Accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema

Artificial Intelligence to Differentiate Pediatric Pseudopapilledema and True Papilledema on Fundus Photographs

Purpose

To develop and test an artificial intelligence (AI) model to aid in differentiating pediatric pseudopapilledema from true papilledema on fundus photographs.

Design

Multicenter retrospective study.

Subjects

A total of 851 fundus photographs from 235 children (age < 18 years) with pseudopapilledema and true papilledema.

Methods

Four pediatric neuro-ophthalmologists at 4 different institutions contributed fundus photographs of children with confirmed diagnoses of papilledema or pseudopapilledema. An AI model to classify fundus photographs as papilledema or pseudopapilledema was developed using a DenseNet backbone and a tribranch convolutional neural network. We performed 10-fold cross-validation and separately analyzed an external test set. The AI model's performance was compared with 2 masked human expert pediatric neuro-ophthalmologists, who performed the same classification task.

Main Outcome Measures

Accuracy, sensitivity, and specificity of the AI model compared with human experts.

Results

The area under receiver operating curve of the AI model was 0.77 for the cross-validation set and 0.81 for the external test set. The accuracy of the AI model was 70.0% for the cross-validation set and 73.9% for the external test set. The sensitivity of the AI model was 73.4% for the cross-validation set and 90.4% for the external test set. The AI model's accuracy was significantly higher than human experts on the cross validation set (P < 0.002), and the model's sensitivity was significantly higher on the external test set (P = 0.0002). The specificity of the AI model and human experts was similar (56.4%-67.3%). Moreover, the AI model was significantly more sensitive at detecting mild papilledema than human experts, whereas AI and humans performed similarly on photographs of moderate-to-severe papilledema. On review of the external test set, only 1 child (with nearly resolved pseudotumor cerebri) had both eyes with papilledema incorrectly classified as pseudopapilledema.

Conclusions

When classifying fundus photographs of pediatric papilledema and pseudopapilledema, our AI model achieved > 90% sensitivity at detecting papilledema, superior to human experts. Due to the high sensitivity and low false negative rate, AI may be useful to triage children with suspected papilledema requiring work-up to evaluate for serious underlying neurologic conditions.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Explainable AI: Machine Learning Interpretation in Blackcurrant Powders

Recently, explainability in machine and deep learning has become an important area in the field of research as well as interest, both due to the increasing use of artificial intelligence (AI) methods and understanding of the decisions made by models. The explainability of artificial intelligence (XAI) is due to the increasing consciousness in, among other things, data mining, error elimination, and learning performance by various AI algorithms. Moreover, XAI will allow the decisions made by models in problems to be more transparent as well as effective. In this study, models from the 'glass box' group of Decision Tree, among others, and the 'black box' group of Random Forest, among others, were proposed to understand the identification of selected types of currant powders. The learning process of these models was carried out to determine accuracy indicators such as accuracy, precision, recall, and F1-score. It was visualized using Local Interpretable Model Agnostic Explanations (LIMEs) to predict the effectiveness of identifying specific types of blackcurrant powders based on texture descriptors such as entropy, contrast, correlation, dissimilarity, and homogeneity. Bagging (Bagging_100), Decision Tree (DT0), and Random Forest (RF7_gini) proved to be the most effective models in the framework of currant powder interpretability. The measures of classifier performance in terms of accuracy, precision, recall, and F1-score for Bagging_100, respectively, reached values of approximately 0.979. In comparison, DT0 reached values of 0.968, 0.972, 0.968, and 0.969, and RF7_gini reached values of 0.963, 0.964, 0.963, and 0.963. These models achieved classifier performance measures of greater than 96%. In the future, XAI using agnostic models can be an additional important tool to help analyze data, including food products, even online.

