CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis

Deep Learning techniques to detect and analysis of multiple sclerosis through MRI: A systematic literature review

Deep learning (DL) techniques represent a rapidly advancing field within artificial intelligence, gaining significant prominence in the detection and analysis of various medical conditions through the analysis of medical data. This study presents a systematic literature review (SLR) focused on deep learning methods for the detection and analysis of multiple sclerosis (MS) using magnetic resonance imaging (MRI). The initial search identified 401 articles, which were rigorously screened, a selection of 82 highly relevant studies. These selected studies primarily concentrate on key areas such as multiple sclerosis, deep learning, convolutional neural networks (CNN), lesion segmentation, and classification, reflecting their alignment with the current state of the art. This review comprehensively examines diverse deep-learning approaches for MS detection and analysis, offering a valuable resource for researchers. Additionally, it presents key insights by summarizing these DL techniques for MS detection and analysis using MRI in a structured tabular format.

Emerging MRI biomarkers for the diagnosis of multiple sclerosis

The need to improve diagnostic precision in multiple sclerosis (MS) is widely recognized. In recent years, several novel magnetic resonance imaging (MRI) biomarkers have been proposed to enhance diagnostic specificity and reduce misdiagnosis. Some of these imaging biomarkers are deemed highly specific for MS and are likely ready to enter the MS diagnostic work-up, while others are still in their exploratory phase. In addition, new synthetic MRI contrasts and artificial intelligence-based diagnostic algorithms are being tested to reduce the time burden related to imaging data acquisition and analysis. In this review, we summarize the most recent advancement in the field, focusing on the adoption of these novel MRI biomarkers-whether used alone or in combination-for the differential diagnosis of MS.

The use of 7T MRI in multiple sclerosis: review and consensus statement from the North American Imaging in Multiple Sclerosis Cooperative

The use of ultra-high-field 7-Tesla (7T) MRI in multiple sclerosis (MS) research has grown significantly over the past two decades. With recent regulatory approvals of 7T scanners for clinical use in 2017 and 2020, the use of this technology for routine care is poised to continue to increase in the coming years. In this context, the North American Imaging in MS Cooperative (NAIMS) convened a workshop in February 2023 to review the previous and current use of 7T technology for MS research and potential future research and clinical applications. In this workshop, experts were tasked with reviewing the current literature and proposing a series of consensus statements, which were reviewed and approved by the NAIMS. In this review and consensus paper, we provide background on the use of 7T MRI in MS research, highlighting this technology's promise for identification and quantification of aspects of MS pathology that are more difficult to visualize with lower-field MRI, such as grey matter lesions, paramagnetic rim lesions, leptomeningeal enhancement and the central vein sign. We also review the promise of 7T MRI to study metabolic and functional changes to the brain in MS. The NAIMS provides a series of consensus statements regarding what is currently known about the use of 7T MRI in MS, and additional statements intended to provide guidance as to what work is necessary going forward to accelerate 7T MRI research in MS and translate this technology for use in clinical practice and clinical trials. This includes guidance on technical development, proposals for a universal acquisition protocol and suggestions for research geared towards assessing the utility of 7T MRI to improve MS diagnostics, prognostics and therapeutic efficacy monitoring. The NAIMS expects that this article will provide a roadmap for future use of 7T MRI in MS.

Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review

Multiple sclerosis (MS) is a demyelinating neurological disorder with a highly heterogeneous clinical presentation and course of progression. Disease-modifying therapies are the only available treatment, as there is no known cure for the disease. Careful selection of suitable therapies is necessary, as they can be accompanied by serious risks and adverse effects such as infection. Magnetic resonance imaging (MRI) plays a central role in the diagnosis and management of MS, though MRI lesions have displayed only moderate associations with MS clinical outcomes, known as the clinico-radiological paradox. With the advent of machine learning (ML) in healthcare, the predictive power of MRI can be improved by leveraging both traditional and advanced ML algorithms capable of analyzing increasingly complex patterns within neuroimaging data. The purpose of this review was to examine the application of MRI-based ML for prediction of MS disease progression. Studies were divided into five main categories: predicting the conversion of clinically isolated syndrome to MS, cognitive outcome, EDSS-related disability, motor disability and disease activity. The performance of ML models is discussed along with highlighting the influential MRI-derived biomarkers. Overall, MRI-based ML presents a promising avenue for MS prognosis. However, integration of imaging biomarkers with other multimodal patient data shows great potential for advancing personalized healthcare approaches in MS.

Diagnostic performance of central vein sign versus oligoclonal bands for multiple sclerosis

BACKGROUND

Cerebrospinal fluid (CSF) oligoclonal bands (OCB) are a diagnostic biomarker in multiple sclerosis (MS). The central vein sign (CVS) is an imaging biomarker for MS that may improve diagnostic accuracy.

OBJECTIVES

The objective of the study is to examine the diagnostic performance of simplified CVS methods in comparison to OCB in participants with clinical or radiological suspicion for MS.

METHODS

Participants from the CentrAl Vein Sign in MS (CAVS-MS) pilot study with CSF testing were included. Select-3 and Select-6 (counting up to three or six CVS+ lesions per scan) were rated on post-gadolinium FLAIR* images. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value for Select-3, Select-6, OCB, and combinations thereof were calculated for MS diagnosis at baseline and at 12 months.

