Swept source optical coherence tomography to early detect multiple sclerosis disease. The use of machine learning techniques

Discrimination of multiple sclerosis using scanning laser ophthalmoscopy images with autoencoder-based feature extraction

OBJECTIVE

Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.

METHODS

We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).

RESULTS

The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).

CONCLUSIONS

We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice.

SLO-Net: Enhancing Multiple Sclerosis Diagnosis Beyond Optical Coherence Tomography Using Infrared Reflectance Scanning Laser Ophthalmoscopy Images

Purpose

Several machine learning studies have used optical coherence tomography (OCT) for multiple sclerosis (MS) classification with promising outcomes. Infrared reflectance scanning laser ophthalmoscopy (IR-SLO) captures high-resolution fundus images, commonly combined with OCT for fixed B-scan positions. However, no machine learning research has utilized IR-SLO images for automated MS diagnosis.

Methods

This study utilized a dataset comprised of IR-SLO images and OCT data from Isfahan, Iran, encompassing 32 MS and 70 healthy individuals. A number of convolutional neural networks (CNNs)-namely, VGG-16, VGG-19, ResNet-50, ResNet-101, and a custom architecture-were trained with both IR-SLO images and OCT thickness maps as two separate input datasets. The highest performing models for each modality were then integrated to create a bimodal model that receives the combination of OCT thickness maps and IR-SLO images. Subject-wise data splitting was employed to prevent data leakage among training, validation, and testing sets.

Results

Overall, images of the 102 patients from the internal dataset were divided into test, validation, and training subsets. Subsequently, we employed a bootstrapping approach on the training data through iterative sampling with replacement. The performance of the proposed bimodal model was evaluated on the internal test dataset, demonstrating an accuracy of 92.40% ± 4.1% (95% confidence interval [CI], 83.61-98.08), sensitivity of 95.43% ± 5.75% (95% CI, 83.71-100.0), specificity of 92.82% ± 3.72% (95% CI, 81.15-96.77), area under the receiver operating characteristic (AUROC) curve of 96.99% ± 2.99% (95% CI, 86.11-99.78), and area under the precision-recall curve (AUPRC) of 97.27% ± 2.94% (95% CI, 86.83-99.83). Furthermore, to assess the model generalization ability, we examined its performance on an external test dataset following the same bootstrap methodology, achieving promising results, with accuracy of 85.43% ± 0.08% (95% CI, 71.43-100.0), sensitivity of 97.33% ± 0.06% (95% CI, 83.33-100.0), specificity of 84.6% ± 0.10% (95% CI, 71.43-100.0), AUROC curve of 99.67% ± 0.02% (95% CI, 95.63-100.0), and AUPRC of 99.65% ± 0.02% (95% CI, 94.90-100.0).

Conclusions

Incorporating both modalities improves the performance of automated diagnosis of MS, showcasing the potential of utilizing IR-SLO as a complementary tool alongside OCT.

Translational Relevance

Should the results of our proposed bimodal model be validated in future work with larger and more diverse datasets, diagnosis of MS based on both OCT and IR-SLO can be reliably integrated into routine clinical practice.

Homonymous Hemiatrophy of Macular Ganglion Cell Layer as a Marker of Retrograde Neurodegeneration in Multiple Sclerosis-A Narrative Review

Retrograde axonal neurodegeneration along the visual pathway-either direct or trans-synaptic-has already been demonstrated in multiple sclerosis (MS), as well as in compressive, vascular, or posttraumatic lesions of the visual pathway. Optical coherence tomography (OCT) can noninvasively track macular and optic nerve changes occurring as a result of this phenomenon. Our paper aimed to review the existing literature regarding hemimacular atrophic changes in the ganglion cell layer identified using OCT examination in MS patients without prior history of optic neuritis. Homonymous hemimacular atrophy has been described in post-chiasmal MS lesions, even in patients with normal visual field results. Temporal and nasal macular OCT evaluation should be performed separately in all MS patients, in addition to an optic nerve OCT evaluation and a visual field exam.

Diagnosis of multiple sclerosis using optical coherence tomography supported by explainable artificial intelligence

BACKGROUND/OBJECTIVES

Study of retinal structure based on optical coherence tomography (OCT) data can facilitate early diagnosis of relapsing-remitting multiple sclerosis (RRMS). Although artificial intelligence can provide highly reliable diagnoses, the results obtained must be explainable.

SUBJECTS/METHODS

The study included 79 recently diagnosed RRMS patients and 69 age matched healthy control subjects. Thickness (Avg) and inter-eye difference (Diff) features are obtained in 4 retinal layers using the posterior pole protocol. Each layer is divided into six analysis zones. The Support Vector Machine plus Recursive Feature Elimination with Leave-One-Out Cross Validation (SVM-RFE-LOOCV) approach is used to find the subset of features that reduces dimensionality and optimises the performance of the classifier.

RESULTS

SVM-RFE-LOOCV was used to identify OCT features with greatest capacity for early diagnosis, determining the area of the papillomacular bundle to be the most influential. A correlation was observed between loss of layer thickness and increase in functional disability. There was also greater functional deterioration in patients with greater asymmetry between left and right eyes. The classifier based on the top-ranked features obtained sensitivity = 0.86 and specificity = 0.90.