Development of a deep learning model to distinguish the cause of optic disc atrophy using retinal fundus photography

The differential diagnosis for optic atrophy can be challenging and requires expensive, time-consuming ancillary testing to determine the cause. While Leber's hereditary optic neuropathy (LHON) and optic neuritis (ON) are both clinically significant causes for optic atrophy, both relatively rare in the general population, contributing to limitations in obtaining large imaging datasets. This study therefore aims to develop a deep learning (DL) model based on small datasets that could distinguish the cause of optic disc atrophy using only fundus photography. We retrospectively reviewed fundus photographs of 120 normal eyes, 30 eyes (15 patients) with genetically-confirmed LHON, and 30 eyes (26 patients) with ON. Images were split into a training dataset and a test dataset and used for model training with ResNet-18. To visualize the critical regions in retinal photographs that are highly associated with disease prediction, Gradient-Weighted Class Activation Map (Grad-CAM) was used to generate image-level attention heat maps and to enhance the interpretability of the DL system. In the 3-class classification of normal, LHON, and ON, the area under the receiver operating characteristic curve (AUROC) was 1.0 for normal, 0.988 for LHON, and 0.990 for ON, clearly differentiating each class from the others with an overall total accuracy of 0.93. Specifically, when distinguishing between normal and disease cases, the precision, recall, and F1 scores were perfect at 1.0. Furthermore, in the differentiation of LHON from other conditions, ON from others, and between LHON and ON, we consistently observed precision, recall, and F1 scores of 0.8. The model performance was maintained until only 10% of the pixel values of the image, identified as important by Grad-CAM, were preserved and the rest were masked, followed by retraining and evaluation.

Recent advances in the use of optical coherence tomography in neuro-ophthalmology: A review

Optical coherence tomography (OCT) is an in vivo imaging modality that provides non-invasive, high resolution and fast cross-sectional images of the optic nerve head, retina and choroid. OCT angiography (OCTA) is an emerging tool. It is a non-invasive, dye-free imaging approach of visualising the microvasculature of the retina and choroid by employing motion contrast imaging for blood flow detection and is gradually receiving attention for its potential roles in various neuro-ophthalmic and retinal conditions. We will review the clinical utility of the OCT in the management of various common neuro-ophthalmic and neurological disorders. We also review some of the OCTA research findings in these conditions. Finally, we will discuss the limitations of OCT as well as introduce other emerging technologies.

The Current State of Artificial Intelligence in Neuro-Ophthalmology. A Review

This article presents a summary of recent advances in the development and use of complex systems using artificial intelligence (AI) in neuro-ophthalmology. The aim of the following article is to present the principles of AI and algorithms that are currently being used or are still in the stage of evaluation or validation within the neuro-ophthalmology environment. For the purpose of this text, a literature search was conducted using specific keywords in available scientific databases, cumulatively up to April 2023. The AI systems developed across neuro-ophthalmology mostly achieve high sensitivity, specificity and accuracy. Individual AI systems and algorithms are subsequently selected, simply described and compared in the article. The results of the individual studies differ significantly, depending on the chosen methodology, the set goals, the size of the test, evaluated set, and the evaluated parameters. It has been demonstrated that the evaluation of various diseases will be greatly speeded up with the help of AI and make the diagnosis more efficient in the future, thus showing a high potential to be a useful tool in clinical practice even with a significant increase in the number of patients.

Multimodal and multi-omics-based deep learning model for screening of optic neuropathy

Purpose

To examine the use of multimodal data and multi-omics strategies for optic nerve disease screening.

Methods

This was a single-center retrospective study. A deep learning model was created from fundus photography and infrared reflectance (IR) images of patients with diabetic optic neuropathy, glaucomatous optic neuropathy, and optic neuritis. Patients who were seen at the Ophthalmology Department of First Affiliated Hospital of Nanchang University in Jiangxi Province from November 2019 to April 2023 were included in this study. The data were analyzed in single and multimodal modes following the traditional omics, Resnet101, and fusion models. The accuracy and area-under-the-curve (AUC) of each model were compared.