RESULTS

Of 53 participants, 25 were OCB+. At baseline, sensitivity for MS diagnosis was 0.75 for OCB, 0.83 for Select-3, and 0.71 for Select-6. Specificity for MS diagnosis was 0.76 for OCB, 0.48 for Select-3, and 0.86 for Select-6. At 12 months, PPV for MS diagnosis was 0.95 for Select-6 and 1.00 for Select-6 with OCB+ status.

DISCUSSION

Results suggest similar diagnostic performance of simplified CVS methods and OCB. Ongoing studies will refine whether CVS could be used in replacement or in conjunction with OCB.

Current and future role of MRI in the diagnosis and prognosis of multiple sclerosis

In the majority of cases, multiple sclerosis (MS) is characterized by reversible episodes of neurological dysfunction, often followed by irreversible clinical disability. Accurate diagnostic criteria and prognostic markers are critical to enable early diagnosis and correctly identify patients with MS at increased risk of disease progression. The 2017 McDonald diagnostic criteria, which include magnetic resonance imaging (MRI) as a fundamental paraclinical tool, show high sensitivity and accuracy for the diagnosis of MS allowing early diagnosis and treatment. However, their inappropriate application, especially in the context of atypical clinical presentations, may increase the risk of misdiagnosis. To further improve the diagnostic process, novel imaging markers are emerging, but rigorous validation and standardization is still needed before they can be incorporated into clinical practice. This Series article discusses the current role of MRI in the diagnosis and prognosis of MS, while examining promising MRI markers, which could serve as reliable predictors of subsequent disease progression, helping to optimize the management of individual patients with MS. We also explore the potential of new technologies, such as artificial intelligence and automated quantification tools, to support clinicians in the management of patients. Yet, to ensure consistency and improvement in the use of MRI in MS diagnosis and patient follow-up, it is essential that standardized brain and spinal cord MRI protocols are applied, and that interpretation of results is performed by qualified (neuro)radiologists in all countries.

Artificial Intelligence and Multiple Sclerosis

In this paper, we analyse the different advances in artificial intelligence (AI) approaches in multiple sclerosis (MS). AI applications in MS range across investigation of disease pathogenesis, diagnosis, treatment, and prognosis. A subset of AI, Machine learning (ML) models analyse various data sources, including magnetic resonance imaging (MRI), genetic, and clinical data, to distinguish MS from other conditions, predict disease progression, and personalize treatment strategies. Additionally, AI models have been extensively applied to lesion segmentation, identification of biomarkers, and prediction of outcomes, disease monitoring, and management. Despite the big promises of AI solutions, model interpretability and transparency remain critical for gaining clinician and patient trust in these methods. The future of AI in MS holds potential for open data initiatives that could feed ML models and increasing generalizability, the implementation of federated learning solutions for training the models addressing data sharing issues, and generative AI approaches to address challenges in model interpretability, and transparency. In conclusion, AI presents an opportunity to advance our understanding and management of MS. AI promises to aid clinicians in MS diagnosis and prognosis improving patient outcomes and quality of life, however ensuring the interpretability and transparency of AI-generated results is going to be key for facilitating the integration of AI into clinical practice.

[XVI Post-ECTRIMS Meeting: review of the new developments presented at the 2023 ECTRIMS Congress (II)]

The XVI Post-ECTRIMS meeting was held in Seville on 20 and 21 October 2023, where expert neurologists in multiple sclerosis (MS) summarised the main new developments presented at the ECTRIMS 2023 congress, which took place in Milan from 11 to 13 October. The aim of this article is to summarise the content presented at the Post-ECTRIMS Meeting, in an article in two parts. This second part covers the health of women and elderly MS patients, new trends in the treatment of cognitive impairment, focusing particularly on meditation, neuroeducation and cognitive rehabilitation, and introduces the concept of fatigability, which has been used to a limited extent in MS. The key role of digitalization and artificial intelligence in the theoretically near future is subject to debate, along with the potential these technologies can offer. The most recent research on the various treatment algorithms and their efficacy and safety in the management of the disease is reviewed. Finally, the most relevant data for cladribine and evobrutinib are presented, as well as future therapeutic strategies currently being investigated.

Central Vein Sign and Paramagnetic Rim Lesions: Susceptibility Changes in Brain Tissues and Their Implications for the Study of Multiple Sclerosis Pathology

