The papilla as screening parameter for early diagnosis of glaucoma

Implementing and evaluating a fully functional AI-enabled model for chronic eye disease screening in a real clinical environment

BACKGROUND

Artificial intelligence (AI) has the potential to increase the affordability and accessibility of eye disease screening, especially with the recent approval of AI-based diabetic retinopathy (DR) screening programs in several countries.

METHODS

This study investigated the performance, feasibility, and user experience of a seamless hardware and software solution for screening chronic eye diseases in a real-world clinical environment in Germany. The solution integrated AI grading for DR, age-related macular degeneration (AMD), and glaucoma, along with specialist auditing and patient referral decision. The study comprised several components: (1) evaluating the entire system solution from recruitment to eye image capture and AI grading for DR, AMD, and glaucoma; (2) comparing specialist's grading results with AI grading results; (3) gathering user feedback on the solution.

RESULTS

A total of 231 patients were recruited, and their consent forms were obtained. The sensitivity, specificity, and area under the curve for DR grading were 100.00%, 80.10%, and 90.00%, respectively. For AMD grading, the values were 90.91%, 78.79%, and 85.00%, and for glaucoma grading, the values were 93.26%, 76.76%, and 85.00%. The analysis of all false positive cases across the three diseases and their comparison with the final referral decisions revealed that only 17 patients were falsely referred among the 231 patients. The efficacy analysis of the system demonstrated the effectiveness of the AI grading process in the study's testing environment. Clinical staff involved in using the system provided positive feedback on the disease screening process, particularly praising the seamless workflow from patient registration to image transmission and obtaining the final result. Results from a questionnaire completed by 12 participants indicated that most found the system easy, quick, and highly satisfactory. The study also revealed room for improvement in the AMD model, suggesting the need to enhance its training data. Furthermore, the performance of the glaucoma model grading could be improved by incorporating additional measures such as intraocular pressure.

CONCLUSIONS

The implementation of the AI-based approach for screening three chronic eye diseases proved effective in real-world settings, earning positive feedback on the usability of the integrated platform from both the screening staff and auditors. The auditing function has proven valuable for obtaining efficient second opinions from experts, pointing to its potential for enhancing remote screening capabilities.

TRIAL REGISTRATION

Institutional Review Board of the Hamburg Medical Chamber (Ethik-Kommission der Ärztekammer Hamburg): 2021-10574-BO-ff.

3-LbNets: Tri-Labeling Deep Convolutional Neural Network for the Automated Screening of Glaucoma, Glaucoma Suspect, and No Glaucoma in Fundus Images

Early detection of glaucoma, a widespread visual disease, can prevent vision loss. Unfortunately, ophthalmologists are scarce and clinical diagnosis requires much time and cost. Therefore, we developed a screening Tri-Labeling deep convolutional neural network (3-LbNets) to identify no glaucoma, glaucoma suspect, and glaucoma cases in global fundus images. 3-LbNets extracts important features from 3 different labeling modals and puts them into an artificial neural network (ANN) to find the final result. The method was effective, with an AUC of 98.66% for no glaucoma, 97.54% for glaucoma suspect, and 97.19% for glaucoma when analysing 206 fundus images evaluated with unanimous agreement from 3 well-trained ophthalmologists (3/3). When analysing 178 difficult to interpret fundus images (with majority agreement (2/3)), this method had an AUC of 80.80% for no glaucoma, 69.52% for glaucoma suspect, and 82.74% for glaucoma cases.Clinical relevance-This establishes a robust global fundus image screening network based on the ensemble method that can optimize glaucoma screening to alleviate the toll on those with glaucoma and prevent glaucoma suspects from developing the disease.

RimNet: A Deep Neural Network Pipeline for Automated Identification of the Optic Disc Rim

Purpose

Accurate neural rim measurement based on optic disc imaging is important to glaucoma severity grading and often performed by trained glaucoma specialists. We aim to improve upon existing automated tools by building a fully automated system (RimNet) for direct rim identification in glaucomatous eyes and measurement of the minimum rim-to-disc ratio (mRDR) in intact rims, the angle of absent rim width (ARW) in incomplete rims, and the rim-to-disc-area ratio (RDAR) with the goal of optic disc damage grading.

