Computer-aided diagnosis of glaucoma using fundus images: A review

Progress and challenges of in vivo flow cytometry and its applications in circulating cells of eyes

Circulating inflammatory cells in eyes have emerged as early indicators of numerous major diseases, yet the monitoring of these cells remains an underdeveloped field. In vivo flow cytometry (IVFC), a noninvasive technique, offers the promise of real-time, dynamic quantification of circulating cells. However, IVFC has not seen extensive applications in the detection of circulating cells in eyes, possibly due to the eye's unique physiological structure and fundus imaging limitations. This study reviews the current research progress in retinal flow cytometry and other fundus examination techniques, such as adaptive optics, ultra-widefield retinal imaging, multispectral imaging, and optical coherence tomography, to propose novel ideas for circulating cell monitoring.

Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation

Pathologic myopia (PM) is a common blinding retinal degeneration suffered by highly myopic population. Early screening of this condition can reduce the damage caused by the associated fundus lesions and therefore prevent vision loss. Automated diagnostic tools based on artificial intelligence methods can benefit this process by aiding clinicians to identify disease signs or to screen mass populations using color fundus photographs as inputs. This paper provides insights about PALM, our open fundus imaging dataset for pathological myopia recognition and anatomical structure annotation. Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment. In addition, this paper elaborates on other details such as the labeling process used to construct the database, the quality and characteristics of the samples and provides other relevant usage notes.

Novel linkage approach to join community-acquired and national data

BACKGROUND

Community optometrists in Scotland have performed regular free-at-point-of-care eye examinations for all, for over 15 years. Eye examinations include retinal imaging but image storage is fragmented and they are not used for research. The Scottish Collaborative Optometry-Ophthalmology Network e-research project aimed to collect these images and create a repository linked to routinely collected healthcare data, supporting the development of pre-symptomatic diagnostic tools.

METHODS

As the image record was usually separate from the patient record and contained minimal patient information, we developed an efficient matching algorithm using a combination of deterministic and probabilistic steps which minimised the risk of false positives, to facilitate national health record linkage. We visited two practices and assessed the data contained in their image device and Practice Management Systems. Practice activities were explored to understand the context of data collection processes. Iteratively, we tested a series of matching rules which captured a high proportion of true positive records compared to manual matches. The approach was validated by testing manual matching against automated steps in three further practices.

RESULTS

A sequence of deterministic rules successfully matched 95% of records in the three test practices compared to manual matching. Adding two probabilistic rules to the algorithm successfully matched 99% of records.

CONCLUSIONS

The potential value of community-acquired retinal images can be harnessed only if they are linked to centrally-held healthcare care data. Despite the lack of interoperability between systems within optometry practices and inconsistent use of unique identifiers, data linkage is possible using robust, almost entirely automated processes.

Are Macula or Optic Nerve Head Structures Better at Diagnosing Glaucoma? An Answer Using Artificial Intelligence and Wide-Field Optical Coherence Tomography

Purpose

We wanted to develop a deep-learning algorithm to automatically segment optic nerve head (ONH) and macula structures in three-dimensional (3D) wide-field optical coherence tomography (OCT) scans and to assess whether 3D ONH or macula structures (or a combination of both) provide the best diagnostic power for glaucoma.

Methods

A cross-sectional comparative study was performed using 319 OCT scans of glaucoma eyes and 298 scans of nonglaucoma eyes. Scans were compensated to improve deep-tissue visibility. We developed a deep-learning algorithm to automatically label major tissue structures, trained with 270 manually annotated B-scans. The performance was assessed using the Dice coefficient (DC). A glaucoma classification algorithm (3D-CNN) was then designed using 500 OCT volumes and corresponding automatically segmented labels. This algorithm was trained and tested on three datasets: cropped scans of macular tissues, those of ONH tissues, and wide-field scans. The classification performance for each dataset was reported using the area under the curve (AUC).

Results

Our segmentation algorithm achieved a DC of 0.94 ± 0.003. The classification algorithm was best able to diagnose glaucoma using wide-field scans, followed by ONH scans, and finally macula scans, with AUCs of 0.99 ± 0.01, 0.93 ± 0.06 and 0.91 ± 0.11, respectively.

Conclusions

This study showed that wide-field OCT may allow for significantly improved glaucoma diagnosis over typical OCTs of the ONH or macula.

Translational Relevance

This could lead to mainstream clinical adoption of 3D wide-field OCT scan technology.

Quality assessment of non-mydriatic fundus photographs for glaucoma screening in primary healthcare centres: a real-world study

BACKGROUND

This study assessed the quality distribution of non-mydriatic fundus photographs (NMFPs) in real-world glaucoma screening and analysed its influencing factors.

METHODS

This cross-sectional study was conducted in primary healthcare centres in the Yinzhou District, China, from 17 March to 3 December 2021. The quality distribution of bilateral NMFPs was assessed by the Digital Reading Department of the Eye Hospital of Wenzhou Medical University. Generalised estimating equations and logistic regression models identified factors affecting image quality.

RESULTS

A total of 17 232 photographs of 8616 subjects were assessed. Of these, 11.9% of images were reliable for the right eyes, while only 4.6% were reliable for the left eyes; 93.6% of images were readable in the right eyes, while 90.3% were readable in the left eyes. In adjusted models, older age was associated with decreased odds of image readability (adjusted OR (aOR)=1.07, 95% CI 1.06~1.08, p<0.001). A larger absolute value of spherical equivalent significantly decreased the odds of image readability (all p<0.001). Media opacity and worse visual acuity had a significantly lower likelihood of achieving readable NMFPs (aOR=1.52, 95% CI 1.31~1.75; aOR=1.70, 95% CI 1.42~2.02, respectively, all p<0.001). Astigmatism axes within 31°~60° and 121°~150° had lower odds of image readability (aOR=1.35, 95% CI 1.11~1.63, p<0.01) than astigmatism axes within 180°±30°.