CONCLUSIONS

There was consistency between the features identified as relevant by the SVM-RFE-LOOCV approach and the retinotopic distribution of the retinal nerve fibres and the optic nerve head. This simple method contributes to implementation of an assisted diagnosis system and its accuracy exceeds that achieved with magnetic resonance imaging of the central nervous system, the current gold standard. This paper provides novel insights into RRMS affectation of the neuroretina.

Artificial Intelligence for Multiple Sclerosis Management Using Retinal Images: Pearl, Peaks, and Pitfalls

Multiple sclerosis (MS) is a complex autoimmune disease characterized by inflammatory processes, demyelination, neurodegeneration, and axonal damage within the central nervous system (CNS). Retinal imaging, particularly Optical coherence tomography (OCT), has emerged as a crucial tool for investigating MS-related retinal injury. The integration of artificial intelligence(AI) has shown promise in enhancing OCT analysis for MS. Researchers are actively utilizing AI algorithms to accurately detect and classify MS-related abnormalities, leading to improved efficiency in diagnosis, monitoring, and personalized treatment planning. The prognostic value of AI in predicting MS disease progression has garnered substantial attention. Machine learning (ML) and deep learning (DL) algorithms can analyze longitudinal OCT data to forecast the course of the disease, providing critical information for personalized treatment planning and improved patient outcomes. Early detection of high-risk patients allows for targeted interventions to mitigate disability progression effectively. As such, AI-driven approaches yielded remarkable abilities in classifying distinct MS subtypes based on retinal features, aiding in disease characterization and guiding tailored therapeutic strategies. Additionally, these algorithms have enhanced the accuracy and efficiency of OCT image segmentation, streamlined diagnostic processes, and reduced human error. This study reviews the current research studies on the integration of AI,including ML and DL algorithms, with OCT in the context of MS. It examines the advancements, challenges, potential prospects, and ethical concerns of AI-powered techniques in enhancing MS diagnosis, monitoring disease progression, revolutionizing patient care, the development of patient screening tools, and supported clinical decision-making based on OCT images.

The macular retinal ganglion cell layer as a biomarker for diagnosis and prognosis in multiple sclerosis: A deep learning approach

PURPOSE

The macular ganglion cell layer (mGCL) is a strong potential biomarker of axonal degeneration in multiple sclerosis (MS). For this reason, this study aims to develop a computer-aided method to facilitate diagnosis and prognosis in MS.

METHODS

This paper combines a cross-sectional study of 72 MS patients and 30 healthy control subjects for diagnosis and a 10-year longitudinal study of the same MS patients for the prediction of disability progression, during which the mGCL was measured using optical coherence tomography (OCT). Deep neural networks were used as an automatic classifier.

RESULTS

For MS diagnosis, greatest accuracy (90.3%) was achieved using 17 features as inputs. The neural network architecture comprised the input layer, two hidden layers and the output layer with softmax activation. For the prediction of disability progression 8 years later, accuracy of 81.9% was achieved with a neural network comprising two hidden layers and 400 epochs.

CONCLUSION

We present evidence that by applying deep learning techniques to clinical and mGCL thickness data it is possible to identify MS and predict the course of the disease. This approach potentially constitutes a non-invasive, low-cost, easy-to-implement and effective method.

The retina-brain axis and diabetic retinopathy

Diabetic retinopathy (DR) is a major contributor to permanent vision loss and blindness. Changes in retinal neurons, glia, and microvasculature have been the focus of intensive study in the quest to better understand DR. However, the impact of diabetes on the rest of the visual system has received less attention. There are reports of associations of changes in the visual system with preclinical and clinical manifestations of diabetes. Simultaneous investigation of the retina and the brain may shed light on the mechanisms underlying neurodegeneration in diabetics. Additionally, investigating the links between DR and other neurodegenerative disorders of the brain including Alzheimer's and Parkinson's disease may reveal shared mechanisms for neurodegeneration and potential therapy options.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Explainable artificial intelligence toward usable and trustworthy computer-aided diagnosis of multiple sclerosis from Optical Coherence Tomography

BACKGROUND

Several studies indicate that the anterior visual pathway provides information about the dynamics of axonal degeneration in Multiple Sclerosis (MS). Current research in the field is focused on the quest for the most discriminative features among patients and controls and the development of machine learning models that yield computer-aided solutions widely usable in clinical practice. However, most studies are conducted with small samples and the models are used as black boxes. Clinicians should not trust machine learning decisions unless they come with comprehensive and easily understandable explanations.

MATERIALS AND METHODS

A total of 216 eyes from 111 healthy controls and 100 eyes from 59 patients with relapsing-remitting MS were enrolled. The feature set was obtained from the thickness of the ganglion cell layer (GCL) and the retinal nerve fiber layer (RNFL). Measurements were acquired by the novel Posterior Pole protocol from Spectralis Optical Coherence Tomography (OCT) device. We compared two black-box methods (gradient boosting and random forests) with a glass-box method (explainable boosting machine). Explainability was studied using SHAP for the black-box methods and the scores of the glass-box method.

