 0.874 which is 2.7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA dataset.ConclusionOnce trained on carefully annotated data, Deep Learning based methods for optic disc detection and localization are not only robust, accurate and fully automated but also eliminates the need for dataset-dependent heuristic algorithms. Our empirical evaluation of glaucoma classification on ORIGA reveals that reporting only Area Under the Curve, for datasets with class imbalance and without pre-defined train and test splits, does not portray true picture of the classifier’s performance and calls for additional performance metrics to substantiate the results.

A Large-Scale Database and a CNN Model for Attention-Based Glaucoma Detection.

Glaucoma is one of the leading causes of irreversible vision loss. Many approaches have recently been proposed for automatic glaucoma detection based on fundus images. However, none of the existing approaches can efficiently remove high redundancy in fundus images for glaucoma detection, which may reduce the reliability and accuracy of glaucoma detection. To avoid this disadvantage, this paper proposes an attention-based convolutional neural network (CNN) for glaucoma detection, called AG-CNN. Specifically, we first establish a large-scale attention-based glaucoma (LAG) database, which includes 11 760 fundus images labeled as either positive glaucoma (4878) or negative glaucoma (6882). Among the 11 760 fundus images, the attention maps of 5824 images are further obtained from ophthalmologists through a simulated eye-tracking experiment. Then, a new structure of AG-CNN is designed, including an attention prediction subnet, a pathological area localization subnet, and a glaucoma classification subnet. The attention maps are predicted in the attention prediction subnet to highlight the salient regions for glaucoma detection, under a weakly supervised training manner. In contrast to other attention-based CNN methods, the features are also visualized as the localized pathological area, which are further added in our AG-CNN structure to enhance the glaucoma detection performance. Finally, the experiment results from testing over our LAG database and another public glaucoma database show that the proposed AG-CNN approach significantly advances the state-of-the-art in glaucoma detection.

Glaucoma Assessment from OCT images using Capsule Network.

Optical coherence tomographic (OCT) images provide valuable information for understanding the changes occurring in the retina due to glaucoma, specifically, related to the retinal nerve fiber layer and the optic nerve head. In this paper, we propose a deep learning approach using Capsule network for glaucoma classification, which directly operates on 3D OCT volumes. The network is trained only on labelled volumes and does not attempt any region/structure segmentation. The proposed network was assessed on 50 volumes and found to achieve 0.97 for the area under the ROC curve (AUC). This is considerably higher than the existing approaches which are majorly based on machine learning or rely on segmentation of the required structures from OCT. Our network also outperforms 3D convolutional neural networks despite the fewer network parameters and fewer epochs needed for training.

Evaluation of a Deep Learning System For Identifying Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

Pegasus outperformed 5 of the 6 ophthalmologists in terms of diagnostic performance, and there was no statistically significant difference between the deep learning system and the "best case" consensus between the ophthalmologists. The agreement between Pegasus and gold standard was 0.715, whereas the highest ophthalmologist agreement with the gold standard was 0.613. Furthermore, the high sensitivity of Pegasus makes it a valuable tool for screening patients with glaucomatous optic neuropathy. The purpose of this study was to evaluate the performance of a deep learning system for the identification of glaucomatous optic neuropathy. Six ophthalmologists and the deep learning system, Pegasus, graded 110 color fundus photographs in this retrospective single-center study. Patient images were randomly sampled from the Singapore Malay Eye Study. Ophthalmologists and Pegasus were compared with each other and to the original clinical diagnosis given by the Singapore Malay Eye Study, which was defined as the gold standard. Pegasus' performance was compared with the "best case" consensus scenario, which was the combination of ophthalmologists whose consensus opinion most closely matched the gold standard. The performance of the ophthalmologists and Pegasus, at the binary classification of nonglaucoma versus glaucoma from fundus photographs, was assessed in terms of sensitivity, specificity and the area under the receiver operating characteristic curve (AUROC), and the intraobserver and interobserver agreements were determined. Pegasus achieved an AUROC of 92.6% compared with ophthalmologist AUROCs that ranged from 69.6% to 84.9% and the "best case" consensus scenario AUROC of 89.1%. Pegasus had a sensitivity of 83.7% and a specificity of 88.2%, whereas the ophthalmologists' sensitivity ranged from 61.3% to 81.6% and specificity ranged from 80.0% to 94.1%. The agreement between Pegasus and gold standard was 0.715, whereas the highest ophthalmologist agreement with the gold standard was 0.613. Intraobserver agreement ranged from 0.62 to 0.97 for ophthalmologists and was perfect (1.00) for Pegasus. The deep learning system took ∼10% of the time of the ophthalmologists in determining classification. Pegasus outperformed 5 of the 6 ophthalmologists in terms of diagnostic performance, and there was no statistically significant difference between the deep learning system and the "best case" consensus between the ophthalmologists. The high sensitivity of Pegasus makes it a valuable tool for screening patients with glaucomatous optic neuropathy. Future work will extend this study to a larger sample of patients.