Multiple sclerosis (MS) is the most common acquired inflammatory and demyelinating disease in adults. The conventional diagnostic of MS and the follow-up of inflammatory activity is based on the detection of hyperintense foci in T2 and fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) and lesions with brain-blood barrier (BBB) disruption in the central nervous system (CNS) parenchyma. However, T2/FLAIR hyperintense lesions are not specific to MS and the MS pathology and inflammatory processes go far beyond focal lesions and can be independent of BBB disruption. MRI techniques based on the magnetic susceptibility properties of the tissue, such as T2*, susceptibility-weighted images (SWI), and quantitative susceptibility mapping (QSM) offer tools for advanced MS diagnostic, follow-up, and the assessment of more detailed features of MS dynamic pathology. Susceptibility-weighted techniques are sensitive to the paramagnetic components of biological tissues, such as deoxyhemoglobin. This capability enables the visualization of brain parenchymal veins. Consequently, it presents an opportunity to identify veins within the core of multiple sclerosis (MS) lesions, thereby affirming their venocentric characteristics. This advancement significantly enhances the accuracy of the differential diagnostic process. Another important paramagnetic component in biological tissues is iron. In MS, the dynamic trafficking of iron between different cells, such as oligodendrocytes, astrocytes, and microglia, enables the study of different stages of demyelination and remyelination. Furthermore, the accumulation of iron in activated microglia serves as an indicator of latent inflammatory activity in chronic MS lesions, termed paramagnetic rim lesions (PRLs). PRLs have been correlated with disease progression and degenerative processes, underscoring their significance in MS pathology. This review will elucidate the underlying physical principles of magnetic susceptibility and their implications for the formation and interpretation of T2*, SWI, and QSM sequences. Additionally, it will explore their applications in multiple sclerosis (MS), particularly in detecting the central vein sign (CVS) and PRLs, and assessing iron metabolism. Furthermore, the review will discuss their role in advancing early and precise MS diagnosis and prognostic evaluation, as well as their utility in studying chronic active inflammation and degenerative processes.

The new era of artificial intelligence in neuroradiology: current research and promising tools

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

BACKGROUND

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals.

OBJECTIVES

Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used.

METHODS

We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms.

RESULTS

The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed.

CONCLUSION

The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.

Clinical correlation between disease progression and central vein sign in pediatric onset multiple sclerosis: A binational study

BACKGROUND

The central vein sign (CVS) has been proposed as a novel MRI biomarker to improve diagnosis of pediatric-onset MS (POMS). However, the role of CVS in POMS progression has yet to be discovered.

OBJECTIVES

To investigate the appearance of CVS and its correlation with POMS disease progression.

METHODS

One hundred fifty-six POMS from two MS centers in Israel and Czech Republic MS centers were followed for five years. Patient assessment was performed by the Expanded Disability Status Scale (EDSS) and Annual Relapse Rate (ARR). Patients in whom at least 40 % of brain MRI lesions had CVS ("rule of 40") were determined as CVS-positive.

RESULTS

The total group of POMS consisted of 96 CVS-negative (61.5 %), aged 14.6 ± 1.9 years, EDSS 2.0, 75 % Interquartile Range (IQR) 1.0-3.0, disease duration (DD) 6.28 ± 0.38 years, and 60 CVS-positive (38.5 %), aged 15.1 ± 0.3 years, EDSS 2.0, IQR 1.5-3.0, DD 5.62 ± 0.13 years, were analyzed. After a three and five-year follow-up, the CVS-positive patients had higher EDSS scores than those who were CVS-negative, 2.0, IQR 1.0-2.5, vs 1.0, IQR 1.0-2.0, (p = 0.009) and 2.0, IQR 1.0-3.25 vs 1.0, IQR 1.0-2.0, (p = 0.0003), respectively. Patients with CVS-positive POMS were characterized by a significantly higher ARR (0.78 ± 0.08 vs 0.57 ± 0.04, p = 0.002). These results were confirmed in subgroups of Disease Modifying Treatments (DMT) untreated and treated patients.

CONCLUSION

CVS-positive POMS is characterized by higher disability progression than CVS-negative, indicating the importance of CVS in disease pathogenesis.

A multicenter pilot study evaluating simplified central vein assessment for the diagnosis of multiple sclerosis

BACKGROUND

The central vein sign (CVS) is a proposed magnetic resonance imaging (MRI) biomarker for multiple sclerosis (MS); the optimal method for abbreviated CVS scoring is not yet established.

OBJECTIVE

The aim of this study was to evaluate the performance of a simplified approach to CVS assessment in a multicenter study of patients being evaluated for suspected MS.

METHODS

Adults referred for possible MS to 10 sites were recruited. A post-Gd 3D T2*-weighted MRI sequence (FLAIR*) was obtained in each subject. Trained raters at each site identified up to six CVS-positive lesions per FLAIR* scan. Diagnostic performance of CVS was evaluated for a diagnosis of MS which had been confirmed using the 2017 McDonald criteria at thresholds including three positive lesions (Select-3*) and six positive lesions (Select-6*). Inter-rater reliability assessments were performed.

RESULTS

Overall, 78 participants were analyzed; 37 (47%) were diagnosed with MS, and 41 (53%) were not. The mean age of participants was 45 (range: 19-64) years, and most were female (n = 55, 71%). The area under the receiver operating characteristic curve (AUROC) for the simplified counting method was 0.83 (95% CI: 0.73-0.93). Select-3* and Select-6* had sensitivity of 81% and 65% and specificity of 68% and 98%, respectively. Inter-rater agreement was 78% for Select-3* and 83% for Select-6*.

CONCLUSION

A simplified method for CVS assessment in patients referred for suspected MS demonstrated good diagnostic performance and inter-rater agreement.