CONCLUSIONS

The image readability of NMFPs in large-scale glaucoma screening for individuals 50 years and older is comparable with relevant studies, but image reliability is unsatisfactory. Addressing the associated factors may be vital when implementing ophthalmological telemedicine in underserviced areas.

TRIAL REGISTRATION NUMBER

ChiCTR2200059277.

DeepDrRVO: A GAN-auxiliary two-step masked transformer framework benefits early recognition and differential diagnosis of retinal vascular occlusion from color fundus photographs

Retinal vascular occlusion (RVO) are common causes of visual impairment. Accurate recognition and differential diagnosis of RVO are unmet medical needs for determining appropriate treatments and health care to properly manage the ocular condition and minimize the damaging effects. To leverage deep learning as a potential solution to detect RVO reliably, we developed a deep learning model on color fundus photographs (CFPs) using a two-step masked SwinTransformer with a Few-Sample Generator (FSG)-auxiliary training framework (called DeepDrRVO) for early and differential RVO diagnosis. The DeepDrRVO was trained on the training set from the in-house cohort and achieved consistently high performance in early recognition and differential diagnosis of RVO in the validation set from the in-house cohort with an accuracy of 86.3%, and other three independent multi-center cohorts with the accuracy of 92.6%, 90.8%, and 100%. Further comparative analysis showed that the proposed DeepDrRVO outperforms conventional state-of-the-art classification models, such as ResNet18, ResNet50d, MobileNetv3, and EfficientNetb1. These results highlight the potential benefits of the deep learning model in automatic early RVO detection and differential diagnosis for improving clinical outcomes and providing insights into diagnosing other ocular diseases with a few-shot learning challenge. The DeepDrRVO is publicly available on https://github.com/ZhouSunLab-Workshops/DeepDrRVO.

A residual connection enabled deep neural network model for optic disk and optic cup segmentation for glaucoma diagnosis

Glaucoma diagnosis at an early stage is vital for the timely initiation of its treatment for and preventing possible vision loss. For glaucoma diagnosis, an accurate estimation of the cup-to-disk ratio (CDR) is required. The current automatic CDR computation techniques attribute lower accuracy and higher complexity, which are important considerations for diagnostics system design to be used for such critical diagnoses. The current methods involve a deeper deep learning model, comprising a large number of parameters, which results in higher system complexity and training/testing time. To address these challenges, this paper proposes a Residual Connection (non-identity)-based Deep Neural Network (RC-DNN), which is based on non-identity residual connectivity for joint optic disk (OD) and optic cup (OC) detection. The proposed model is emboldened by efficient residual connectivity, which is beneficial in several ways. First, the model is efficient and can perform simultaneous segmentation of the OC and OD. Second, the efficient residual information flow permeates the vanishing gradient problem which results in faster converges of the model. Third, feature inspiration empowers the network to perform the segmentation with only a few network layers. We performed a comprehensive performance evaluation of the developed model based on its training in RIM-ONE and DRISHTIGS databases. For OC segmentation, for the images (test set) from {DRISHTI-GS and RIM-ONE} datasets, our proposed model achieves the dice coefficient, Jaccard coefficient, sensitivity, specificity, and balanced accuracy of {92.62, 86.52}, {86.87, 77.54}, {94.21, 95.36}, {99.83, 99.639}, and {94.2, 98.9}, respectively. These experimental results indicate that the developed model provides significant performance enhancement for joint OC and OD segmentation. Additionally, the reduced computational complexity based on reduced model parameters and higher segmentation accuracy provides the additional features of efficacy, robustness, and reliability of the developed model. These attributes of the developed model advocate for its deployment of population-scale glaucoma screening programs.

Automated Glaucoma Screening and Diagnosis Based on Retinal Fundus Images Using Deep Learning Approaches: A Comprehensive Review

Glaucoma is a chronic eye disease that may lead to permanent vision loss if it is not diagnosed and treated at an early stage. The disease originates from an irregular behavior in the drainage flow of the eye that eventually leads to an increase in intraocular pressure, which in the severe stage of the disease deteriorates the optic nerve head and leads to vision loss. Medical follow-ups to observe the retinal area are needed periodically by ophthalmologists, who require an extensive degree of skill and experience to interpret the results appropriately. To improve on this issue, algorithms based on deep learning techniques have been designed to screen and diagnose glaucoma based on retinal fundus image input and to analyze images of the optic nerve and retinal structures. Therefore, the objective of this paper is to provide a systematic analysis of 52 state-of-the-art relevant studies on the screening and diagnosis of glaucoma, which include a particular dataset used in the development of the algorithms, performance metrics, and modalities employed in each article. Furthermore, this review analyzes and evaluates the used methods and compares their strengths and weaknesses in an organized manner. It also explored a wide range of diagnostic procedures, such as image pre-processing, localization, classification, and segmentation. In conclusion, automated glaucoma diagnosis has shown considerable promise when deep learning algorithms are applied. Such algorithms could increase the accuracy and efficiency of glaucoma diagnosis in a better and faster manner.

Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives

Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.

A novel deep learning model for breast lesion classification using ultrasound Images: A multicenter data evaluation

PURPOSE

Breast cancer is one of the major reasons of death due to cancer in women. Early diagnosis is the most critical key for disease screening, control, and reducing mortality. A robust diagnosis relies on the correct classification of breast lesions. While breast biopsy is referred to as the "gold standard" in assessing both the activity and degree of breast cancer, it is an invasive and time-consuming approach.