Results

A total of 312 images fundus and infrared fundus photographs were collected from 156 patients. When multi-modal data was used, the accuracy of the traditional omics mode, Resnet101, and fusion models with the training set were 0.97, 0.98, and 0.99, respectively. The accuracy of the same models with the test sets were 0.72, 0.87, and 0.88, respectively. We compared single- and multi-mode states by applying the data to the different groups in the learning model. In the traditional omics model, the macro-average AUCs of the features extracted from fundus photography, IR images, and multimodal data were 0.94, 0.90, and 0.96, respectively. When the same data were processed in the Resnet101 model, the scores were 0.97 equally. However, when multimodal data was utilized, the macro-average AUCs in the traditional omics, Resnet101, and fusion modesl were 0.96, 0.97, and 0.99, respectively.

Conclusion

The deep learning model based on multimodal data and multi-omics strategies can improve the accuracy of screening and diagnosing diabetic optic neuropathy, glaucomatous optic neuropathy, and optic neuritis.

Deep learning system for distinguishing optic neuritis from non-arteritic anterior ischemic optic neuropathy at acute phase based on fundus photographs

Purpose

To develop a deep learning system to differentiate demyelinating optic neuritis (ON) and non-arteritic anterior ischemic optic neuropathy (NAION) with overlapping clinical profiles at the acute phase.

Methods

We developed a deep learning system (ONION) to distinguish ON from NAION at the acute phase. Color fundus photographs (CFPs) from 871 eyes of 547 patients were included, including 396 ON from 232 patients and 475 NAION from 315 patients. Efficientnet-B0 was used to train the model, and the performance was measured by calculating the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Also, Cohen's kappa coefficients were obtained to compare the system's performance to that of different ophthalmologists.

Results

In the validation data set, the ONION system distinguished between acute ON and NAION achieved the following mean performance: time-consuming (23 s), AUC 0.903 (95% CI 0.827-0.947), sensitivity 0.796 (95% CI 0.704-0.864), and specificity 0.865 (95% CI 0.783-0.920). Testing data set: time-consuming (17 s), AUC 0.902 (95% CI 0.832-0.944), sensitivity 0.814 (95% CI 0.732-0.875), and specificity 0.841 (95% CI 0.762-0.897). The performance (κ = 0.805) was comparable to that of a retinal expert (κ = 0.749) and was better than the other four ophthalmologists (κ = 0.309-0.609).

Conclusion

The ONION system performed satisfactorily distinguishing ON from NAION at the acute phase. It might greatly benefit the challenging differentiation between ON and NAION.

Diagnosis of Optic Disc Oedema: Fundus Features, Ocular Imaging Findings, and Artificial Intelligence

Optic disc swelling is a manifestation of a broad range of processes affecting the optic nerve head and/or the anterior segment of the optic nerve. Accurately diagnosing optic disc oedema, grading its severity, and recognising its cause, is crucial in order to treat patients in a timely manner and limit vision loss. Some ocular fundus features, in light of a patient's history and visual symptoms, may suggest a specific mechanism or aetiology of the visible disc oedema, but current criteria can at most enable an educated guess as to the most likely cause. In many cases only the clinical evolution and ancillary testing can inform the exact diagnosis. The development of ocular fundus imaging, including colour fundus photography, fluorescein angiography, optical coherence tomography, and multimodal imaging, has provided assistance in quantifying swelling, distinguishing true optic disc oedema from pseudo-optic disc oedema, and differentiating among the numerous causes of acute optic disc oedema. However, the diagnosis of disc oedema is often delayed or not made in busy emergency departments and outpatient neurology clinics. Indeed, most non-eye care providers are not able to accurately perform ocular fundus examination, increasing the risk of diagnostic errors in acute neurological settings. The implementation of non-mydriatic fundus photography and artificial intelligence technology in the diagnostic process addresses these important gaps in clinical practice.