Central vein sign and paramagnetic rim sign: From radiologically isolated syndrome to multiple sclerosis

The widespread use of magnetic resonance imaging (MRI) has led to an increase in incidental findings in the central nervous system. Radiologically isolated syndrome (RIS) is a condition where imaging reveals lesions suggestive of demyelinating disease without any clinical episodes consistent with multiple sclerosis (MS). The prognosis for RIS patients is uncertain, with some remaining asymptomatic while others progress to MS. Several risk factors for disease progression have been identified, including male sex, younger age at diagnosis, and spinal cord lesions. This article reviews two promising biomarkers, the central vein sign (CVS) and the paramagnetic rim sign (PRS), and their potential role in the diagnosis and prognosis of MS and RIS. Both CVS and PRS have been shown to be accurate diagnostic markers in MS, with high sensitivity and specificity, and have been useful in distinguishing MS from other disorders. Further research is needed to validate these findings and determine the clinical utility of these biomarkers in routine practice.

Present and future of the diagnostic work-up of multiple sclerosis: the imaging perspective

In recent years, the use of magnetic resonance imaging (MRI) for the diagnostic work-up of multiple sclerosis (MS) has evolved considerably. The 2017 McDonald criteria show high sensitivity and accuracy in predicting a second clinical attack in patients with a typical clinically isolated syndrome and allow an earlier diagnosis of MS. They have been validated, are evidence-based, simplify the clinical use of MRI criteria and improve MS patients' management. However, to limit the risk of misdiagnosis, they should be applied by expert clinicians only after the careful exclusion of alternative diagnoses. Recently, new MRI markers have been proposed to improve diagnostic specificity for MS and reduce the risk of misdiagnosis. The central vein sign and chronic active lesions (i.e., paramagnetic rim lesions) may increase the specificity of MS diagnostic criteria, but further effort is necessary to validate and standardize their assessment before implementing them in the clinical setting. The feasibility of subpial demyelination assessment and the clinical relevance of leptomeningeal enhancement evaluation in the diagnostic work-up of MS appear more limited. Artificial intelligence tools may capture MRI attributes that are beyond the human perception, and, in the future, artificial intelligence may complement human assessment to further ameliorate the diagnostic work-up and patients' classification. However, guidelines that ensure reliability, interpretability, and validity of findings obtained from artificial intelligence approaches are still needed to implement them in the clinical scenario. This review provides a summary of the most recent updates regarding the application of MRI for the diagnosis of MS.

Automatic detection of active and inactive multiple sclerosis plaques using the Bayesian approach in susceptibility-weighted imaging

BACKGROUND

Susceptibility-weighted imaging (SWI) is efficient in detecting multiple sclerosis (MS) plaques and evaluating the level of disease activity.

PURPOSE

To automatically detect active and inactive MS plaques in SWI images using a Bayesian approach.

MATERIAL AND METHODS

A 1.5-T scanner was used to evaluate 147 patients with MS. The area of the plaques along with their active or inactive status were automatically identified using a Bayesian approach. Plaques were given an orange color if they were active and a blue color if they were inactive, based on the preset signal intensity.

RESULTS

Experimental findings show that the proposed method has a high accuracy rate of 91% and a sensitivity rate of 76% for identifying the type and area of plaques. Inactive plaques were properly identified in 87% of cases, and active plaques in 76% of cases. The Kappa analysis revealed an 80% agreement between expert diagnoses based on contrast-enhanced and FLAIR images and Bayesian inferences in SWI.

CONCLUSION

The results of our study demonstrated that the proposed method has good accuracy for identifying the MS plaque area as well as for identifying the types of active or inactive plaques in SWI. Therefore, it might be helpful to use the proposed method as a supplemental tool to accelerate the specialist's diagnosis.

What is the potential of paramagnetic rim lesions as diagnostic indicators in multiple sclerosis?

INTRODUCTION

In multiple sclerosis (MS), paramagnetic rim lesions (PRLs) on MRI identify a subset of chronic active lesions (CALs), which have been linked through clinical and pathological studies to more severe disease course and greater disability accumulation. Beside their prognostic relevance, increasing evidence supports the use of PRL as a diagnostic biomarker.

AREAS COVERED

This review summarizes the most recent updates regarding the MRI pathophysiology of PRL, their prevalence in MS (by clinical phenotypes) vs mimicking conditions, and their potential role as diagnostic MS biomarkers. We searched PubMed with terms including 'multiple sclerosis' AND 'paramagnetic rim lesions' OR 'iron rim lesions' OR 'rim lesions' for manuscripts published between January 2008 and July 2022.

EXPERT OPINION

Current research suggests that PRL can improve the diagnostic specificity and the overall accuracy of MS diagnosis when used together with the dissemination in space MRI criteria and the central vein sign. Nevertheless, future prospective multicenter studies should further define the real-world prevalence and specificity of PRL. International guidelines are needed to establish methodological criteria for PRL identification before its implementation into clinical practice.

Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: Emerging machine learning techniques and future avenues

The current diagnostic criteria for multiple sclerosis (MS) lack specificity, and this may lead to misdiagnosis, which remains an issue in present-day clinical practice. In addition, conventional biomarkers only moderately correlate with MS disease progression. Recently, some MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis. Moreover, studies have shown that CL and PRL are potential prognostic biomarkers, the former correlating with cognitive impairments and the latter with early disability progression. As machine learning-based methods have achieved extraordinary performance in the assessment of conventional imaging biomarkers, such as white matter lesion segmentation, several automated or semi-automated methods have been proposed as well for CL, PRL, and CVS. In the present review, we first introduce these MS biomarkers and their imaging methods. Subsequently, we describe the corresponding machine learning-based methods that were proposed to tackle these clinical questions, putting them into context with respect to the challenges they are facing, including non-standardized MRI protocols, limited datasets, and moderate inter-rater variability. We conclude by presenting the current limitations that prevent their broader deployment and suggesting future research directions.