METHOD

The current study's primary objective was to develop a novel deep-learning architecture based on the InceptionV3 network to classify ultrasound breast lesions. The main promotions of the proposed architecture were converting the InceptionV3 modules to residual inception ones, increasing their number, and altering the hyperparameters. In addition, we used a combination of five datasets (three public datasets and two prepared from different imaging centers) for training and evaluating the model.

RESULTS

The dataset was split into the train (80%) and test (20%) groups. The model achieved 0.83, 0.77, 0.8, 0.81, 0.81, 0.18, and 0.77 for the precision, recall, F1 score, accuracy, AUC, Root Mean Squared Error, and Cronbach's α in the test group, respectively.

CONCLUSIONS

This study illustrates that the improved InceptionV3 can robustly classify breast tumors, potentially reducing the need for biopsy in many cases.

Classification of Glaucoma Stages Using Image Empirical Mode Decomposition from Fundus Images

One of the most prevalent causes of visual loss and blindness is glaucoma. Conventionally, instrument-based tools are employed for glaucoma screening. However, they are inefficient, time-consuming, and manual. Hence, computerized methodologies are needed for fast and accurate diagnosis of glaucoma. Therefore, we proposed a Computer-Aided Diagnosis (CAD) method for the classification of glaucoma stages using Image Empirical Mode decomposition (IEMD). In this study, IEMD is applied to decompose the preprocessed fundus photographs into different Intrinsic Mode Functions (IMFs) to capture the pixel variations. Then, the significant texture-based descriptors have been computed from the IMFs. A dimensionality reduction approach called Principal Component Analysis (PCA) has been employed to pick the robust descriptors from the retrieved feature set. We used the Analysis of Variance (ANOVA) test for feature ranking. Finally, the LS-SVM classifier has been employed to classify glaucoma stages. The proposed CAD system achieved a classification accuracy of 94.45% for the binary classification on the RIM-ONE r12 database. Our approach demonstrated better glaucoma classification performance than the existing automated systems.

Retinal Glaucoma Public Datasets: What Do We Have and What Is Missing?

Public databases for glaucoma studies contain color images of the retina, emphasizing the optic papilla. These databases are intended for research and standardized automated methodologies such as those using deep learning techniques. These techniques are used to solve complex problems in medical imaging, particularly in the automated screening of glaucomatous disease. The development of deep learning techniques has demonstrated potential for implementing protocols for large-scale glaucoma screening in the population, eliminating possible diagnostic doubts among specialists, and benefiting early treatment to delay the onset of blindness. However, the images are obtained by different cameras, in distinct locations, and from various population groups and are centered on multiple parts of the retina. We can also cite the small number of data, the lack of segmentation of the optic papillae, and the excavation. This work is intended to offer contributions to the structure and presentation of public databases used in the automated screening of glaucomatous papillae, adding relevant information from a medical point of view. The gold standard public databases present images with segmentations of the disc and cupping made by experts and division between training and test groups, serving as a reference for use in deep learning architectures. However, the data offered are not interchangeable. The quality and presentation of images are heterogeneous. Moreover, the databases use different criteria for binary classification with and without glaucoma, do not offer simultaneous pictures of the two eyes, and do not contain elements for early diagnosis.

Graph deep network for optic disc and optic cup segmentation for glaucoma disease using retinal imaging

The fundus imaging method of eye screening detects eye diseases by segmenting the optic disc (OD) and optic cup (OC). OD and OC are still challenging to segment accurately. This work proposes three-layer graph-based deep architecture with an enhanced fusion method for OD and OC segmentation. CNN encoder-decoder architecture, extended graph network, and approximation via fusion-based rule are explored for connecting local and global information. A graph-based model is developed for combining local and overall knowledge. By extending feature masking, regularization of repetitive features with fusion for combining channels has been done. The performance of the proposed network is evaluated through the analysis of different metric parameters such as dice similarity coefficient (DSC), intersection of union (IOU), accuracy, specificity, sensitivity. Experimental verification of this methodology has been done using the four benchmarks publicly available datasets DRISHTI-GS, RIM-ONE for OD, and OC segmentation. In addition, DRIONS-DB and HRF fundus imaging datasets were analyzed for optimizing the model's performance based on OD segmentation. DSC metric of methodology achieved 0.97 and 0.96 for DRISHTI-GS and RIM-ONE, respectively. Similarly, IOU measures for DRISHTI-GS and RIM-ONE datasets were 0.96 and 0.93, respectively, for OD measurement. For OC segmentation, DSC and IOU were measured as 0.93 and 0.90 respectively for DRISHTI-GS and 0.83 and 0.82 for RIM-ONE data. The proposed technique improved value of metrics with most of the existing methods in terms of DSC and IOU of the results metric of the experiments for OD and OC segmentation.

PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment

Glaucoma is one of the ophthalmological diseases that frequently causes loss of vision in today's society. Previous studies assess which anatomical parameters of the optic nerve can be predictive of glaucomatous damage, but to date there is no test that by itself has sufficient sensitivity and specificity to diagnose this disease. This work provides a public dataset with medical data and fundus images of both eyes of the same patient. Segmentations of the cup and optic disc, as well as the labeling of the patients based on the evaluation of clinical data are also provided. The dataset has been tested with a neural network to classify healthy and glaucoma patients. Specifically, the ResNet-50 has been used as the basis to classify patients using information from each eye independently as well as using the joint information from both eyes of each patient. Results provide the baseline metrics, with the aim of promoting research in the early detection of glaucoma based on the joint analysis of both eyes of the same patient.