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of "good", "borderline", or "poor" quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance "good" quality photographs (AUC = 0.93 (95% CI, 0.91-0.95), accuracy = 91.4% (95% CI, 90.0-92.9%), sensitivity = 93.8% (95% CI, 92.5-95.2%), specificity = 75.9% (95% CI, 69.7-82.1%) and "poor" quality photographs (AUC = 1.00 (95% CI, 0.99-1.00), accuracy = 99.1% (95% CI, 98.6-99.6%), sensitivity = 81.5% (95% CI, 70.6-93.8%), specificity = 99.7% (95% CI, 99.6-100.0%). "Borderline" quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88-0.93), accuracy = 90.6% (95% CI, 89.1-92.2%), sensitivity = 65.4% (95% CI, 56.6-72.9%), specificity = 93.4% (95% CI, 92.1-94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1-92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.

Research on Assistant Diagnosis of Fundus Optic Neuropathy Based on Deep Learning

PURPOSE

The purpose of this study was to use the neural network to distinguish optic edema (ODE), and optic atrophy from normal fundus images and try to use visualization to explain the artificial intelligence methods.

METHODS

Three hundred and sixty-seven images of ODE, 206 images of optic atrophy, and 231 images of normal fundus were used, which were provided by two hospitals. A set of image preprocessing and data enhancement methods were created and a variety of different neural network models, such as VGG16, VGG19, Inception V3, and 50-layer Deep Residual Learning (ResNet50) were used. The accuracy, recall, F1-score, and ROC curve under different networks were analyzed to evaluate the performance of models. Besides, CAM (class activation mapping) was utilized to find the focus of neural network and visualization of neural network with feature fusion.

RESULTS

Our image preprocessing and data enhancement method significantly improved the accuracy of model performance by about 10%. Among the networks, VGG16 had the best effect, as the accuracy of ODE, optic atrophy and normal fundus were 98, 90, and 95%, respectively. The macro-average and micro-average of VGG16 both reached 0.98. From CAM we can clearly find out that the focus area of the network is near the optic cup. From feature fusion images, we can find out the difference between the three types fundus images.

CONCLUSION

Through image preprocessing, data enhancement, and neural network training, we applied artificial intelligence to identify ophthalmic diseases, acquired the focus area through CAM, and identified the difference between the three ophthalmic diseases through neural network middle layers visualization. With the help of assistant diagnosis, ophthalmologists can evaluate cases more precisely and more clearly.

Terrestrial health applications of visual assessment technology and machine learning in spaceflight associated neuro-ocular syndrome

The neuro-ocular effects of long-duration spaceflight have been termed Spaceflight Associated Neuro-Ocular Syndrome (SANS) and are a potential challenge for future, human space exploration. The underlying pathogenesis of SANS remains ill-defined, but several emerging translational applications of terrestrial head-mounted, visual assessment technology and machine learning frameworks are being studied for potential use in SANS. To develop such technology requires close consideration of the spaceflight environment which is limited in medical resources and imaging modalities. This austere environment necessitates the utilization of low mass, low footprint technology to build a visual assessment system that is comprehensive, accessible, and efficient. In this paper, we discuss the unique considerations for developing this technology for SANS and translational applications on Earth. Several key limitations observed in the austere spaceflight environment share similarities to barriers to care for underserved areas on Earth. We discuss common terrestrial ophthalmic diseases and how machine learning and visual assessment technology for SANS can help increase screening for early intervention. The foundational developments with this novel system may help protect the visual health of both astronauts and individuals on Earth.

Use of machine learning to achieve keratoconus detection skills of a corneal expert

PURPOSE

To construct an automatic machine-learning derived algorithm discriminating between normal corneas and suspect irregular or keratoconic corneas.

METHODS

A total of 8526 corneal tomography images of 4904 eyes obtained between November 2010 and July 2017 using a combined Scheimpflug/Placido tomographer were retrospectively evaluated. Each image was evaluated for acquisition quality and was labeled as normal, suspect irregular or keratoconic by a cornea specialist. Two algorithms were built. The first was based on 94 instrument-derived output parameters, and the second integrated keratoconus prediction indices of the device with the 94 instrument-derived output parameters. Both models were compared with the tomographer's keratoconus detection algorithms. Out of the 8526 images evaluated, 7104 images of 3787 eyes had sufficient acquisition quality. Of those, 5904 examinations were randomly chosen for construction of the models using the random forest algorithm. The models were then validated using the remaining 1200 examinations.