Design

Retrospective cross sectional study.

Participants

One thousand and twenty-eight optic disc photographs with evidence of glaucomatous optic nerve damage from 1021 eyes of 903 patients with any form of primary glaucoma were included. The mean age was 63.7 (± 14.9) yrs. The average mean deviation of visual fields was -8.03 (± 8.59).

Methods

The images were required to be of adequate quality, have signs of glaucomatous damage, and be free of significant concurrent pathology as independently determined by glaucoma specialists. Rim and optic cup masks for each image were manually delineated by glaucoma specialists. The database was randomly split into 80/10/10 for training, validation, and testing, respectively. RimNet consists of a deep learning rim and cup segmentation model, a computer vision mRDR measurement tool for intact rims, and an ARW measurement tool for incomplete rims. The mRDR is calculated at the thinnest rim section while ARW is calculated in regions of total rim loss. The RDAR was also calculated. Evaluation on the Drishti-GS dataset provided external validation (Sivaswamy 2015).

Main Outcome Measures

Median Absolute Error (MAE) between glaucoma specialists and RimNet for mRDR and ARW.

Results

On the test set, RimNet achieved a mRDR MAE of 0.03 (0.05), ARW MAE of 31 (89)°, and an RDAR MAE of 0.09 (0.10). On the Drishti-GS dataset, an mRDR MAE of 0.03 (0.04) and an mRDAR MAE of 0.09 (0.10) was observed.

Conclusions

RimNet demonstrated acceptably accurate rim segmentation and mRDR and ARW measurements. The fully automated algorithm presented here would be a valuable component in an automated mRDR-based glaucoma grading system. Further improvements could be made by improving identification and segmentation performance on incomplete rims and expanding the number and variety of glaucomatous training images.

Accuracy of Using Generative Adversarial Networks for Glaucoma Detection During the COVID-19 Pandemic: A Systematic Review and Bibliometric Analysis

Background

Glaucoma leads to irreversible blindness. Globally, it is the second most common retinal disease that leads to blindness, slightly less common than cataracts. Therefore, there is a great need to avoid the silent growth of this disease using recently developed generative adversarial networks (GANs).

Objective

This paper aims to introduce a GAN technology for the diagnosis of eye disorders, particularly glaucoma. This paper illustrates deep adversarial learning as a potential diagnostic tool and the challenges involved in its implementation. This study describes and analyzes many of the pitfalls and problems that researchers will need to overcome to implement this kind of technology.

Methods

To organize this review comprehensively, articles and reviews were collected using the following keywords: (“Glaucoma,” “optic disc,” “blood vessels”) and (“receptive field,” “loss function,” “GAN,” “Generative Adversarial Network,” “Deep learning,” “CNN,” “convolutional neural network” OR encoder). The records were identified from 5 highly reputed databases: IEEE Xplore, Web of Science, Scopus, ScienceDirect, and PubMed. These libraries broadly cover the technical and medical literature. Publications within the last 5 years, specifically 2015-2020, were included because the target GAN technique was invented only in 2014 and the publishing date of the collected papers was not earlier than 2016. Duplicate records were removed, and irrelevant titles and abstracts were excluded. In addition, we excluded papers that used optical coherence tomography and visual field images, except for those with 2D images. A large-scale systematic analysis was performed, and then a summarized taxonomy was generated. Furthermore, the results of the collected articles were summarized and a visual representation of the results was presented on a T-shaped matrix diagram. This study was conducted between March 2020 and November 2020.

Results

We found 59 articles after conducting a comprehensive survey of the literature. Among the 59 articles, 30 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences. The other 29 articles discuss the recent advances in GANs, do practical experiments, and contain analytical studies of retinal disease.