RESULTS

The best-performing models were obtained for the GCL layer. Explainability pointed out to the temporal location of the GCL layer that is usually broken or thinning in MS and the relationship between low thickness values and high probability of MS, which is coherent with clinical knowledge.

CONCLUSIONS

The insights on how to use explainability shown in this work represent a first important step toward a trustworthy computer-aided solution for the diagnosis of MS with OCT.

Evaluation of multiple sclerosis severity using a new OCT tool

PURPOSE

To assess the ability of a new posterior pole protocol to detect areas with significant differences in retinal nerve fiber layer (RNFL) and ganglion cell layer (GCL) thickness in patients with multiple sclerosis versus healthy control subjects; in addition, to assess the correlation between RNFL and GCL thickness, disease duration, and the Expanded Disability Status Scale (EDSS).

METHODS

We analyzed 66 eyes of healthy control subjects and 100 eyes of remitting-relapsing multiple sclerosis (RR-MS) patients. Double analysis based on first clinical symptom onset (CSO) and conversion to clinically definite MS (CDMS) was performed. The RR-MS group was divided into subgroups by CSO and CDMS year: CSO-1 (≤ 5 years) and CSO-2 (≥ 6 years), and CDMS-1 (≤ 5 years) and CDMS-2 (≥ 6 years).

RESULTS

Significant differences in RNFL and GCL thickness were found between the RR-MS group and the healthy controls and between the CSO and CDMS subgroups and in both layers. Moderate to strong correlations were found between RNFL and GCL thickness and CSO and CDMS. Furthermore, we observed a strong correlation with EDSS 1 year after the OCT examination.

CONCLUSIONS

The posterior pole protocol is a useful tool for assessing MS and can reveal differences even in early stages of the disease. RNFL thickness shows a strong correlation with disability status, while GCL thickness correlates better with disease duration.

Diagnosing Systemic Disorders with AI Algorithms Based on Ocular Images

The advent of artificial intelligence (AI), especially the state-of-the-art deep learning frameworks, has begun a silent revolution in all medical subfields, including ophthalmology. Due to their specific microvascular and neural structures, the eyes are anatomically associated with the rest of the body. Hence, ocular image-based AI technology may be a useful alternative or additional screening strategy for systemic diseases, especially where resources are scarce. This review summarizes the current applications of AI related to the prediction of systemic diseases from multimodal ocular images, including cardiovascular diseases, dementia, chronic kidney diseases, and anemia. Finally, we also discuss the current predicaments and future directions of these applications.

Comprehensible Machine-Learning-Based Models for the Pre-Emptive Diagnosis of Multiple Sclerosis Using Clinical Data: A Retrospective Study in the Eastern Province of Saudi Arabia

Multiple Sclerosis (MS) is characterized by chronic deterioration of the nervous system, mainly the brain and the spinal cord. An individual with MS develops the condition when the immune system begins attacking nerve fibers and the myelin sheathing that covers them, affecting the communication between the brain and the rest of the body and eventually causing permanent damage to the nerve. Patients with MS (pwMS) might experience different symptoms depending on which nerve was damaged and how much damage it has sustained. Currently, there is no cure for MS; however, there are clinical guidelines that help control the disease and its accompanying symptoms. Additionally, no specific laboratory biomarker can precisely identify the presence of MS, leaving specialists with a differential diagnosis that relies on ruling out other possible diseases with similar symptoms. Since the emergence of Machine Learning (ML) in the healthcare industry, it has become an effective tool for uncovering hidden patterns that aid in diagnosing several ailments. Several studies have been conducted to diagnose MS using ML and Deep Learning (DL) models trained using MRI images, achieving promising results. However, complex and expensive diagnostic tools are needed to collect and examine imaging data. Thus, the intention of this study is to implement a cost-effective, clinical data-driven model that is capable of diagnosing pwMS. The dataset was obtained from King Fahad Specialty Hospital (KFSH) in Dammam, Saudi Arabia. Several ML algorithms were compared, namely Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Extra Trees (ET). The results indicated that the ET model outpaced the rest with an accuracy of 94.74%, recall of 97.26%, and precision of 94.67%.

Diagnostic performance of artificial intelligence in multiple sclerosis: a systematic review and meta-analysis

BACKGROUND

The expansion of the availability of advanced imaging methods needs more time, expertise, and resources which is in contrast to the primary goal of the imaging techniques. To overcome most of these difficulties, artificial intelligence (AI) can be used. A number of studies used AI models for multiple sclerosis (MS) diagnosis and reported diverse results. Therefore, we aim to perform a comprehensive systematic review and meta-analysis study on the role of AI in the diagnosis of MS.

METHODS

We performed a systematic search using four databases including PubMed, Scopus, Web of Science, and IEEE. Studies that applied deep learning or AI to the diagnosis of MS based on any modalities were considered eligible in our study. The accuracy, sensitivity, specificity, precision, and area under curve (AUC) were pooled with a random-effects model and 95% confidence interval (CI).