RESULTS

Both RF algorithms had a larger AUC compared with any of the tomographer's KC detection algorithms (p < 10^-9). The first constructed model had 90.2% accuracy, sensitivity of 94.2%, and specificity of 89.6% (Youden 0.838). Calculated AUC was 0.964. The second model had 91.5% accuracy, sensitivity of 94.7%, and specificity of 89.8% (Youden 0.846). Calculated AUC was 0.969.

CONCLUSION

Using the RF machine-learning algorithm, accuracy of discrimination between normal, suspect irregular and keratoconic corneas approximates that of an experienced corneal expert. Applying machine learning to corneal tomography can facilitate keratoconus screening in large populations as well as off-site screening of refractive surgery candidates.

Artificial Intelligence Meets Neuro-Ophthalmology

ABSTRACT

Recent advances in artificial intelligence have provided ophthalmologists with fast, accurate, and automated means for diagnosing and treating ocular conditions, paving the way to a modern and scalable eye care system. Compared to other ophthalmic disciplines, neuro-ophthalmology has, until recently, not benefitted from significant advances in the area of artificial intelligence. In this narrative review, we summarize and discuss recent advancements utilizing artificial intelligence for the detection of structural and functional optic nerve head abnormalities, and ocular movement disorders in neuro-ophthalmology.

The use of deep learning technology for the detection of optic neuropathy

The emergence of computer graphics processing units (GPUs), improvements in mathematical models, and the availability of big data, has allowed artificial intelligence (AI) to use machine learning and deep learning (DL) technology to achieve robust performance in various fields of medicine. The DL system provides improved capabilities, especially in image recognition and image processing. Recent progress in the sorting of AI data sets has stimulated great interest in the development of DL algorithms. Compared with subjective evaluation and other traditional methods, DL algorithms can identify diseases faster and more accurately in diagnostic tests. Medical imaging is of great significance in the clinical diagnosis and individualized treatment of ophthalmic diseases. Based on the morphological data sets of millions of data points, various image-related diagnostic techniques can now impart high-resolution information on anatomical and functional changes, thereby providing unprecedented insights in ophthalmic clinical practice. As ophthalmology relies heavily on imaging examinations, it is one of the first medical fields to apply DL algorithms in clinical practice. Such algorithms can assist in the analysis of large amounts of data acquired from the examination of auxiliary images. In recent years, rapid advancements in imaging technology have facilitated the application of DL in the automatic identification and classification of pathologies that are characteristic of ophthalmic diseases, thereby providing high quality diagnostic information. This paper reviews the origins, development, and application of DL technology. The technical and clinical problems associated with building DL systems to meet clinical needs and the potential challenges of clinical application are discussed, especially in relation to the field of optic nerve diseases.

Virtual Reality and Augmented Reality- Emerging Screening and Diagnostic Techniques in Ophthalmology: a Systematic Review

In healthcare, virtual reality (VR) and augmented reality (AR) have been applied extensively for many purposes. Similar to other technologies such as telemedicine and artificial intelligence, VR and AR may improve clinical diagnosis and screening services in ophthalmology by alleviating current problems, including workforce shortage, diagnostic error, and underdiagnosis. In the past decade a number of studies and products have used VR and AR concepts to build clinical tests for ophthalmology, but comprehensive reviews on these studies are limited. Therefore, we conducted a systematic review on the use of VR and AR as a diagnostic and screening tool in ophthalmology. We identified 26 studies that implemented a variety of VR and AR tests on different conditions, including VR cover tests for binocular vision disorder, VR perimetry for glaucoma, and AR slit lamp biomicroscopy for retinal diseases. In general, while VR and AR tools can become standardized, automated, and cost-effective tests with good user experience, several weaknesses, including unsatisfactory accuracy, weak validation, and hardware limitations, have prevented these VR and AR tools from having wider clinical application. Also, a comparison between VR and AR is made to explain why studies have predominantly used VR rather than AR.