From pathology to MRI and back: Clinically relevant biomarkers of multiple sclerosis lesions

Focal lesions in both white and gray matter are characteristic of multiple sclerosis (MS). Histopathological studies have helped define the main underlying pathological processes involved in lesion formation and evolution, serving as a gold standard for many years. However, histopathology suffers from an intrinsic bias resulting from over-reliance on tissue samples from late stages of the disease or atypical cases and is inadequate for routine patient assessment. Pathological-radiological correlative studies have established advanced MRI's sensitivity to several relevant MS-pathological substrates and its practicality for assessing dynamic changes and following lesions over time. This review focuses on novel imaging techniques that serve as biomarkers of critical pathological substrates of MS lesions: the central vein, chronic inflammation, remyelination and repair, and cortical lesions. For each pathological process, we address the correlative value of MRI to MS pathology, its contribution in elucidating MS pathology in vivo, and the clinical utility of the imaging biomarker.

Evaluation of Disability Progression in Multiple Sclerosis via Magnetic-Resonance-Based Deep Learning Techniques

Short-term disability progression was predicted from a baseline evaluation in patients with multiple sclerosis (MS) using their three-dimensional T1-weighted (3DT1) magnetic resonance images (MRI). One-hundred-and-eighty-one subjects diagnosed with MS underwent 3T-MRI and were followed up for two to six years at two sites, with disability progression defined according to the expanded-disability-status-scale (EDSS) increment at the follow-up. The patients’ 3DT1 images were bias-corrected, brain-extracted, registered onto MNI space, and divided into slices along coronal, sagittal, and axial projections. Deep learning image classification models were applied on slices and devised as ResNet50 fine-tuned adaptations at first on a large independent dataset and secondly on the study sample. The final classifiers’ performance was evaluated via the area under the curve (AUC) of the false versus true positive diagram. Each model was also tested against its null model, obtained by reshuffling patients’ labels in the training set. Informative areas were found by intersecting slices corresponding to models fulfilling the disability progression prediction criteria. At follow-up, 34% of patients had disability progression. Five coronal and five sagittal slices had one classifier surviving the AUC evaluation and null test and predicted disability progression (AUC > 0.72 and AUC > 0.81, respectively). Likewise, fifteen combinations of classifiers and axial slices predicted disability progression in patients (AUC > 0.69). Informative areas were the frontal areas, mainly within the grey matter. Briefly, 3DT1 images may give hints on disability progression in MS patients, exploiting the information hidden in the MRI of specific areas of the brain.

Multiple sclerosis cortical lesion detection with deep learning at ultra-high-field MRI

Manually segmenting multiple sclerosis (MS) cortical lesions (CLs) is extremely time consuming, and past studies have shown only moderate inter-rater reliability. To accelerate this task, we developed a deep-learning-based framework (CLAIMS: Cortical Lesion AI-Based Assessment in Multiple Sclerosis) for the automated detection and classification of MS CLs with 7 T MRI. Two 7 T datasets, acquired at different sites, were considered. The first consisted of 60 scans that include 0.5 mm isotropic MP2RAGE acquired four times (MP2RAGE×4), 0.7 mm MP2RAGE, 0.5 mm T₂ *-weighted GRE, and 0.5 mm T₂ *-weighted EPI. The second dataset consisted of 20 scans including only 0.75 × 0.75 × 0.9 mm³ MP2RAGE. CLAIMS was first evaluated using sixfold cross-validation with single and multi-contrast 0.5 mm MRI input. Second, the performance of the model was tested on 0.7 mm MP2RAGE images after training with either 0.5 mm MP2RAGE×4, 0.7 mm MP2RAGE, or alternating the two. Third, its generalizability was evaluated on the second external dataset and compared with a state-of-the-art technique based on partial volume estimation and topological constraints (MSLAST). CLAIMS trained only with MP2RAGE×4 achieved results comparable to those of the multi-contrast model, reaching a CL true positive rate of 74% with a false positive rate of 30%. Detection rate was excellent for leukocortical and subpial lesions (83%, and 70%, respectively), whereas it reached 53% for intracortical lesions. The correlation between disability measures and CL count was similar for manual and CLAIMS lesion counts. Applying a domain-scanner adaptation approach and testing CLAIMS on the second dataset, the performance was superior to MSLAST when considering a minimum lesion volume of 6 μL (lesion-wise detection rate of 71% versus 48%). The proposed framework outperforms previous state-of-the-art methods for automated CL detection across scanners and protocols. In the future, CLAIMS may be useful to support clinical decisions at 7 T MRI, especially in the field of diagnosis and differential diagnosis of MS patients.

Lesion size and shape in central vein sign assessment for multiple sclerosis diagnosis: An in vivo and postmortem MRI study

BACKGROUND

The "central vein sign" (CVS), a linear hypointensity on T2*-weighted imaging corresponding to a central vein/venule, is associated with multiple sclerosis (MS) lesions. The effect of lesion-size exclusion criteria on MS diagnostic accuracy has not been extensively studied.