RESULTS

After the screening, 41 articles with 5989 individuals met the inclusion criteria and were included in our qualitative and quantitative synthesis. Our analysis showed that the overall accuracy among studies was 94% (95%CI: 93%, 96%). The pooled sensitivity and specificity were 92% (95%CI: 90%, 95%) and 93% (95%CI: 90%, 96%), respectively. Furthermore, our analysis showed 92% precision in MS diagnosis for AI studies (95%CI: 88%, 97%). Also, the overall pooled AUC was 93% (95%CI: 89%, 96%).

CONCLUSION

Overall, AI models can further improve our diagnostic practice in MS patients. Our results indicate that the use of AI can aid the clinicians in accurate diagnosis of MS and improve current diagnostic approaches as most of the parameters including accuracy, sensitivity, specificity, precision, and AUC were considerably high, especially when using MRI data.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients' data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.

The Role of Optical Coherence Tomography Criteria and Machine Learning in Multiple Sclerosis and Optic Neuritis Diagnosis

BACKGROUND AND OBJECTIVES

Recent studies have suggested that intereye differences (IEDs) in peripapillary retinal nerve fiber layer (pRNFL) or ganglion cell + inner plexiform (GCIPL) thickness by spectral domain optical coherence tomography (SD-OCT) may identify people with a history of unilateral optic neuritis (ON). However, this requires further validation. Machine learning classification may be useful for validating thresholds for OCT IEDs and for examining added utility for visual function tests, such as low-contrast letter acuity (LCLA), in the diagnosis of people with multiple sclerosis (PwMS) and for unilateral ON history.

METHODS

Participants were from 11 sites within the International Multiple Sclerosis Visual System consortium. pRNFL and GCIPL thicknesses were measured using SD-OCT. A composite score combining OCT and visual measures was compared individual measurements to determine the best model to distinguish PwMS from controls. These methods were also used to distinguish those with a history of ON among PwMS. Receiver operating characteristic (ROC) curve analysis was performed on a training data set (2/3 of cohort) and then applied to a testing data set (1/3 of cohort). Support vector machine (SVM) analysis was used to assess whether machine learning models improved diagnostic capability of OCT.

RESULTS

Among 1,568 PwMS and 552 controls, variable selection models identified GCIPL IED, average GCIPL thickness (both eyes), and binocular 2.5% LCLA as most important for classifying PwMS vs controls. This composite score performed best, with area under the curve (AUC) = 0.89 (95% CI 0.85-0.93), sensitivity = 81%, and specificity = 80%. The composite score ROC curve performed better than any of the individual measures from the model (p < 0.0001). GCIPL IED remained the best single discriminator of unilateral ON history among PwMS (AUC = 0.77, 95% CI 0.71-0.83, sensitivity = 68%, specificity = 77%). SVM analysis performed comparably with standard logistic regression models.

DISCUSSION

A composite score combining visual structure and function improved the capacity of SD-OCT to distinguish PwMS from controls. GCIPL IED best distinguished those with a history of unilateral ON. SVM performed as well as standard statistical models for these classifications.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that SD-OCT accurately distinguishes multiple sclerosis from normal controls as compared with clinical criteria.

Multiple sclerosis diagnosis and phenotype identification by multivariate classification of in vivo frontal cortex metabolite profiles

Multiple sclerosis (MS) is a heterogeneous autoimmune disease for which diagnosis continues to rely on subjective clinical judgment over a battery of tests. Proton magnetic resonance spectroscopy (¹H MRS) enables the noninvasive in vivo detection of multiple small-molecule metabolites and is therefore in principle a promising means of gathering information sufficient for multiple sclerosis diagnosis and subtype classification. Here we show that supervised classification using ¹H-MRS-visible normal-appearing frontal cortex small-molecule metabolites alone can indeed differentiate individuals with progressive MS from control (held-out validation sensitivity 79% and specificity 68%), as well as between relapsing and progressive MS phenotypes (held-out validation sensitivity 84% and specificity 74%). Post hoc assessment demonstrated the disproportionate contributions of glutamate and glutamine to identifying MS status and phenotype, respectively. Our finding establishes ¹H MRS as a viable means of characterizing progressive multiple sclerosis disease status and paves the way for continued refinement of this method as an auxiliary or mainstay of multiple sclerosis diagnostics.

Role of artificial intelligence in MS clinical practice

•

For medical applications, machine learning (including deep learning) are the most commonly used artificial intelligence (AI) approaches.

•

It can improve multiple sclerosis (MS) diagnosis, prognostication and treatment monitoring.

•

Thanks to AI, MRI and cognitive phenotypes of MS patients were identified.

•

AI can shorten MRI protocols for MS, allowing the application of advanced techniques.

•

It can reduce the human effort for MRI analysis, especially for lesion segmentation.

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.