Serafini R, Lakhtakia S, Valliani AA, Warburton AJ, Patel A, Zhou D, Sklar B, Chelnis J, Elahi E. Portable hardware & software technologies for addressing ophthalmic health disparities: A systematic review

Vision impairment continues to be a major global problem, as the WHO estimates 2.2 billion people struggling with vision loss or blindness. One billion of these cases, however, can be prevented by expanding diagnostic capabilities. Direct global healthcare costs associated with these conditions totaled $255 billion in 2010, with a rapid upward projection to $294 billion in 2020. Accordingly, WHO proposed 2030 targets to enhance integration and patient-centered vision care by expanding refractive error and cataract worldwide coverage. Due to the limitations in cost and portability of adapted vision screening models, there is a clear need for new, more accessible vision testing tools in vision care. This comparative, systematic review highlights the need for new ophthalmic equipment and approaches while looking at existing and emerging technologies that could expand the capacity for disease identification and access to diagnostic tools. Specifically, the review focuses on portable hardware- and software-centered strategies that can be deployed in remote locations for detection of ophthalmic conditions and refractive error. Advancements in portable hardware, automated software screening tools, and big data-centric analytics, including machine learning, may provide an avenue for improving ophthalmic healthcare.

Papilledema: A review of etiology, pathophysiology, diagnosis, and management

Papilledema is optic nerve head edema secondary to raised intracranial pressure (ICP). It is distinct from other causes of optic disk edema in that visual function is usually normal in the acute phase. Papilledema is caused by transmission of elevated ICP to the subarachnoid space surrounding the optic nerve that hinders axoplasmic transport within ganglion cell axons. There is ongoing controversy as to whether axoplasmic flow stasis is produced by physical compression of axons or microvascular ischemia. The most common cause of papilledema, especially in patients under the age of 50, is idiopathic intracranial hypertension (IIH); however, conditions that decrease cerebrospinal fluid (CSF) outflow by either causing CSF derangements or mechanically blocking CSF outflow channels, and rarely conditions that increase CSF production, can be the culprit. When papilledema is suspected clinically, blood pressure should be measured, and pseudopapilledema should be ruled out. Magnetic resonance imaging of the brain and orbits with venography sequences is the preferred neuroimaging modality that should be performed next to look for indirect imaging signs of increased ICP and to rule out nonidiopathic causes. Lumbar puncture with measurement of opening pressure and evaluation of CSF composition should then be performed. In patients not in a typical demographic group for IIH, further investigations should be conducted to assess for underlying causes of increased ICP. Magnetic resonance imaging of the neck and spine, magnetic resonance angiography of the brain, computed tomography of the chest, complete blood count, and creatinine testing should be able to identify most secondary causes of intracranial hypertension. Treatment for patients with papilledema should be targeted toward the underlying etiology. Most patients with IIH respond to weight loss and oral acetazolamide. For patients with decreased central acuity and constricted visual fields at presentation, as well as patients who do not respond to treatment with acetazolamide, surgical treatments should be considered, with ventriculoperitoneal shunting being the typical procedure of choice.

Detection of Optic Disc Abnormalities in Color Fundus Photographs Using Deep Learning

BACKGROUND

To date, deep learning-based detection of optic disc abnormalities in color fundus photographs has mostly been limited to the field of glaucoma. However, many life-threatening systemic and neurological conditions can manifest as optic disc abnormalities. In this study, we aimed to extend the application of deep learning (DL) in optic disc analyses to detect a spectrum of nonglaucomatous optic neuropathies.