An Efficient Hierarchical Optic Disc and Cup Segmentation Network Combined with Multi-task Learning and Adversarial Learning

Automatic and accurate segmentation of optic disc (OD) and optic cup (OC) in fundus images is a fundamental task in computer-aided ocular pathologies diagnosis. The complex structures, such as blood vessels and macular region, and the existence of lesions in fundus images bring great challenges to the segmentation task. Recently, the convolutional neural network-based methods have exhibited its potential in fundus image analysis. In this paper, we propose a cascaded two-stage network architecture for robust and accurate OD and OC segmentation in fundus images. In the first stage, the U-Net like framework with an improved attention mechanism and focal loss is proposed to detect accurate and reliable OD location from the full-scale resolution fundus images. Based on the outputs of the first stage, a refined segmentation network in the second stage that integrates multi-task framework and adversarial learning is further designed for OD and OC segmentation separately. The multi-task framework is conducted to predict the OD and OC masks by simultaneously estimating contours and distance maps as auxiliary tasks, which can guarantee the smoothness and shape of object in segmentation predictions. The adversarial learning technique is introduced to encourage the segmentation network to produce an output that is consistent with the true labels in space and shape distribution. We evaluate the performance of our method using two public retinal fundus image datasets (RIM-ONE-r3 and REFUGE). Extensive ablation studies and comparison experiments with existing methods demonstrate that our approach can produce competitive performance compared with state-of-the-art methods.

A Comprehensive Review of Methods and Equipment for Aiding Automatic Glaucoma Tracking

Glaucoma is a chronic optic neuropathy characterized by irreversible damage to the retinal nerve fiber layer (RNFL), resulting in changes in the visual field (VC). Glaucoma screening is performed through a complete ophthalmological examination, using images of the optic papilla obtained in vivo for the evaluation of glaucomatous characteristics, eye pressure, and visual field. Identifying the glaucomatous papilla is quite important, as optical papillary images are considered the gold standard for tracking. Therefore, this article presents a review of the diagnostic methods used to identify the glaucomatous papilla through technology over the last five years. Based on the analyzed works, the current state-of-the-art methods are identified, the current challenges are analyzed, and the shortcomings of these methods are investigated, especially from the point of view of automation and independence in performing these measurements. Finally, the topics for future work and the challenges that need to be solved are proposed.

Grade classification of human glioma using a convolutional neural network based on mid-infrared spectroscopy mapping

This study proposes a convolutional neural network (CNN)-based computer-aided diagnosis (CAD) system for the grade classification of human glioma by using mid-infrared (MIR) spectroscopic mappings. Through data augmentation of pixels recombination, the mappings in the training set increased almost 161 times relative to the original mappings. The pixels of the recombined mappings in the training set came from all of the one-dimensional (1D) vibrational spectroscopy of 62 (almost 80% of all 77 patients) patients at specific bands. Compared with the performance of the CNN-CAD system based on the 1D vibrational spectroscopy, we found that the mean diagnostic accuracy of the recombined MIR spectroscopic mappings at peaks of 2917 cm^-1 , 1539 cm^-1 and 1234 cm^-1 on the test set performed higher and the model also had more stable patterns. This research demonstrates that two-dimensional MIR mapping at a single frequency can be used by the CNN-CAD system for diagnosis and the research also gives a prompt that the mapping collection process can be replaced by a single-frequency IR imaging system, which is cheaper and more portable than a Fourier transform infrared microscopy and thus may be widely utilized in hospitals to provide meaningful assistance for pathologists in clinics.

Discrimination of Breast Cancer Based on Ultrasound Images and Convolutional Neural Network

The aim of our study was to establish an artificial intelligence tool for the diagnosis of breast disease base on ultrasound (US) images. A deep learning algorithm Efficient-Det assisted US diagnosis method was developed to determine breast suspicious lesions as benign, malignant, or normal. Totally 1181 US images from 487 patients of our hospital and 694 publicly accessible images were employed for modeling, including 558 benign images, 370 malignant images, and 253 normal tissue images. The actual diagnosis results for the patients were determined by the biopsy or surgery. Efficient-Det was first retrained using an exclusive public breast cancer US dataset with transfer learning techniques. A blind test set consisting of 50 benign, 50 malignant, and 50 normal tissue images was randomly picked from the patients' images as the independent test set to test its searching ability on suspicious tumor regions. Furthermore, the confusion matrix and classification accuracy were employed as evaluation metrics to select the optimal classification models. Efficient-Det has demonstrated remarkable progress in general image recognition tasks with specific advantages of locating and identifying tumor areas simultaneously. Compared to the manual method (mean accuracy: 95.3% and 60 s per image) and traditional feature engineering method (mean accuracy: 90% and 15 s per image), our Efficient-Det has the capability of providing a competitive (mean accuracy: 92.6%) and fast (0.06 s per image) classification result. The deployment of Efficient-Det in our local breast cancer discrimination task exhibits specific applicability within real clinical workflows.

Glaucoma Detection Using Image Processing and Supervised Learning for Classification

A difficult challenge in the realm of biomedical engineering is the detection of physiological changes occurring inside the human body, which is a difficult undertaking. At the moment, these irregularities are graded manually, which is very difficult, time-consuming, and tiresome due to the many complexities associated with the methods involved in their identification. In order to identify illnesses at an early stage, the use of computer-assisted diagnostics has acquired increased attention as a result of the requirement of a disease detection system. The major goal of this proposed work is to build a computer-aided design (CAD) system to help in the early identification of glaucoma as well as the screening and treatment of the disease. The fundus camera is the most affordable image analysis modality available, and it meets the financial needs of the general public. The extraction of structural characteristics from the segmented optic disc and the segmented optic cup may be used to characterize glaucoma and determine its severity. For this study, the primary goal is to estimate the potential of the image analysis model for the early identification and diagnosis of glaucoma, as well as for the evaluation of ocular disorders. The suggested CAD system would aid the ophthalmologist in the diagnosis of ocular illnesses by providing a second opinion as a judgment made by human specialists in a controlled environment. An ensemble-based deep learning model for the identification and diagnosis of glaucoma is in its early stages now. This method's initial module is an ensemble-based deep learning model for glaucoma diagnosis, which is the first of its kind ever developed. It was decided to use three pretrained convolutional neural networks for the categorization of glaucoma. These networks included the residual network (ResNet), the visual geometry group network (VGGNet), and the GoogLeNet. It was necessary to use five different data sets in order to determine how well the proposed algorithm performed. These data sets included the DRISHTI-GS, the Optic Nerve Segmentation Database (DRIONS-DB), and the High-Resolution Fundus (HRF). Accuracy of 91.11% for the PSGIMSR data set and the sensitivity of 85.55% and specificity of 95.20% for the suggested ensemble architecture on the PSGIMSR data set were achieved. Similarly, accuracy rates of 95.63%, 98.67%, 95.64%, and 88.96% were achieved using the DRIONS-DB, HRF, DRISHTI-GS, and combined data sets, respectively.