Artificial Intelligence in Predicting Systemic Parameters and Diseases From Ophthalmic Imaging

Artificial Intelligence (AI) analytics has been used to predict, classify, and aid clinical management of multiple eye diseases. Its robust performances have prompted researchers to expand the use of AI into predicting systemic, non-ocular diseases and parameters based on ocular images. Herein, we discuss the reasons why the eye is well-suited for systemic applications, and review the applications of deep learning on ophthalmic images in the prediction of demographic parameters, body composition factors, and diseases of the cardiovascular, hematological, neurodegenerative, metabolic, renal, and hepatobiliary systems. Three main imaging modalities are included—retinal fundus photographs, optical coherence tomographs and external ophthalmic images. We examine the range of systemic factors studied from ophthalmic imaging in current literature and discuss areas of future research, while acknowledging current limitations of AI systems based on ophthalmic images.

Comparison of Machine Learning Methods Using Spectralis OCT for Diagnosis and Disability Progression Prognosis in Multiple Sclerosis

Machine learning approaches in diagnosis and prognosis of multiple sclerosis (MS) were analysed using retinal nerve fiber layer (RNFL) thickness, measured by optical coherence tomography (OCT). A cross-sectional study (72 MS patients and 30 healthy controls) was used for diagnosis. These 72 MS patients were involved in a 10-year longitudinal follow-up study for prognostic purposes. Structural measurements of RNFL thickness were performed using different Spectralis OCT protocols: fast macular thickness protocol to measure macular RNFL, and fast RNFL thickness protocol and fast RNFL-N thickness protocol to measure peripapillary RNFL. Binary classifiers such as multiple linear regression (MLR), support vector machines (SVM), decision tree (DT), k-nearest neighbours (k-NN), Naïve Bayes (NB), ensemble classifier (EC) and long short-term memory (LSTM) recurrent neural network were tested. For MS diagnosis, the best acquisition protocol was fast macular thickness protocol using k-NN (accuracy: 95.8%; sensitivity: 94.4%; specificity: 97.2%; precision: 97.1%; AUC: 0.958). For MS prognosis, our model with a 3-year follow up to predict disability progression 8 years later was the best predictive model. DT performed best for fast macular thickness protocol (accuracy: 91.3%; sensitivity: 90.0%; specificity: 92.5%; precision: 92.3%; AUC: 0.913) and SVM for fast RNFL-N thickness protocol (accuracy: 91.3%; sensitivity: 87.5%; specificity: 95.0%; precision: 94.6%; AUC: 0.913). This work concludes that measurements of RNFL thickness obtained with Spectralis OCT have a good ability to diagnose MS and to predict disability progression in MS patients. This machine learning approach would help clinicians to have valuable information.

Detailed Evaluation of Macular Ganglion Cell Complex in Patients with Multiple Sclerosis

Introduction:

Retinal nerve fiber layer thickness has been used for monitoring of disease activity in patients with multiple sclerosis (MS). Macular ganglion cell complex (GCC) layer of retina also can be measured by OCT and has been suggested as a potential biomarker in MS. In this study we investigated the macular GCC and its role as a potential biomarker in patients with Multiple Sclerosis (MS).

Methods:

A prospective cohort-study, subjects consisted of Relapsing-Remitting MS patients (n=62) and healthy controls (n=60). Eyes of MS patients were divided into two subgroups according to the history of the optic neuritis (ON). Standard peripapillary-RNFL and macular scan protocol, and retinal auto-segmentation of spectral-domain OCT were performed. Macular RNFL (mRNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL), and GCC (the sum of these former three layers) were recorded. The macula was divided into nine sectors using the ETDRS grid (4×9=36 variables).

Results:

In total, 50 eyes of 36 patients had previous ON attacks. 35/36 GCC parameters were thinner in MS patients and subgroups compared to the control group (p<0.05). When the eyes with and without a history of optic neuritis were compared, 25 of 36 parameters were thinner in those with ON. There were strong correlations between visual acuity-GCC parameters and EDSS scores in patients with a history of optic neuritis. However, no such relationship was found in those without an ON story.

Conclusion:

Ganglion cell complex gets thinner in patients with MS with a decreasing order of GCL, IPL, and mRNFL. The examination of GCC in detail could be a beneficial biomarker for MS.

Analysis of Retinal Layers in Fibromyalgia Patients with Premium Protocol in Optical Tomography Coherence and Quality of Life

PURPOSE

To evaluate the inner retinal layers in fibromyalgia (FM) patients compared to control subjects using posterior pole protocol (PPole) analysis in optical coherence tomography (OCT) and to correlate structural retinal changes with subjective quality of life.

METHODS

Seventy-four eyes of healthy subjects and 55 eyes of those with FM were analyzed. All subjects underwent retinal evaluation using the PPole protocol for Spectralis OCT (Heidelberg Engineering) to obtain measurements of the retinal nerve fiber layer (RNFL) and the ganglion cell layer (GCL) in the macular area. The EuroQol (EQ-5D) questionnaire and Fibromyalgia Impact Questionnaire (FIQ) were performed to analyze health-related quality of life. Additionally, the FM group was divided into three groups depending on the disease phenotype (atypical, depressive and biological).

RESULTS

: Patients with FM presented with a reduction of the RNFL thickness compared to controls in 17/64 cells of the PPole area, and a reduction of the GCL thickness in 47/64 cells. Depressive FM phenotype showed the greatest number of cells with significant reduction compared with the control group in both RNFL and GCL layers. A correlation between temporal-inferior cells of the GCL and the EuroQol 5D questionnaire results was observed.