METHODS

Using transfer learning, we trained a ResNet-152 deep convolutional neural network (DCNN) to distinguish between normal and abnormal optic discs in color fundus photographs (CFPs). Our training data set included 944 deidentified CFPs (abnormal 364; normal 580). Our testing data set included 151 deidentified CFPs (abnormal 71; normal 80). Both the training and testing data sets contained a wide range of optic disc abnormalities, including but not limited to ischemic optic neuropathy, atrophy, compressive optic neuropathy, hereditary optic neuropathy, hypoplasia, papilledema, and toxic optic neuropathy. The standard measures of performance (sensitivity, specificity, and area under the curve of the receiver operating characteristic curve (AUC-ROC)) were used for evaluation.

RESULTS

During the 10-fold cross-validation test, our DCNN for distinguishing between normal and abnormal optic discs achieved the following mean performance: AUC-ROC 0.99 (95 CI: 0.98-0.99), sensitivity 94% (95 CI: 91%-97%), and specificity 96% (95 CI: 93%-99%). When evaluated against the external testing data set, our model achieved the following mean performance: AUC-ROC 0.87, sensitivity 90%, and specificity 69%.

CONCLUSION

In summary, we have developed a deep learning algorithm that is capable of detecting a spectrum of optic disc abnormalities in color fundus photographs, with a focus on neuro-ophthalmological etiologies. As the next step, we plan to validate our algorithm prospectively as a focused screening tool in the emergency department, which if successful could be beneficial because current practice pattern and training predict a shortage of neuro-ophthalmologists and ophthalmologists in general in the near future.

Deep Learning for Retinal Image Quality Assessment of Optic Nerve Head Disorders

ABSTRACT

Deep learning (DL)-based retinal image quality assessment (RIQA) algorithms have been gaining popularity, as a solution to reduce the frequency of diagnostically unusable images. Most existing RIQA tools target retinal conditions, with a dearth of studies looking into RIQA models for optic nerve head (ONH) disorders. The recent success of DL systems in detecting ONH abnormalities on color fundus images prompts the development of tailored RIQA algorithms for these specific conditions. In this review, we discuss recent progress in DL-based RIQA models in general and the need for RIQA models tailored for ONH disorders. Finally, we propose suggestions for such models in the future.

[Diagnostics of diseases of the optic nerve head in times of artificial intelligence and big data]

Hintergrund

Der Einsatz von künstlicher Intelligenz (KI) ist unter anderem in der automatischen Bildsegmentierung, -analyse und Klassifikation interessant und bereits für verschiedene Bereiche der Augenheilkunde beschrieben.

Fragestellung

Diese Arbeit soll einen Überblick über aktuelle Ansätze und Fortschritte bei der Anwendung von Big Data und KI bei verschiedenen Erkrankungen des Sehnervenkopfes geben.

Material und Methode

Es wurde eine PubMed-Recherche durchgeführt. Gesucht wurde nach Studien, die klinische Fragestellungen mithilfe von Big-Data-Ansätzen beantworteten oder klassische Methoden des maschinellen Lernens bei der Analyse von multimodaler Bildgebung des Sehnervenkopfes verwendeten.

Ergebnisse

Big Data kann bei Volkskrankheiten wie dem Glaukom helfen, klinische Fragestellungen zu beantworten. KI findet sowohl bei der Segmentierung von multimodaler Bildgebung des Sehnervenkopfes als auch bei der Klassifikation von Erkrankungen wie dem Glaukom oder der Stauungspapille auf diesen Bilddaten Anwendung.

Schlussfolgerung

Mithilfe von Big Data und KI können Zusammenhänge besser erkannt und die Diagnostik und Verlaufsbeurteilung von Erkrankungen des Sehnervenkopfes erleichtert oder automatisiert werden. Eine Voraussetzung für die klinische Anwendung ist in Europa die CE-Kennzeichnung als ein Medizinprodukt und in den USA die Zulassung durch die Food and Drug Administration.

Artificial intelligence for detection of optic disc abnormalities

PURPOSE OF REVIEW

The aim of this review is to highlight novel artificial intelligence-based methods for the detection of optic disc abnormalities, with particular focus on neurology and neuro-ophthalmology.