Machine Learning and Deep Learning Techniques for Optic Disc and Cup Segmentation – A Review

Background

Globally, glaucoma is the second leading cause of blindness. Detecting glaucoma in the early stages is essential to avoid disease complications, which lead to blindness. Thus, computer-aided diagnosis systems are powerful tools to overcome the shortage of glaucoma screening programs.

Methods

A systematic search of public databases, including PubMed, Google Scholar, and other sources, was performed to identify relevant studies to overview the publicly available fundus image datasets used to train, validate, and test machine learning and deep learning methods. Additionally, existing machine learning and deep learning methods for optic cup and disc segmentation were surveyed and critically reviewed.

Results

Eight fundus images datasets were publicly available with 15,445 images labeled with glaucoma or non-glaucoma, and manually annotated optic disc and cup boundaries were found. Five metrics were identified for evaluating the developed models. Finally, three main deep learning architectural designs were commonly used for optic disc and optic cup segmentation.

Conclusion

We provided future research directions to formulate robust optic cup and disc segmentation systems. Deep learning can be utilized in clinical settings for this task. However, many challenges need to be addressed before using this strategy in clinical trials. Finally, two deep learning architectural designs have been widely adopted, such as U-net and its variants.

Evaluations of Deep Learning Approaches for Glaucoma Screening Using Retinal Images from Mobile Device

Glaucoma is a silent disease that leads to vision loss or irreversible blindness. Current deep learning methods can help glaucoma screening by extending it to larger populations using retinal images. Low-cost lenses attached to mobile devices can increase the frequency of screening and alert patients earlier for a more thorough evaluation. This work explored and compared the performance of classification and segmentation methods for glaucoma screening with retinal images acquired by both retinography and mobile devices. The goal was to verify the results of these methods and see if similar results could be achieved using images captured by mobile devices. The used classification methods were the Xception, ResNet152 V2 and the Inception ResNet V2 models. The models’ activation maps were produced and analysed to support glaucoma classifier predictions. In clinical practice, glaucoma assessment is commonly based on the cup-to-disc ratio (CDR) criterion, a frequent indicator used by specialists. For this reason, additionally, the U-Net architecture was used with the Inception ResNet V2 and Inception V3 models as the backbone to segment and estimate CDR. For both tasks, the performance of the models reached close to that of state-of-the-art methods, and the classification method applied to a low-quality private dataset illustrates the advantage of using cheaper lenses.

Glaucoma disease diagnosis with an artificial algae-based deep learning algorithm

Glaucoma disease is optic neuropathy; in glaucoma, the optic nerve is damaged because the long duration of intraocular pressure can be caused blindness. Nowadays, deep learning classification algorithms are widely used to diagnose various diseases. However, in general, the training of deep learning algorithms is carried out by traditional gradient-based learning techniques that converge slowly and are highly likely to fall to the local minimum. In this study, we proposed a novel decision support system based on deep learning to diagnose glaucoma. The proposed system has two stages. In the first stage, the preprocessing of glaucoma disease data is performed by normalization and mean absolute deviation method, and in the second stage, the training of the deep learning is made by the artificial algae optimization algorithm. The proposed system is compared to traditional gradient-based deep learning and deep learning trained with other optimization algorithms like genetic algorithm, particle swarm optimization, bat algorithm, salp swarm algorithm, and equilibrium optimizer. Furthermore, the proposed system is compared to the state-of-the-art algorithms proposed for the glaucoma detection. The proposed system has outperformed other algorithms in terms of classification accuracy, recall, precision, false positive rate, and F1-measure by 0.9815, 0.9795, 0.9835, 0.0165, and 0.9815, respectively.

Detection of Optic Disc Localization from Retinal Fundus Image Using Optimized Color Space

Optic disc localization offers an important clue in detecting other retinal components such as the macula, fovea, and retinal vessels. With the correct detection of this area, sudden vision loss caused by diseases such as age-related macular degeneration and diabetic retinopathy can be prevented. Therefore, there is an increase in computer-aided diagnosis systems in this field. In this paper, an automated method for detecting optic disc localization is proposed. In the proposed method, the fundus images are moved from RGB color space to a new color space by using an artificial bee colony algorithm. In the new color space, the localization of the optical disc is clearer than in the RGB color space. In this method, a matrix called the feature matrix is created. This matrix is obtained from the color pixel values of the image patches containing the optical disc and the image patches not containing the optical disc. Then, the conversion matrix is created. The initial values of this matrix are randomly determined. These two matrices are processed in the artificial bee colony algorithm. Ultimately, the conversion matrix becomes optimal and is applied over the original fundus images. Thus, the images are moved to the new color space. Thresholding is applied to these images, and the optic disc localization is obtained. The success rate of the proposed method has been tested on three general datasets. The accuracy success rate for the DRIVE, DRIONS, and MESSIDOR datasets, respectively, is 100%, 96.37%, and 94.42% for the proposed method.

Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study

BACKGROUND

The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable for screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases.

OBJECTIVE

This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images.

METHODS

A generative adversarial network-based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model's performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model's performance were calculated and presented.

RESULTS

Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in 1 external proprietary data set. In the detection of 6 common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR, and myopia were 0.891, 0.916, 0.912, 0.867, 0.895, and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR, and 0.926 for detecting vision-threatening DR.

CONCLUSIONS

The AD approach achieved high sensitivity and specificity in detecting ocular diseases on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening.

Economic Evaluations of Artificial Intelligence in Ophthalmology

ABSTRACT

Artificial intelligence (AI) is expected to cause significant medical quality enhancements and cost-saving improvements in ophthalmology. Although there has been a rapid growth of studies on AI in the recent years, real-world adoption of AI is still rare. One reason may be because the data derived from economic evaluations of AI in health care, which policy makers used for adopting new technology, have been fragmented and scarce. Most data on economics of AI in ophthalmology are from diabetic retinopathy (DR) screening. Few studies classified costs of AI software, which has been considered as a medical device, into direct medical costs. These costs of AI are composed of initial and maintenance costs. The initial costs may include investment in research and development, and costs for validation of different datasets. Meanwhile, the maintenance costs include costs for algorithms upgrade and hardware maintenance in the long run. The cost of AI should be balanced between manufacturing price and reimbursements since it may pose significant challenges and barriers to providers. Evidence from cost-effectiveness analyses showed that AI, either standalone or used with humans, was more cost-effective than manual DR screening. Notably, economic evaluation of AI for DR screening can be used as a model for AI to other ophthalmic diseases.

Accurate Diagnosis of Diabetic Retinopathy and Glaucoma Using Retinal Fundus Images Based on Hybrid Features and Genetic Algorithm

Diabetic retinopathy (DR) and glaucoma can both be incurable if they are not detected early enough. Therefore, ophthalmologists worldwide are striving to detect them by personally screening retinal fundus images. However, this procedure is not only tedious, subjective, and labor-intensive, but also error-prone. Worse yet, it may not even be attainable in some countries where ophthalmologists are in short supply. A practical solution to this complicated problem is a computer-aided diagnosis (CAD) system—the objective of this work. We propose an accurate system to detect at once any of the two diseases from retinal fundus images. The accuracy stems from two factors. First, we calculate a large set of hybrid features belonging to three groups: first-order statistics (FOS), higher-order statistics (HOS), and histogram of oriented gradient (HOG). Then, these features are skillfully reduced using a genetic algorithm scheme that selects only the most relevant and significant of them. Finally, the selected features are fed to a classifier to detect one of three classes: DR, glaucoma, or normal. Four classifiers are tested for this job: decision tree (DT), naive Bayes (NB), k-nearest neighbor (kNN), and linear discriminant analysis (LDA). The experimental work, conducted on three publicly available datasets, two of them merged into one, shows impressive performance in terms of four standard classification metrics, each computed using k-fold crossvalidation for added credibility. The highest accuracy has been provided by DT—96.67% for DR, 100% for glaucoma, and 96.67% for normal.

Five-Category Intelligent Auxiliary Diagnosis Model of Common Fundus Diseases Based on Fundus Images

Purpose

The discrepancy of the number between ophthalmologists and patients in China is large. Retinal vein occlusion (RVO), high myopia, glaucoma, and diabetic retinopathy (DR) are common fundus diseases. Therefore, in this study, a five-category intelligent auxiliary diagnosis model for common fundus diseases is proposed; the model's area of focus is marked.

Methods

A total of 2000 fundus images were collected; 3 different 5-category intelligent auxiliary diagnosis models for common fundus diseases were trained via different transfer learning and image preprocessing techniques. A total of 1134 fundus images were used for testing. The clinical diagnostic results were compared with the diagnostic results. The main evaluation indicators included sensitivity, specificity, F1-score, area under the concentration-time curve (AUC), 95% confidence interval (CI), kappa, and accuracy. The interpretation methods were used to obtain the model's area of focus in the fundus image.

Results

The accuracy rates of the 3 intelligent auxiliary diagnosis models on the 1134 fundus images were all above 90%, the kappa values were all above 88%, the diagnosis consistency was good, and the AUC approached 0.90. For the 4 common fundus diseases, the best results of sensitivity, specificity, and F1-scores of the 3 models were 88.27%, 97.12%, and 84.02%; 89.94%, 99.52%, and 93.90%; 95.24%, 96.43%, and 85.11%; and 88.24%, 98.21%, and 89.55%, respectively.

Conclusions

This study designed a five-category intelligent auxiliary diagnosis model for common fundus diseases. It can be used to obtain the diagnostic category of fundus images and the model's area of focus.

Translational Relevance

This study will help the primary doctors to provide effective services to all ophthalmologic patients.

Glaucoma screening using an attention-guided stereo ensemble network

Glaucoma is a chronic eye disease, which causes gradual vision loss and eventually blindness. Accurate glaucoma screening at early stage is critical to mitigate its aggravation. Extracting high-quality features are critical in training of classification models. In this paper, we propose a deep ensemble network with attention mechanism that detects glaucoma using optic nerve head stereo images. The network consists of two main sub-components, a deep Convolutional Neural Network that obtains global information and an Attention-Guided Network that localizes optic disc while maintaining beneficial information from other image regions. Both images in a stereo pair are fed into these sub-components, the outputs are fused together to generate the final prediction result. Abundant image features from different views and regions are being extracted, providing compensation when one of the stereo images is of poor quality. The attention-based localization method is trained in a weakly-supervised manner and only image-level annotation is required, which avoids expensive segmentation labelling. Results from real patient images show that our approach increases recall (sensitivity) from the state-of-the-art 88.89% to 95.48%, while maintaining precision and performance stability. The marked reduction in false-negative rate can significantly enhance the chance of successful early diagnosis of glaucoma.