OBJECTIVE

Investigate the optimal lesion-size exclusion criteria for CVS use in MS diagnosis.

METHODS

Cross-sectional study of 163 MS and 51 non-MS, and radiological/histopathological correlation of 5 MS and 1 control autopsy cases. The effects of lesion-size exclusion on MS diagnosis using the CVS, and intralesional vein detection on histopathology were evaluated.

RESULTS

CVS+ lesions were larger compared to CVS- lesions, with effect modification by MS diagnosis (mean difference +7.7 mm³, p = 0.004). CVS percentage-based criteria with no lesion-size exclusion showed the highest diagnostic accuracy in differentiating MS cases. However, a simple count of three or more CVS+ lesions greater than 3.5 mm is highly accurate and can be rapidly implemented (sensitivity 93%; specificity 88%). On magnetic resonance imaging (MRI)-histopathological correlation, the CVS had high specificity for identifying intralesional veins (0/7 false positives).

CONCLUSION

Lesion-size measures add important information when using CVS+ lesion counts for MS diagnosis. The CVS is a specific biomarker corresponding to intralesional veins on histopathology.

Role of artificial intelligence in MS clinical practice

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.

Central vein sign: A putative diagnostic marker for multiple sclerosis

The presence of a "central vein sign" (CVS) has been introduced as a biomarker for the diagnosis of multiple sclerosis (MS) and shown to have the ability to accurately differentiate MS from other white matter diseases (MS mimics). Following the development of susceptibility-based magnetic resonance venography that allowed the in vivo detection of CVS, a standard CVS definition was established by introducing the "40% rule" that assesses the number of MS lesions with CVS as a fraction of the total number of lesions to differentiate MS lesions from other types of lesions. The "50% rule," the "three-lesion criteria," and the "six-lesion criteria" were later introduced and defined. Each of these rules had high levels of sensitivity, specificity, and accuracy in differentiating MS from other diseases, which has been recognized by the Magnetic Resonance Imaging in MS (MAGNIMS) group and the Consortium of MS Centers task force. The North American Imaging in Multiple Sclerosis Cooperative even provided statements and recommendations aiming to refine, standardize and evaluate the CVS in MS. Herein, we review the existing literature on CVS and evaluate its added value in the diagnosis of MS and usefulness in differentiating it from other vasculopathies. We also review the histopathology of CVS and identify available automated CVS assessment methods as well as define the role of vascular comorbidities in the diagnosis of MS.

Opportunities for Understanding MS Mechanisms and Progression With MRI Using Large-Scale Data Sharing and Artificial Intelligence

Patients with multiple sclerosis (MS) have heterogeneous clinical presentations, symptoms, and progression over time, making MS difficult to assess and comprehend in vivo. The combination of large-scale data sharing and artificial intelligence creates new opportunities for monitoring and understanding MS using MRI. First, development of validated MS-specific image analysis methods can be boosted by verified reference, test, and benchmark imaging data. Using detailed expert annotations, artificial intelligence algorithms can be trained on such MS-specific data. Second, understanding disease processes could be greatly advanced through shared data of large MS cohorts with clinical, demographic, and treatment information. Relevant patterns in such data that may be imperceptible to a human observer could be detected through artificial intelligence techniques. This applies from image analysis (lesions, atrophy, or functional network changes) to large multidomain datasets (imaging, cognition, clinical disability, genetics). After reviewing data sharing and artificial intelligence, we highlight 3 areas that offer strong opportunities for making advances in the next few years: crowdsourcing, personal data protection, and organized analysis challenges. Difficulties as well as specific recommendations to overcome them are discussed, in order to best leverage data sharing and artificial intelligence to improve image analysis, imaging, and the understanding of MS.

Prediction in treatment outcomes in multiple sclerosis: challenges and recent advances

INTRODUCTION

Multiple Sclerosis (MS) is a chronic autoimmune and neurodegenerative disease of the central nervous system with a course dependent on early treatment response. Increasing evidence also suggests that despite eliminating disease activity (relapses and lesions), many patients continue to accrue disability, highlighting the need for a more comprehensive definition of treatment success. Optimizing disability outcome measures, as well as continuously improving our understanding of neuroinflammatory and neurodegenerative biomarkers is required.

AREAS COVERED

This review describes the challenges inherent in classifying and monitoring disease phenotype in MS. The review also provides an assessment of clinical, radiological, and blood biomarker tools for current and future practice.

EXPERT OPINION

Emerging MRI techniques and standardized patient outcome assessments will increase the accuracy of initial diagnosis and understanding of disease progression.

Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)

Computer-aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence-based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.

Machine Learning Approaches in Study of Multiple Sclerosis Disease Through Magnetic Resonance Images

Multiple sclerosis (MS) is one of the most common autoimmune diseases which is commonly diagnosed and monitored using magnetic resonance imaging (MRI) with a combination of clinical manifestations. The purpose of this review is to highlight the main applications of Machine Learning (ML) models and their performance in the MS field using MRI. We reviewed the articles of the last decade and grouped them based on the applications of ML in MS using MRI data into four categories: 1) Automated diagnosis of MS, 2) Prediction of MS disease progression, 3) Differentiation of MS stages, 4) Differentiation of MS from similar disorders.

Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review

Multiple Sclerosis (MS) is a type of brain disease which causes visual, sensory, and motor problems for people with a detrimental effect on the functioning of the nervous system. In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. MRI modalities provide physicians with fundamental information about the structure and function of the brain, which is crucial for the rapid diagnosis of MS lesions. Diagnosing MS using MRI is time-consuming, tedious, and prone to manual errors. Research on the implementation of computer aided diagnosis system (CADS) based on artificial intelligence (AI) to diagnose MS involves conventional machine learning and deep learning (DL) methods. In conventional machine learning, feature extraction, feature selection, and classification steps are carried out by using trial and error; on the contrary, these steps in DL are based on deep layers whose values are automatically learn. In this paper, a complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided. Initially, the steps involved in various CADS proposed using MRI modalities and DL techniques for MS diagnosis are investigated. The important preprocessing techniques employed in various works are analyzed. Most of the published papers on MS diagnosis using MRI modalities and DL are presented. The most significant challenges facing and future direction of automated diagnosis of MS using MRI modalities and DL techniques are also provided.

Central vein sign and iron rim in multiple sclerosis: ready for clinical use?

PURPOSE OF REVIEW

To summarize recent evidence from the application of susceptibility-based MRI sequences to investigate the 'central vein sign' (CVS) and 'iron rim' as biomarkers to improve the diagnostic work-up of multiple sclerosis (MS) and predict disease severity.

RECENT FINDINGS

The CVS is a specific biomarker for MS being detectable from the earliest phase of the disease. A threshold of 40% of lesions with the CVS can be optimal to distinguish MS from non-MS patients. Iron rim lesions, reflecting chronic active lesions, develop in relapsing-remitting MS patients and persist in progressive MS. They increase in size in the first few years after their formation and then stabilize. Iron rim lesions can distinguish MS from non-MS patients but not the different MS phenotypes. The presence of at least four iron rim lesions is associated with an earlier clinical disability, higher prevalence of clinically progressive MS and more severe brain atrophy. Automated methods for CVS and iron rim lesion detection are under development to facilitate their quantification.

SUMMARY

The assessment of the CVS and iron rim lesions is feasible in the clinical scenario and provides MRI measures specific to MS pathological substrates, improving diagnosis and prognosis of these patients.

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.

Preventing multiple sclerosis misdiagnosis using the "central vein sign": A real-world study

BACKGROUND

Misdiagnosis of multiple sclerosis (MS) is common and often occurs due to misattribution of non-MS magnetic resonance imaging (MRI) lesions to MS demyelination. A recently developed MRI biomarker, the central vein sign (CVS), has demonstrated high specificity for MS lesions and may thus help prevent misdiagnosis.

OBJECTIVE

This study explores the potential "real world" diagnostic value of CVS by comparing CVS in patients with MS and patients previously misdiagnosed with MS.

METHODS

Fifteen patients with MS and 15 misdiagnosed with MS were prospectively recruited to undergo 3T brain MRI. T2-weighted fluid-attenuated inversion recovery (FLAIR) and T2*-weighted segmented echo-planar-imaging (T2*-EPI) were acquired. The generated FLAIR* images were analyzed by two independent raters. The percentage of lesions with CVS was calculated for each patient.

RESULTS

A CVS lesion threshold of 29% or higher resulted in high sensitivity (0.79) and specificity (0.88) for MS and correctly identified 87% of patients previously misdiagnosed with MS. Interrater reliability for CVS was high with a Cohen's kappa coefficient of 0.86.

CONCLUSION

This study demonstrates the ability of CVS to differentiate between patients with MS and patients with an MS misdiagnosis resulting from standard MRI and clinical evaluation. Clinical application of CVS may reduce MS misdiagnosis.

The Use of the Central Vein Sign in the Diagnosis of Multiple Sclerosis: A Systematic Review and Meta-analysis

Background: The central vein sign (CVS) is a radiological feature proposed as a multiple sclerosis (MS) imaging biomarker able to accurately differentiate MS from other white matter diseases of the central nervous system. In this work, we evaluated the pooled proportion of the CVS in brain MS lesions and to estimate the diagnostic performance of CVS to perform a diagnosis of MS and propose an optimal cut-off value. Methods: A systematic search was performed on publicly available databases (PUBMED/MEDLINE and Web of Science) up to 24 August 2020. Analysis of the proportion of white matter MS lesions with a central vein was performed using bivariate random-effect models. A meta-regression analysis was performed and the impact of using particular sequences (such as 3D echo-planar imaging) and post-processing techniques (such as FLAIR*) was investigated. Pooled sensibility and specificity were estimated using bivariate models and meta-regression was performed to address heterogeneity. Inclusion and publication bias were assessed using asymmetry tests and a funnel plot. A hierarchical summary receiver operating curve (HSROC) was used to estimate the summary accuracy in diagnostic performance. The Youden index was employed to estimate the optimal cut-off value using individual patient data. Results: The pooled proportion of lesions showing a CVS in the MS population was 73%. The use of the CVS showed a remarkable diagnostic performance in MS cases, providing a pooled specificity of 92% and a sensitivity of 95%. The optimal cut-off value obtained from the individual patient data pooled together was 40% with excellent accuracy calculated by the area under the ROC (0.946). The 3D-EPI sequences showed both a higher pooled proportion compared to other sequences and explained heterogeneity in the meta-regression analysis of diagnostic performances. The 1.5 Tesla (T) scanners showed a lower (58%) proportion of MS lesions with a CVS compared to both 3T (74%) and 7T (82%). Conclusions: The meta-analysis we have performed shows that the use of the CVS in differentiating MS from other mimicking diseases is encouraged; moreover, the use of dedicated sequences such as 3D-EPI and the high MRI field is beneficial.