Joint retina segmentation and classification for early glaucoma diagnosis.

We propose a joint segmentation and classification deep model for early glaucoma diagnosis using retina imaging with optical coherence tomography (OCT). Our motivation roots in the observation that ophthalmologists make the clinical decision by analyzing the retinal nerve fiber layer (RNFL) from OCT images. To simulate this process, we propose a novel deep model that joins the retinal layer segmentation and glaucoma classification. Our model consists of three parts. First, the segmentation network simultaneously predicts both six retinal layers and five boundaries between them. Then, we introduce a post processing algorithm to fuse the two results while enforcing the topology correctness. Finally, the classification network takes the RNFL thickness vector as input and outputs the probability of being glaucoma. In the classification network, we propose a carefully designed module to implement the clinical strategy to diagnose glaucoma. We validate our method both in a collected dataset of 1004 circular OCT B-Scans from 234 subjects and in a public dataset of 110 B-Scans from 10 patients with diabetic macular edema. Experimental results demonstrate that our method achieves superior segmentation performance than other state-of-the-art methods both in our collected dataset and in public dataset with severe retina pathology. For glaucoma classification, our model achieves diagnostic accuracy of 81.4% with AUC of 0.864, which clearly outperforms baseline methods.

Artificial intelligence in glaucoma.

The use of computers has become increasingly relevant to medical decision-making, and artificial intelligence methods have recently demonstrated significant advances in medicine. We therefore provide an overview of current artificial intelligence methods and their applications, to help the practicing ophthalmologist understand their potential impact on glaucoma care. Techniques used in artificial intelligence can successfully analyze and categorize data from visual fields, optic nerve structure [e.g., optical coherence tomography (OCT) and fundus photography], ocular biomechanical properties, and a combination thereof to identify disease severity, determine disease progression, and/or recommend referral for specialized care. Algorithms have become increasingly complex in recent years, utilizing both supervised and unsupervised methods of artificial intelligence. Impressive performance of these algorithms on previously unseen data has been reported, often outperforming standard global indices and expert observers. However, there remains no clearly defined gold standard for determining the presence and severity of glaucoma, which undermines the training of these algorithms. To improve upon existing methodologies, future work must employ more robust definitions of disease, optimize data inputs for artificial intelligence analysis, and improve methods of extracting knowledge from learned results. Artificial intelligence has the potential to revolutionize the screening, diagnosis, and classification of glaucoma, both through the automated processing of large data sets, and by earlier detection of new disease patterns. In addition, artificial intelligence holds promise for fundamentally changing research aimed at understanding the development, progression, and treatment of glaucoma, by identifying novel risk factors and by evaluating the importance of existing ones.

Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning.

Glaucoma detection in color fundus images is a challenging task that requires expertise and years of practice. In this study we exploited the application of different Convolutional Neural Networks (CNN) schemes to show the influence in the performance of relevant factors like the data set size, the architecture and the use of transfer learning vs newly defined architectures. We also compared the performance of the CNN based system with respect to human evaluators and explored the influence of the integration of images and data collected from the clinical history of the patients. We accomplished the best performance using a transfer learning scheme with VGG19 achieving an AUC of 0.94 with sensitivity and specificity ratios similar to the expert evaluators of the study. The experimental results using three different data sets with 2313 images indicate that this solution can be a valuable option for the design of a computer aid system for the detection of glaucoma in large-scale screening programs.

Transitions of the Understanding and Definition of Primary Glaucoma.