An enhanced deep image model for glaucoma diagnosis using feature-based detection in retinal fundus

This paper proposes a deep image analysis-based model for glaucoma diagnosis that uses several features to detect the formation of glaucoma in retinal fundus. These features are combined with most extracted parameters like inferior, superior, nasal, and temporal region area, and cup-to-disc ratio that overall forms a deep image analysis. This proposed model is exercised to investigate the various aspects related to the prediction of glaucoma in retinal fundus images that help the ophthalmologist in making better decisions for the human eye. The proposed model is presented with the combination of four machine learning algorithms that provide the classification accuracy of 98.60% while other existing models like support vector machine (SVM), K-nearest neighbors (KNN), and Naïve Bayes provide individually with accuracies of 97.61%, 90.47%, and 95.23% respectively. These results clearly demonstrate that this proposed model offers the best methodology to an early diagnosis of glaucoma in retinal fundus.

Noninvasive temporal detection of early retinal vascular changes during diabetes

Diabetes associated complications, including diabetic retinopathy and loss of vision, are major health concerns. Detecting early retinal vascular changes during diabetes is not well documented, and only few studies have addressed this domain. The purpose of this study was to noninvasively evaluate temporal changes in retinal vasculature at very early stages of diabetes using fundus images from preclinical models of diabetes. Non-diabetic and Akita/+ male mice with different duration of diabetes were subjected to fundus imaging using a Micron III imaging system. The images were obtained from 4 weeks- (onset of diabetes), 8 weeks-, 16 weeks-, and 24 weeks-old male Akita/+ and non-diabetic mice. In total 104 fundus images were subjected to analysis for various feature extractions. A combination of Canny Edge Detector and Angiogenesis Analyzer plug-ins in ImageJ were utilized to quantify various retinal vascular changes in fundus images. Statistical analyses were conducted to determine significant differences in the various extracted features from fundus images of diabetic and non-diabetic animals. Our novel image analysis method led to extraction of over 20 features. These results indicated that some of these features were significantly changed with a short duration of diabetes, and others remained the same but changed after longer duration of diabetes. These patterns likely distinguish acute (protective) and chronic (damaging) associated changes with diabetes. We show that with a combination of various plugging one can extract over 20 features from retinal vasculature fundus images. These features change during diabetes, thus allowing the quantification of quality of retinal vascular architecture as biomarkers for disease progression. In addition, our method was able to identify unique differences among diabetic mice with different duration of diabetes. The ability to noninvasively detect temporal retinal vascular changes during diabetes could lead to identification of specific markers important in the development and progression of diabetes mediated-microvascular changes, evaluation of therapeutic interventions, and eventual reversal of these changes in order to stop or delay disease progression.

Offline computer-aided diagnosis for Glaucoma detection using fundus images targeted at mobile devices

BACKGROUND AND OBJECTIVE

Glaucoma, an eye condition that leads to permanent blindness, is typically asymptomatic and therefore difficult to be diagnosed in time. However, if diagnosed in time, Glaucoma can effectively be slowed down by using adequate treatment; hence, an early diagnosis is of utmost importance. Nonetheless, the conventional approaches to diagnose Glaucoma adopt expensive and bulky equipment that requires qualified experts, making it difficult, costly and time-consuming to diagnose large amounts of people. Consequently, new alternatives to diagnose Glaucoma that suppress these issues should be explored.

METHODS

This work proposes an interpretable computer-aided diagnosis (CAD) pipeline that is capable of diagnosing Glaucoma using fundus images and run offline in mobile devices. Several public datasets of fundus images were merged and used to build Convolutional Neural Networks (CNNs) that perform segmentation and classification tasks. These networks are then used to build a pipeline for Glaucoma assessment that outputs a Glaucoma confidence level and also provides several morphological features and segmentations of relevant structures, resulting in an interpretable Glaucoma diagnosis. To assess the performance of this method in a restricted environment, this pipeline was integrated into a mobile application and time and space complexities were assessed.

RESULTS

Considering the test set, the developed pipeline achieved 0.91 and 0.75 of Intersection over Union (IoU) in the optic disc and optic cup segmentation, respectively. With regards to the classification, an accuracy of 0.87 with a sensitivity of 0.85 and an AUC of 0.93 were attained. Moreover, this pipeline runs on an average Android smartphone in under two seconds.

CONCLUSIONS

The results demonstrate the potential that this method can have in the contribution to an early Glaucoma diagnosis. The proposed approach achieved similar or slightly better metrics than the current CAD systems for Glaucoma assessment while running on more restricted devices. This pipeline can, therefore, be used to construct accurate and affordable CAD systems that could enable large Glaucoma screenings, contributing to an earlier diagnose of this condition.

Channel and Spatial Attention Regression Network for Cup-to-Disc Ratio Estimation

Cup-to-disc ratio (CDR) is of great importance during assessing structural changes at the optic nerve head (ONH) and diagnosis of glaucoma. While most efforts have been put on acquiring the CDR number through CNN-based segmentation algorithms followed by the calculation of CDR, these methods usually only focus on the features in the convolution kernel, which is, after all, the operation of the local region, ignoring the contribution of rich global features (such as distant pixels) to the current features. In this paper, a new end-to-end channel and spatial attention regression deep learning network is proposed to deduces CDR number from the regression perspective and combine the self-attention mechanism with the regression network. Our network consists of four modules: the feature extraction module to extract deep features expressing the complicated pattern of optic disc (OD) and optic cup (OC), the attention module including the channel attention block (CAB) and the spatial attention block (SAB) to improve feature representation by aggregating long-range contextual information, the regression module to deduce CDR number directly, and the segmentation-auxiliary module to focus the model’s attention on the relevant features instead of the background region. Especially, the CAB selects relatively important feature maps in channel dimension, shifting the emphasis on the OD and OC region; meanwhile, the SAB learns the discriminative ability of feature representation at pixel level by capturing the relationship of intra-feature map. The experimental results of ORIGA dataset show that our method obtains absolute CDR error of 0.067 and the Pearson’s correlation coefficient of 0.694 in estimating CDR and our method has a great potential in predicting the CDR number.