Conclusions

Recent deep learning techniques, namely GANs, have shown encouraging performance in retinal disease detection. Although this methodology involves an extensive computing budget and optimization process, it saturates the greedy nature of deep learning techniques by synthesizing images and solves major medical issues. This paper contributes to this research field by offering a thorough analysis of existing works, highlighting current limitations, and suggesting alternatives to support other researchers and participants in further improving and strengthening future work. Finally, new directions for this research have been identified.

Joint optic disc and optic cup segmentation based on boundary prior and adversarial learning

PURPOSE

The most direct means of glaucoma screening is to use cup-to-disc ratio via colour fundus photography, the first step of which is the precise segmentation of the optic cup (OC) and optic disc (OD). In recent years, convolution neural networks (CNN) have shown outstanding performance in medical segmentation tasks. However, most CNN-based methods ignore the effect of boundary ambiguity on performance, which leads to low generalization. This paper is dedicated to solving this issue.

METHODS

In this paper, we propose a novel segmentation architecture, called BGA-Net, which introduces an auxiliary boundary branch and adversarial learning to jointly segment OD and OC in a multi-label manner. To generate more accurate results, the generative adversarial network is exploited to encourage boundary and mask predictions to be similar to the ground truth ones.

RESULTS

Experimental results show that our BGA-Net system achieves state-of-the-art OC and OD segmentation performance on three publicly available datasets, i.e., the Dice scores for the optic disc/cup on the Drishti-GS, RIM-ONE-r3 and REFUGE datasets are 0.975/0.898, 0.967/0.872 and 0.951/0.866, respectively.

CONCLUSION

In this work, we not only achieve superior OD and OC segmentation results, but also confirm that the values calculated through the geometric relationship between the former two are highly related to glaucoma.

Joint optic disc and cup segmentation based on densely connected depthwise separable convolution deep network

BACKGROUND

Glaucoma is an eye disease that causes vision loss and even blindness. The cup to disc ratio (CDR) is an important indicator for glaucoma screening and diagnosis. Accurate segmentation for the optic disc and cup helps obtain CDR. Although many deep learning-based methods have been proposed to segment the disc and cup for fundus image, achieving highly accurate segmentation performance is still a great challenge due to the heavy overlap between the optic disc and cup.

METHODS

In this paper, we propose a two-stage method where the optic disc is firstly located and then the optic disc and cup are segmented jointly according to the interesting areas. Also, we consider the joint optic disc and cup segmentation task as a multi-category semantic segmentation task for which a deep learning-based model named DDSC-Net (densely connected depthwise separable convolution network) is proposed. Specifically, we employ depthwise separable convolutional layer and image pyramid input to form a deeper and wider network to improve segmentation performance. Finally, we evaluate our method on two publicly available datasets, Drishti-GS and REFUGE dataset.

RESULTS

The experiment results show that the proposed method outperforms state-of-the-art methods, such as pOSAL, GL-Net, M-Net and Stack-U-Net in terms of disc coefficients, with the scores of 0.9780 (optic disc) and 0.9123 (optic cup) on the DRISHTI-GS dataset, and the scores of 0.9601 (optic disc) and 0.8903 (optic cup) on the REFUGE dataset. Particularly, in the more challenging optic cup segmentation task, our method outperforms GL-Net by 0.7[Formula: see text] in terms of disc coefficients on the Drishti-GS dataset and outperforms pOSAL by 0.79[Formula: see text] on the REFUGE dataset, respectively.

CONCLUSIONS

The promising segmentation performances reveal that our method has the potential in assisting the screening and diagnosis of glaucoma.

Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images

In this paper, we propose a method for localizing the optic nerve head and segmenting the optic disc/cup in retinal fundus images. The approach is based on a simple two-stage Mask-RCNN compared to sophisticated methods that represent the state-of-the-art in the literature. In the first stage, we detect and crop around the optic nerve head then feed the cropped image as input for the second stage. The second stage network is trained using a weighted loss to produce the final segmentation. To further improve the detection in the first stage, we propose a new fine-tuning strategy by combining the cropping output of the first stage with the original training image to train a new detection network using different scales for the region proposal network anchors. We evaluate the method on Retinal Fundus Images for Glaucoma Analysis (REFUGE), Magrabi, and MESSIDOR datasets. We used the REFUGE training subset to train the models in the proposed method. Our method achieved 0.0430 mean absolute error in the vertical cup-to-disc ratio (MAE vCDR) on the REFUGE test set compared to 0.0414 obtained using complex and multiple ensemble networks methods. The models trained with the proposed method transfer well to datasets outside REFUGE, achieving a MAE vCDR of 0.0785 and 0.077 on MESSIDOR and Magrabi datasets, respectively, without being retrained. In terms of detection accuracy, the proposed new fine-tuning strategy improved the detection rate from 96.7% to 98.04% on MESSIDOR and from 93.6% to 100% on Magrabi datasets compared to the reported detection rates in the literature.

Automated Glaucoma Screening from Retinal Fundus Image Using Deep Learning

Glaucoma is the second leading cause of blindness worldwide. This paper proposes an automated glaucoma screening method using retinal fundus images via the ensemble technique to fuse the results of different classification networks and the result of each classification network was fed as an input to a simple artificial neural network (ANN) to obtain the final result. Three public datasets, i.e., ORIGA-650, RIM-ONE R3, and DRISHTI-GS were used for training and evaluating the performance of the proposed network. The experimental results showed that the proposed network outperformed other state-of-art glaucoma screening algorithms with AUC of 0.94. Our proposed algorithms showed promising potential as a medical support system for glaucoma screening especially in low resource countries.

An efficient optic cup segmentation method decreasing the influences of blood vessels

BACKGROUND

Optic cup is an important structure in ophthalmologic diagnosis such as glaucoma. Automatic optic cup segmentation is also a key issue in computer aided diagnosis based on digital fundus image. However, current methods didn't effectively solve the problem of edge blurring caused by blood vessels around the optic cup.

METHODS

In this study, an improved Bertalmio-Sapiro-Caselles-Ballester (BSCB) model was proposed to eliminate the noising induced by blood vessel. First, morphological operations were performed to get the enhanced green channel image. Then blood vessels were extracted and filled by improved BSCB model. Finally, Local Chart-Vest model was used to segment the optic cup. A total of 94 samples which included 32 glaucoma fundus images and 62 normal fundus images were experimented.

RESULTS

The evaluation parameters of F-score and the boundary distance achieved by the proposed method against the results from experts were 0.7955 ± 0.0724 and 11.42 ± 3.61, respectively. Average vertical optic cup-to-disc ratio values of the normal and glaucoma samples achieved by the proposed method were 0.4369 ± 0.1193 and 0.7156 ± 0.0698, which were also close to those by experts. In addition, 39 glaucoma images from the public dataset RIM-ONE were also used for methodology evaluation.

CONCLUSIONS

The results showed that our proposed method could overcome the influence of blood vessels in some degree and was competitive to other current optic cup segmentation algorithms. This novel methodology will be expected to use in clinic in the field of glaucoma early detection.

Optic cup segmentation from fundus images for glaucoma diagnosis

Glaucoma is a serious disease that can cause complete, permanent blindness, and its early diagnosis is very difficult. In recent years, computer-aided screening and diagnosis of glaucoma has made considerable progress. The optic cup segmentation from fundus images is an extremely important part for the computer-aided screening and diagnosis of glaucoma. This paper presented an automatic optic cup segmentation method that used both color difference information and vessel bends information from fundus images to determine the optic cup boundary. During the implementation of this algorithm, not only were the locations of the 2 types of information points used, but also the confidences of the information points were evaluated. In this way, the information points with higher confidence levels contributed more to the determination of the final cup boundary. The proposed method was evaluated using a public database for fundus images. The experimental results demonstrated that the cup boundaries obtained by the proposed method were more consistent than existing methods with the results obtained by ophthalmologists.

How strong is the relationship between glaucoma, the retinal nerve fibre layer, and neurodegenerative diseases such as Alzheimer's disease and multiple sclerosis?