CONCLUSIONS

Patients with FM present with a reduction of the inner retinal layers in the macular area. This degeneration correlates with disease severity/reduced quality of life in these patients. The PPole protocol for OCT is a non-invasive and fast tool that might help clinicians diagnose and monitor neurodegeneration in FM patients.

Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography

BACKGROUND

Multiple sclerosis (MS) is a neurodegenerative disease that affects the central nervous system, especially the brain, spinal cord, and optic nerve. Diagnosis of this disease is a very complex process and generally requires a lot of time. In addition, treatments are applied without any information on the disability course in each MS patient. For these two reasons, the objective of this study was to improve the MS diagnosis and predict the long-term course of disability in MS patients based on clinical data and retinal nerve fiber layer (RNFL) thickness, measured by optical coherence tomography (OCT).

MATERIAL AND METHODS

A total of 104 healthy controls and 108 MS patients, 82 of whom had a 10-year follow-up, were enrolled. Classification algorithms such as multiple linear regression (MLR), support vector machines (SVM), decision tree (DT), k-nearest neighbours (k-NN), Naïve Bayes (NB), ensemble classifier (EC) and long short-term memory (LSTM) recurrent neural network were tested to develop two predictive models: MS diagnosis model and MS disability course prediction model.

RESULTS

For MS diagnosis, the best result was obtained using EC (accuracy: 87.7%; sensitivity: 87.0%; specificity: 88.5%; precision: 88.7%; AUC: 0.8775). In line with this good performance, the accuracy was 85.4% using k-NN and 84.4% using SVM. And, for long-term prediction of MS disability course, LSTM recurrent neural network was the most appropriate classifier (accuracy: 81.7%; sensitivity: 81.1%; specificity: 82.2%; precision: 78.9%; AUC: 0.8165). The use of MLR, SVM and k-NN also showed a good performance (AUC ≥ 0.8).

CONCLUSIONS

This study demonstrated that machine learning techniques, using clinical and OCT data, can help establish an early diagnosis and predict the course of MS. This advance could help clinicians select more specific treatments for each MS patient. Therefore, our findings underscore the potential of RNFL thickness as a reliable MS biomarker.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

Bruch's membrane opening-minimum rim width: An alternative OCT biomarker study for multiple sclerosis

PURPOSE

Bruch's membrane opening-minimum rim width (BMO-MRW) and RNFL measured using anatomic positioning system (APS-RNFL) are novel OCT methods and remained unexplored in MS patients.To investigate the novel parameters of spectral-domain OCT as an alternative biomarker in patients with multiple sclerosis (MS).

METHODS

Retrospective cohort study; participants consisted of relapsing-remitting MS (RRMS) patients and healthy controls (HC). Eyes were classified according to the presence of MS and previous optic neuritis (ON). Measurements of standard peripapillary RNFL (S-RNFL), BMO-MRW, and APS-RNFL were performed.

RESULT

A total of 244 eyes of 122 participants (MS-patients: 63, HC: 59) were included in the study. Fifty-one eyes had a history of previous ON. In almost all measured parameters, neuroretinal rim thicknesses were observed the thinnest in eyes with ON history between all subgroups. S-RNFL and APS-RNFL techniques showed the difference in neuroretinal rim thickness in all three subjects (ON+, ON-, and HC). However, BMO-MRW, on the other hand, could not distinguish between ON(-) patients and HC. The relationship between OCT parameters and EDSS were observed only in eyes with an ON history in all three techniques. A meaningful model with 78% accuracy was obtained by using only the OCT parameters as risk factors. In the ROC analysis, no parameters were found to have acceptable high sensitivity and specificity. BMO-MRW was statistically weaker in every aspect than other RNFL techniques.

CONCLUSION

The novel APS-RNFL technique appears to be a bit more reliable alternative to S-RNFL technique to support therapeutic decision-making in MS. BMO-MRW has not been found as a successful alternative to S-RNFL.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Retinal applications of swept source optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA)

The advent of optical coherence tomography (OCT) revolutionized both clinical assessment and research of vitreoretinal conditions. Since then, extraordinary advances have been made in this imaging technology, including the relatively recent development of swept-source OCT (SS-OCT). SS-OCT enables a fast scan rate and utilizes a tunable swept laser, thus enabling the incorporation of longer wavelengths than conventional spectral-domain devices. These features enable imaging of larger areas with reduced motion artifact, and a better visualization of the choroidal vasculature, respectively. Building on the principles of OCT, swept-source OCT has also been applied to OCT angiography (SS-OCTA), thus enabling a non-invasive in depth-resolved imaging of the retinal and choroidal microvasculature. Despite their advantages, the widespread use of SS-OCT and SS-OCTA remains relatively limited. In this review, we summarize the technical details, advantages and limitations of SS-OCT and SS-OCTA, with a particular emphasis on their relevance for the study of retinal conditions. Additionally, we comprehensively review relevant studies performed to date to the study of retinal health and disease, and highlight current gaps in knowledge and opportunities to take advantage of swept source technology to improve our current understanding of many medical and surgical chorioretinal conditions. We anticipate that SS-OCT and SS-OCTA will continue to evolve rapidly, contributing to a paradigm shift to more widespread adoption of new imaging technology to clinical practice.