Objective:In previous decades, glaucoma has been primarily attributed to elevated intraocular pressure (IOP), but this has gradually been replaced by the development of optic neuropathy as the central concept of glaucoma in developed countries. However, there still remain strong controversies in the definition of glaucoma in China. In this current review, we are going to discuss these controversies and elaborate on the historical transitions of the definition of glaucoma both in China and developed countries. Furthermore, we will briefly describe the “ocular-cranial pressure gradient” theory and discuss the relationship between glaucoma and degenerative diseases of the central nervous system (CNS) in order to show the complex pathogenesis of glaucoma and the importance for the modification to the definition of glaucoma.Data Sources:We performed a comprehensive search in both PubMed and SinoMed using the following keywords: (a) “primary glaucoma” and “guideline,” (b) “ocular-cranial pressure gradient,” and (c) “glaucoma,” “Alzheimer's disease,” and “Parkinson's disease.” The literature search included the related articles with no restrictions on publication date.Study Selection:The primary references were Chinese and English articles including (a) original guidelines and expert consensuses of primary glaucoma, (b) reviews focusing on the differences between various versions of these guidelines and consensuses, and (c) papers about ocular-cranial pressure gradient theory and the relationship between glaucoma and CNS degenerative diseases.Results:The definitions and classifications of both primary open-angle glaucoma and primary angle-closure glaucoma differ between Chinese glaucoma consensuses and international primary glaucoma guidelines. Chinese definitions and classifications put more emphasis on the IOP, while international guidelines put more emphasis on the presence of optic neuropathy. The ocular-cranial pressure gradient theory and the research on the relationship between glaucoma and CNS degenerative diseases have provided new directions for exploring the pathogenesis of glaucoma.Conclusions:As regards the definition and classification of primary glaucoma, we find that there are still some discrepancies between Chinese expert consensuses and international guidelines. Glaucoma is a disease with complex etiologies, while its common characteristic is a specific optic neuropathy. The current definition and understanding of glaucoma is an ongoing and evolving process, reflecting our latest available evidence on its pathogenesis. Chinese ophthalmology community may need to update our guidelines, accommodating these latest developments.

Automatic Diagnosis and Classification of Glaucoma Using Hybrid Features and k-Nearest Neighbor

Automatic Diagnosis and Classification of Glaucoma Using Hybrid Features and <i>k</i>-Nearest Neighbor

Glaucoma Features in an East African Population: A 6-Year Cohort Study of Older Adults in Nakuru, Kenya.

Glaucoma is a leading cause of blindness in people of African descent. Minimal data is available from African population-based cohort studies. The primary aims of this study were to describe the normative distribution of glaucoma features to enable glaucoma classification and to assess risk factors for those with glaucoma at follow-up among people aged 50 years and above in Kenya. Random cluster sampling with probability proportionate to size was used to select a representative cross-sectional sample of adults aged 50 years and above in 2007 to 2008 in Nakuru District, Kenya. A 6-year follow-up was undertaken in 2013 to 2014. Comprehensive ophthalmic examination included visual acuity, digital retinal photography, visual fields, intraocular pressure, optical coherence tomography, and independent grading of optic nerve images. We report glaucoma features, prevalence and predictors for glaucoma based on the International Society for Geographical & Epidemiological Ophthalmology (ISGEO) criteria. Measures were estimated using a Poisson regression model and including inverse-probability weighting for loss to follow-up. At baseline, 4414 participants aged 50 years and above underwent examination. Anterior chamber optical coherence tomography findings: mean anterior chamber angle of 36.6 degrees, mean central corneal thickness of 508.1 μm and a mean anterior chamber depth of 2.67 mm. A total of 2171 participants were examined at follow-up. The vertical cup to disc ratio distribution was 0.7 and 0.8 at the 97.5th and 99.5th percentiles, respectively. A total of 88 (4.3%, 95% confidence interval, 3.5%-5.9%) of participants at follow-up had glaucoma consistent with ISGEO criteria. A relative afferent pupillary defect and raised intraocular pressure were associated with the diagnosis. Glaucoma is a public health challenge in low-resource settings. Research into testing and treatment modalities in Africa is needed.

Evaluation of data mining classifiers for prediction and classification of Glaucoma associated proteins

Evaluation of data mining classifiers for prediction and classification of Glaucoma associated proteins

The glaucoma image classification using texture features for SVM classifier

The most dangerous cause that occurs blindness is glaucoma; the aging society is mostly affected by this defect. It causes due to the increase of pressure in the optic nerve, and it causes more damage to the optic nerve. The accurate and efficient glaucoma classification can be pursued by the texture features in the images. The texture feature extraction around the optic cup shows the precise results for the identification and classification of glaucoma. From the texture feature extraction, the Support Vector Machine (SVM) classifier used to classify the result. The high level accuracy on different images is done by the classification method. The results show the accuracy of this method.