Glaucoma is a neurodegenerative disorder with established relationships with ocular structures such as the retinal nerve fibre layer (RNFL) and the ganglion cell layer (GCL). Ocular imaging techniques such as optical coherence tomography (OCT) allow for quantitative measurement of these structures. OCT has been used in the monitoring of glaucoma, as well as investigating other neurodegenerative conditions such as Alzheimer's disease (AD) and multiple sclerosis (MS). In this review, we highlight the association between these disorders and ocular structures (RNFL and GCL), examining their usefulness as biomarkers of neurodegeneration. The average RNFL thickness loss in patients with AD is 11 μm, and 7 μm in MS patients. Most of the studies investigating these changes are cross-sectional. Further longitudinal studies are required to assess sensitivity and specificity of these potential ocular biomarkers to neurodegenerative disease progression.

A survey on computer aided diagnosis for ocular diseases

Background

Computer Aided Diagnosis (CAD), which can automate the detection process for ocular diseases, has attracted extensive attention from clinicians and researchers alike. It not only alleviates the burden on the clinicians by providing objective opinion with valuable insights, but also offers early detection and easy access for patients.

Method

We review ocular CAD methodologies for various data types. For each data type, we investigate the databases and the algorithms to detect different ocular diseases. Their advantages and shortcomings are analyzed and discussed.

Result

We have studied three types of data (i.e., clinical, genetic and imaging) that have been commonly used in existing methods for CAD. The recent developments in methods used in CAD of ocular diseases (such as Diabetic Retinopathy, Glaucoma, Age-related Macular Degeneration and Pathological Myopia) are investigated and summarized comprehensively.

Conclusion

While CAD for ocular diseases has shown considerable progress over the past years, the clinical importance of fully automatic CAD systems which are able to embed clinical knowledge and integrate heterogeneous data sources still show great potential for future breakthrough.

The East London glaucoma prediction score: web-based validation of glaucoma risk screening tool

AIM

It is difficult for Optometrists and General Practitioners to know which patients are at risk. The East London glaucoma prediction score (ELGPS) is a web based risk calculator that has been developed to determine Glaucoma risk at the time of screening. Multiple risk factors that are available in a low tech environment are assessed to provide a risk assessment. This is extremely useful in settings where access to specialist care is difficult. Use of the calculator is educational. It is a free web based service. Data capture is user specific.

METHOD

The scoring system is a web based questionnaire that captures and subsequently calculates the relative risk for the presence of Glaucoma at the time of screening. Three categories of patient are described: Unlikely to have Glaucoma; Glaucoma Suspect and Glaucoma. A case review methodology of patients with known diagnosis is employed to validate the calculator risk assessment.

RESULTS

Data from the patient records of 400 patients with an established diagnosis has been captured and used to validate the screening tool. The website reports that the calculated diagnosis correlates with the actual diagnosis 82% of the time. Biostatistics analysis showed: Sensitivity = 88%; Positive predictive value = 97%; Specificity = 75%.

CONCLUSION

Analysis of the first 400 patients validates the web based screening tool as being a good method of screening for the at risk population. The validation is ongoing. The web based format will allow a more widespread recruitment for different geographic, population and personnel variables.

The medical and surgical treatment of glaucoma

BACKGROUND

Ongoing demographic changes in Europe are heightening the importance of adequate treatment for glaucoma, a disorder that is markedly more common in the elderly.

METHOD

A selective search for relevant literature, including Cochrane Reviews and the guidelines of the European Glaucoma Society, regarding the topical and surgical treatment of glaucoma.

RESULTS

It is recommended that the intraocular pressure (IOP) should be lowered by 20% to 50% from its baseline value, depending on the extent of already existing damage, the rate of progression, the baseline IOP, and the age of the patient. Topical monotherapy can lower the IOP by 15% to 30%. The success rate of filtration surgery has risen because of the intraoperative application of topical antimetabolites and currently ranges from 50% to 90%, depending on the study.

CONCLUSIONS

The goal of glaucoma treatment is to protect the patient from blindness and visual impairment while keeping the treatment-related decline in quality of life to a minimum. Any type of glaucoma treatment, be it medical or surgical, must further this aim in consideration of the situation of the individual patient.