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.

Microperimetry and Optical Coherence Tomography Changes in Type-1 Diabetes Mellitus without Retinopathy

Background: We aimed to measure and correlate inner retinal layer (IRL) thickness and macular sensitivity by optical coherence tomography (OCT) and by microperimetry, respectively, in type 1 diabetes mellitus patients (DM1) without diabetic retinopathy (DR). Methods: Fifty-one DM1 patients and 81 age-matched healthy subjects underwent measurement of the axial length (AL), retinal thickness in the macular ETDRS areas by swept source (SS)-OCT and macular sensitivity by microperimeter. Results: The total retinal and IRL thicknesses were thicker in the DM1 group (p < 0.05) in practically all ETDRS areas, and they had a generalized decrease in sensitivity (p < 0.05) in 9 areas between both groups. There was a significant negative correlation between retinal sensitivity and age in all areas and in visual acuity (VA) in 5 out of the 9 areas for DM1 patients. Only a mild negative correlation was observed between retinal sensitivity in the 5° nasal inner (5NI) area and in IRL thickness in the temporal inner (TI) area (−0.309 with p = 0.029) in the DM1 group. Conclusion: Aging and disease evolution in DM1 patients without DR signs generate a decrease in retinal sensitivity. There was a direct relationship between retinal sensitivity and macular thickness in the DM1 group.

Angiography with optical coherence tomography as a biomarker in multiple sclerosis

PURPOSE

To investigate superficial retinal microvascular plexuses detected by optical coherence tomography angiography (OCT-A) in multiple sclerosis (MS) subjects and compare them with healthy controls.

METHODS

A total of 92 eyes from 92 patients with relapsing-remitting MS and 149 control eyes were included in this prospective observational study. OCT-A imaging was performed using Triton Swept-Source OCT (Topcon Corporation, Japan). The vessel density (VD) percentage in the superficial retinal plexus and optic disc area (6 x 6 mm grid) was measured and compared between groups.

RESULTS

MS patients showed a significant decrease VD in the superior (p = 0.005), nasal (p = 0.029) and inferior (p = 0.040) parafoveal retina compared with healthy subjects. Patients with disease durations of more than 5 years presented lower VD in the superior (p = 0.002), nasal (p = 0.017) and inferior (p = 0.022) parafoveal areas compared with healthy subjects. Patients with past optic neuritis episodes did not show retinal microvasculature alterations, but patients with an EDSS score of less than 3 showed a significant decrease in nasal (p = 0.024) and superior (p = 0.006) perifoveal VD when compared with healthy subjects.

CONCLUSIONS

MS produces a decrease in retinal vascularization density in the superficial plexus of the parafoveal retina. Alterations in retinal vascularization observed in MS patients are independent of the presence of optic nerve inflammation. OCT-A has the ability to detect subclinical vascular changes and is a potential biomarker for diagnosing the presence and progression of MS.

Early diagnosis of multiple sclerosis by OCT analysis using Cohen's d method and a neural network as classifier

BACKGROUND

The consequences of inflammation, demyelination, axonal degeneration and neuronal loss in the central nervous system, typical of the development of multiple sclerosis (MS), are manifested in thinning of the retina and optic nerve. The purpose of this work is to diagnose early-stage MS patients based on analysis of retinal layer thickness obtained by swept-source optical coherence tomography (SS-OCT).

METHOD

OCT (Triton® SS-OCT device -Topcon, Tokyo, Japan-) recordings were obtained from 48 control subjects and 48 recently diagnosed MS patients. The following thicknesses were measured on a 45 × 60 grid: retinal nerve fibre layer (RNFL), ganglion cell layer (GCL+), GCL++, retinal thickness and choroid. Using Cohen's d effect size, it was determined the regions and layers with greatest capacity to discriminate between control subjects and patients. Points exceeding the threshold set were used as inputs for an automatic classifier: support vector machine and feed-forward neural network.

RESULTS

In MS at clinical onset the layer with greatest discriminant capacity is GCL++ [AUC = 0.83] which exhibits a horseshoe-like macular topographic distribution. It is followed by retina, GCL+ and RNFL; choroidal thicknesses do not provide discriminatory capacity. Using a neural network as a classifier between controls and MS patients, obtains sensitivity of 0.98 and specificity of 0.98.

CONCLUSIONS

This work suggest that OCT may serve as an important complementary role to other clinical tests, particularly regarding neurodegeneration. It is possible to characterise structural alterations in retina and diagnose early-stage MS with high degree of accuracy using OCT and artificial neural networks.

Retinal thickness as a potential biomarker of neurodegeneration and a predictor of early cognitive impairment in patients with multiple sclerosis

OBJECTIVES

The purpose of this research is to predict the cognitive impairment and to determine its correlation with retinal thickness, mainly (RFNL and GCIPL) in cases of multiple sclerosis.