Robust feature selection algorithm based on transductive SVM wrapper and genetic algorithm: application on computer-aided glaucoma classification

Robust feature selection algorithm based on transductive SVM wrapper and genetic algorithm: application on computer-aided glaucoma classification

Robust feature selection algorithm based on transductive SVM wrapper and genetic algorithm: application on computer-aided glaucoma classification

Glaucoma has become a devastating disease after cataract to cause blindness. Thus, early diagnoses for glaucoma can prevent the vision loss. Computer-aided diagnosis (CAD) systems, which automate the process of ocular disease detection, are urgently needed to alleviate the burden on the clinicians. In the current work, advanced machine-learning algorithms are investigated to propose a robust system for Glaucoma diagnosis based on retinal images. Three features extraction methods, namely the grey-level cooccurrence matrix (GLCM), Hu moments and central moments are combined to form the entry feature vector. To select the most relevant features and taking into account at the same time the unlabelled data existing in medical databases, a new scheme of feature selection algorithm is proposed. It is based on transductive support vector machine (SVM) wrapper and genetic algorithm, which automatically detect and classify the glaucoma disease using fundus images. The effectiveness of the proposed GA-TSVM is evaluated on a public retinal database RIM-ONE using the classification accuracy, sensitivity and specificity metrics. The experimental results established that with 16% of labelled data, the proposed system could easily distinguish between the normal and the affected glaucoma cases.

Joint optic disc and cup boundary extraction from monocular fundus images

Background and objectiveAccurate segmentation of optic disc and cup from monocular color fundus images plays a significant role in the screening and diagnosis of glaucoma. Though optic cup is characterized by the drop in depth from the disc boundary, most existing methods segment the two structures separately and rely only on color and vessel kink based cues due to the lack of explicit depth information in color fundus images. MethodsWe propose a novel boundary-based Conditional Random Field formulation that extracts both the optic disc and cup boundaries in a single optimization step. In addition to the color gradients, the proposed method explicitly models the depth which is estimated from the fundus image itself using a coupled, sparse dictionary trained on a set of image-depth map (derived from Optical Coherence Tomography) pairs. ResultsThe estimated depth achieved a correlation coefficient of 0.80 with respect to the ground truth. The proposed segmentation method outperformed several state-of-the-art methods on five public datasets. The average dice coefficient was in the range of 0.87–0.97 for disc segmentation across three datasets and 0.83 for cup segmentation on the DRISHTI-GS1 test set. The method achieved a good glaucoma classification performance with an average AUC of 0.85 for five fold cross-validation on RIM-ONE v2. ConclusionsWe propose a method to jointly segment the optic disc and cup boundaries by modeling the drop in depth between the two structures. Since our method requires a single fundus image per eye during testing it can be employed in the large-scale screening of glaucoma where expensive 3D imaging is unavailable.

Sensitized Glaucoma Detection Using a Unique Template Based Correlation Filter and Undecimated Isotropic Wavelet Transform

Glaucoma is the most common cause of vision loss and its identification using image processing techniques is apparently becoming more important. This paper reports the development of an automated Glaucoma detection system based on image features of eye fundus photographs, which can be used to detect Glaucoma at an early stage. We have improved the sensitivity of Glaucoma detection by using Neuroretinal rim thickness, Neuroretinal rim area and vessel information of fundus image as additional features along with the cup-to-disc ratio feature that is normally used. A unique template based correlation technique using Pearson-r coefficients is employed to extract the features like cup-to-disc ratio, rim area and rim thickness. We have used vessel information as a new feature which is obtained by segmenting the vessels by employing an undecimated isotropic wavelet transform. Analysis of the extracted proposed features stored as a data base during each visit of the patient helps in monitoring the progression of the disease. An efficient methodology is developed showing promising results with better sensitivity and specificity in the classification of Glaucoma and healthy images, respectively.

On the problem of the classification of congenital glaucoma

Objective. To monitor congenital glaucoma and to determine the proportion of the exposed stage of the disease revealed during the initial examination and the long-term follow up. Materials and methods. The present study included 27 children (47 eyes) at the age ranging from 8 to 17 years presenting with various forms of compensated congenital glaucoma at the initial, advanced, and terminal stages of the disease. Results. The clinical and functional characteristics of the eyes at each stage of congenital glaucoma were analyzed during the initial examination and the long-term follow-up period. It was found that the currently universally accepted classification of congenital glaucoma that subdivides the disease into stages based on the structural anatomical changes in the eyes ceases to adequately reflect the objective state of the visual system as the child grows. Conclusion. The study has demonstrated that the stage of congenital glaucoma needs to be corrected in accordance with the age and growth of the child and the possibility of its examination with the use of the psychophysical methods and the evaluation of visual acuity.