Machine learning applied to retinal image processing for glaucoma detection: review and perspective

INTRODUCTION

This is a systematic review on the main algorithms using machine learning (ML) in retinal image processing for glaucoma diagnosis and detection. ML has proven to be a significant tool for the development of computer aided technology. Furthermore, secondary research has been widely conducted over the years for ophthalmologists. Such aspects indicate the importance of ML in the context of retinal image processing.

METHODS

The publications that were chosen to compose this review were gathered from Scopus, PubMed, IEEEXplore and Science Direct databases. Then, the papers published between 2014 and 2019 were selected . Researches that used the segmented optic disc method were excluded. Moreover, only the methods which applied the classification process were considered. The systematic analysis was performed in such studies and, thereupon, the results were summarized.

DISCUSSION

Based on architectures used for ML in retinal image processing, some studies applied feature extraction and dimensionality reduction to detect and isolate important parts of the analyzed image. Differently, other works utilized a deep convolutional network. Based on the evaluated researches, the main difference between the architectures is the number of images demanded for processing and the high computational cost required to use deep learning techniques.

CONCLUSIONS

All the analyzed publications indicated it was possible to develop an automated system for glaucoma diagnosis. The disease severity and its high occurrence rates justify the researches which have been carried out. Recent computational techniques, such as deep learning, have shown to be promising technologies in fundus imaging. Although such a technique requires an extensive database and high computational costs, the studies show that the data augmentation and transfer learning techniques have been applied as an alternative way to optimize and reduce networks training.

Current applications of machine learning in the screening and diagnosis of glaucoma: a systematic review and Meta-analysis

AIM

To compare the effectiveness of two well described machine learning modalities, ocular coherence tomography (OCT) and fundal photography, in terms of diagnostic accuracy in the screening and diagnosis of glaucoma.

METHODS

A systematic search of Embase and PubMed databases was undertaken up to 1^st of February 2019. Articles were identified alongside their reference lists and relevant studies were aggregated. A Meta-analysis of diagnostic accuracy in terms of area under the receiver operating curve (AUROC) was performed. For the studies which did not report an AUROC, reported sensitivity and specificity values were combined to create a summary ROC curve which was included in the Meta-analysis.

RESULTS

A total of 23 studies were deemed suitable for inclusion in the Meta-analysis. This included 10 papers from the OCT cohort and 13 from the fundal photos cohort. Random effects Meta-analysis gave a pooled AUROC of 0.957 (95%CI=0.917 to 0.997) for fundal photos and 0.923 (95%CI=0.889 to 0.957) for the OCT cohort. The slightly higher accuracy of fundal photos methods is likely attributable to the much larger database of images used to train the models (59 788 vs 1743).

CONCLUSION

No demonstrable difference is shown between the diagnostic accuracy of the two modalities. The ease of access and lower cost associated with fundal photo acquisition make that the more appealing option in terms of screening on a global scale, however further studies need to be undertaken, owing largely to the poor study quality associated with the fundal photography cohort.

Automated detection of glaucoma using optical coherence tomography angiogram images

Glaucoma is a malady that occurs due to the buildup of fluid pressure in the inner eye. Detection of glaucoma at an early stage is crucial as by 2040, 111.8 million people are expected to be afflicted with glaucoma globally. Feature extraction methods prove to be promising in the diagnosis of glaucoma. In this study, we have used optical coherence tomography angiogram (OCTA) images for automated glaucoma detection. Ocular sinister (OS) from the left eye while ocular dexter (OD) were obtained from right eye of subjects. We have used OS macular, OS disc, OD macular and OD disc images. In this work, local phase quantization (LPQ) technique was applied to extract the features. Information fusion and principal component analysis (PCA) are used to combine and reduce the features. Our method achieved the highest accuracy of 94.3% using LPQ coupled with PCA for right eye optic disc images with AdaBoost classifier. The proposed technique can aid clinicians in glaucoma detection at an early stage. The developed model is ready to be tested with more images before deploying for clinical application.

Fundus Image Classification Using VGG-19 Architecture with PCA and SVD

Automated medical image analysis is an emerging field of research that identifies the disease with the help of imaging technology. Diabetic retinopathy (DR) is a retinal disease that is diagnosed in diabetic patients. Deep neural network (DNN) is widely used to classify diabetic retinopathy from fundus images collected from suspected persons. The proposed DR classification system achieves a symmetrically optimized solution through the combination of a Gaussian mixture model (GMM), visual geometry group network (VGGNet), singular value decomposition (SVD) and principle component analysis (PCA), and softmax, for region segmentation, high dimensional feature extraction, feature selection and fundus image classification, respectively. The experiments were performed using a standard KAGGLE dataset containing 35,126 images. The proposed VGG-19 DNN based DR model outperformed the AlexNet and spatial invariant feature transform (SIFT) in terms of classification accuracy and computational time. Utilization of PCA and SVD feature selection with fully connected (FC) layers demonstrated the classification accuracies of 92.21%, 98.34%, 97.96%, and 98.13% for FC7-PCA, FC7-SVD, FC8-PCA, and FC8-SVD, respectively.