METHODS

60 multiple sclerosis patients and 30 age and sex-matched healthy controls were included in this study. Cognitive functions were evaluated in all study participants by the Montreal Cognitive Assessment (MoCA). OCT imaging was done to determine the thickness. The correlation between the cognitive domains of MoCA and the thickness of the retinal nerve fiber layers was analyzed by Spearman correlation. ROC curve was constructed to determine the cut-off points for retinal thickness, and a binary logistic regression was performed to determine the independent predictive capacity of established cut-off points.

RESULTS

Impaired cognition was found in 26 MS patients (43.3%). Cognitively impaired patients were significantly older (P < 0.05), had significantly longer disease duration (P < 0.05), had higher average EDSS scores (4.3 ± 1.22 vs 3.1 ± 1.45, P < 0.001), and occurred more in progressive types of MS (P < 0.001). A significant positive correlation was found between cognitive function and RNFL thickness and GCIPL (P < 0.001). The retinal thickness (RNFL and GCIPL) cut-off points established for the prediction of cognitive impairment in MS patients were 79 μm and 76 μm, respectively.

CONCLUSION

The clear correlation between cognitive impairment and atrophy of inner retinal layers (RNFL and GCIPL) proposes that OCT is valuable in evaluating the neurodegeneration and prediction of early cognitive impairment in MS.

ABBREVIATIONS

EDSS: Expanded Disability Status Scale; HCs: Healthy controls; GCIPL: Ganglion cell-inner plexiform layer; ILM: Internal limiting membrane; INL:  Inner nuclear layer; MoCA: Montreal Cognitive Assessment; MS: Multiple sclerosis; PPMS: Primary progressive multiple sclerosis; RNFL:  Retinal nerve fiber layer; RRMS: Relapsing-remitting multiple sclerosis; SD: Standard deviations; SPMS: Secondary progressive multiple sclerosis; SPSS: Statistical Package for the Social Sciences.

Optical coherence tomography findings in patients with alcohol use disorder and their relationship with clinical parameters

Purpose: In our study, we aimed to investigate the ganglion cell-inner plexiform layer thickness (GCIPL), retinal nerve fibre layer thickness (RNFL), mean macular volume (MMV), central macular thickness (CMT), mean macular thickness (MMT), and choroidal thickness (CT) values with optical coherence tomography (OCT) in patients who are diagnosed with alcohol use disorder (AUD).Materials and methods: The study included 43 patients who were diagnosed with AUD, and 43 healthy controls. Detailed biomicroscopic examinations of all the participants, visual acuity, intraocular pressure, anterior and posterior segment examinations, and then, OCT measurements were carried out.Results: Although the measured values for RNFL in the superior and temporal quadrant are within normal limits, they were slightly higher compared to those in the control group (p values 0.127 and 0.191 for superior quadrant and temporal quadrant, respectively). The CT measurements in all quadrants were higher than the control group; however, these measurements were not statistically significant (p > 0.05). When the relation between clinical features and OCT findings of the patients were examined, it was determined that the ages of the patients were statistically significantly and inversely correlated with the temporal CT and also the nasal and temporal quadrants of RNFL.Conclusions: Our study is the first study that examines the retinal GCIPL and CT with OCT in patients who are diagnosed with AUD. In our results, it was determined that there were no statistically significant differences between the participants in terms of OCT parameters. Further studies with larger sampling groups evaluating neurotransmission findings may provide wider results.

Computer-Aided Diagnosis of Multiple Sclerosis Using a Support Vector Machine and Optical Coherence Tomography Features

The purpose of this paper is to evaluate the feasibility of diagnosing multiple sclerosis (MS) using optical coherence tomography (OCT) data and a support vector machine (SVM) as an automatic classifier. Forty-eight MS patients without symptoms of optic neuritis and forty-eight healthy control subjects were selected. Swept-source optical coherence tomography (SS-OCT) was performed using a DRI (deep-range imaging) Triton OCT device (Topcon Corp., Tokyo, Japan). Mean values (right and left eye) for macular thickness (retinal and choroidal layers) and peripapillary area (retinal nerve fibre layer, retinal, ganglion cell layer—GCL, and choroidal layers) were compared between both groups. Based on the analysis of the area under the receiver operator characteristic curve (AUC), the 3 variables with the greatest discriminant capacity were selected to form the feature vector. A SVM was used as an automatic classifier, obtaining the confusion matrix using leave-one-out cross-validation. Classification performance was assessed with Matthew’s correlation coefficient (MCC) and the AUC_CLASSIFIER. The most discriminant variables were found to be the total GCL++ thickness (between inner limiting membrane to inner nuclear layer boundaries), evaluated in the peripapillary area and macular retina thickness in the nasal quadrant of the outer and inner rings. Using the SVM classifier, we obtained the following values: MCC = 0.81, sensitivity = 0.89, specificity = 0.92, accuracy = 0.91, and AUC_CLASSIFIER = 0.97. Our findings suggest that it is possible to classify control subjects and MS patients without previous optic neuritis by applying machine-learning techniques to study the structural neurodegeneration in the retina.