RECENT FINDINGS

Methods for detection of optic disc abnormalities on retinal fundus images have evolved considerably over the last few years, from classical ophthalmoscopy to artificial intelligence-based identification methods being applied to retinal imaging with the aim of predicting sight and life-threatening complications of underlying brain or optic nerve conditions.

SUMMARY

Artificial intelligence and in particular newly developed deep-learning systems are playing an increasingly important role for the detection and classification of acquired neuro-ophthalmic optic disc abnormalities on ocular fundus images. The implementation of automatic deep-learning methods for detection of abnormal optic discs, coupled with innovative hardware solutions for fundus imaging, could revolutionize the practice of neurologists and other non-ophthalmic healthcare providers.

Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs

BACKGROUND

Nonophthalmologist physicians do not confidently perform direct ophthalmoscopy. The use of artificial intelligence to detect papilledema and other optic-disk abnormalities from fundus photographs has not been well studied.

METHODS

We trained, validated, and externally tested a deep-learning system to classify optic disks as being normal or having papilledema or other abnormalities from 15,846 retrospectively collected ocular fundus photographs that had been obtained with pharmacologic pupillary dilation and various digital cameras in persons from multiple ethnic populations. Of these photographs, 14,341 from 19 sites in 11 countries were used for training and validation, and 1505 photographs from 5 other sites were used for external testing. Performance at classifying the optic-disk appearance was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity, and specificity, as compared with a reference standard of clinical diagnoses by neuro-ophthalmologists.

RESULTS

The training and validation data sets from 6779 patients included 14,341 photographs: 9156 of normal disks, 2148 of disks with papilledema, and 3037 of disks with other abnormalities. The percentage classified as being normal ranged across sites from 9.8 to 100%; the percentage classified as having papilledema ranged across sites from zero to 59.5%. In the validation set, the system discriminated disks with papilledema from normal disks and disks with nonpapilledema abnormalities with an AUC of 0.99 (95% confidence interval [CI], 0.98 to 0.99) and normal from abnormal disks with an AUC of 0.99 (95% CI, 0.99 to 0.99). In the external-testing data set of 1505 photographs, the system had an AUC for the detection of papilledema of 0.96 (95% CI, 0.95 to 0.97), a sensitivity of 96.4% (95% CI, 93.9 to 98.3), and a specificity of 84.7% (95% CI, 82.3 to 87.1).

CONCLUSIONS

A deep-learning system using fundus photographs with pharmacologically dilated pupils differentiated among optic disks with papilledema, normal disks, and disks with nonpapilledema abnormalities. (Funded by the Singapore National Medical Research Council and the SingHealth Duke-NUS Ophthalmology and Visual Sciences Academic Clinical Program.).

Classification of optical coherence tomography images using a capsule network

Background

Classification of optical coherence tomography (OCT) images can be achieved with high accuracy using classical convolution neural networks (CNN), a commonly used deep learning network for computer-aided diagnosis. Classical CNN has often been criticized for suppressing positional relations in a pooling layer. Therefore, because capsule networks can learn positional information from images, we attempted application of a capsule network to OCT images to overcome that shortcoming. This study is our attempt to improve classification accuracy by replacing CNN with a capsule network.

Methods

From an OCT dataset, we produced a training dataset of 83,484 images and a test dataset of 1000 images. For training, the dataset comprises 37,205 images with choroidal neovascularization (CNV), 11,348 with diabetic macular edema (DME), 8616 with drusen, and 26,315 normal images. The test dataset has 250 images from each category. The proposed model was constructed based on a capsule network for improving classification accuracy. It was trained using the training dataset. Subsequently, the test dataset was used to evaluate the trained model.

Results

Classification of OCT images using our method achieved accuracy of 99.6%, which is 3.2 percentage points higher than that of other methods described in the literature.

Conclusion

The proposed method achieved classification accuracy results equivalent to those reported for other methods for CNV, DME, drusen, and normal images.