Paramagnetic Rim Lesions are Specific to Multiple Sclerosis: An International Multicenter 3T MRI Study

In multiple sclerosis (MS), a subset of chronic active white matter lesions are identifiable on magnetic resonance imaging by their paramagnetic rims, and increasing evidence supports their association with severity of clinical disease. We studied their potential role in differential diagnosis, screening an international multicenter clinical research-based sample of 438 individuals affected by different neurological conditions (MS, other inflammatory, infectious, and non-inflammatory conditions). Paramagnetic rim lesions, rare in other neurological conditions (52% of MS vs 7% of non-MS cases), yielded high specificity (93%) in differentiating MS from non-MS. Future prospective multicenter studies should validate their role as a diagnostic biomarker. ANN NEUROL 2020;88:1034-1042.

RimNet: A deep 3D multimodal MRI architecture for paramagnetic rim lesion assessment in multiple sclerosis

OBJECTIVES

In multiple sclerosis (MS), the presence of a paramagnetic rim at the edge of non-gadolinium-enhancing lesions indicates perilesional chronic inflammation. Patients featuring a higher paramagnetic rim lesion burden tend to have more aggressive disease. The objective of this study was to develop and evaluate a convolutional neural network (CNN) architecture (RimNet) for automated detection of paramagnetic rim lesions in MS employing multiple magnetic resonance (MR) imaging contrasts.

MATERIALS AND METHODS

Imaging data were acquired at 3 Tesla on three different scanners from two different centers, totaling 124 MS patients, and studied retrospectively. Paramagnetic rim lesion detection was independently assessed by two expert raters on T2*-phase images, yielding 462 rim-positive (rim+) and 4857 rim-negative (rim-) lesions. RimNet was designed using 3D patches centered on candidate lesions in 3D-EPI phase and 3D FLAIR as input to two network branches. The interconnection of branches at both the first network blocks and the last fully connected layers favors the extraction of low and high-level multimodal features, respectively. RimNet's performance was quantitatively evaluated against experts' evaluation from both lesion-wise and patient-wise perspectives. For the latter, patients were categorized based on a clinically relevant threshold of 4 rim+ lesions per patient. The individual prediction capabilities of the images were also explored and compared (DeLong test) by testing a CNN trained with one image as input (unimodal).

RESULTS

The unimodal exploration showed the superior performance of 3D-EPI phase and 3D-EPI magnitude images in the rim+/- classification task (AUC = 0.913 and 0.901), compared to the 3D FLAIR (AUC = 0.855, Ps < 0.0001). The proposed multimodal RimNet prototype clearly outperformed the best unimodal approach (AUC = 0.943, P < 0.0001). The sensitivity and specificity achieved by RimNet (70.6% and 94.9%, respectively) are comparable to those of experts at the lesion level. In the patient-wise analysis, RimNet performed with an accuracy of 89.5% and a Dice coefficient (or F1 score) of 83.5%.

CONCLUSIONS

The proposed prototype showed promising performance, supporting the usage of RimNet for speeding up and standardizing the paramagnetic rim lesions analysis in MS.

The central vein sign in multiple sclerosis patients with vascular comorbidities

Background:

The central vein sign (CVS) is an imaging biomarker able to differentiate multiple sclerosis (MS) from other conditions causing similar appearance lesions on magnetic resonance imaging (MRI), including cerebral small vessel disease (CSVD). However, the impact of vascular risk factors (VRFs) for CSVD on the percentage of CVS positive (CVS+) lesions in MS has never been evaluated.

Objective:

To investigate the association between different VRFs and the percentage of CVS+ lesions in MS.

Methods:

In 50 MS patients, 3T brain MRIs (including high-resolution 3-dimensional T2*-weighted images) were analyzed for the presence of the CVS and MRI markers of CSVD. A backward stepwise regression model was used to predict the combined predictive effect of VRF (i.e. age, hypertension, diabetes, obesity, ever-smoking, and hypercholesterolemia) and MRI markers of CSVD on the CVS.

Results:

The median frequency of CVS+ lesions was 71% (range: 35%–100%). In univariate analysis, age ( p < 0.0001), hypertension ( p < 0.001), diabetes ( p < 0.01), obesity ( p < 0.01), smoking ( p < 0.05), and the presence of enlarged-perivascular-spaces on MRI ( p < 0.005) were all associated with a lower percentage of CVS+ lesions. The stepwise regression model showed that age and arterial hypertension were both associated with the percentage of CVS+ lesions in MS (adjusted R2 = 0.46; p < 0.0001 and p = 0.01, respectively).

Conclusion:

The proportion of CVS+ lesions significantly decreases in older and hypertensive MS patients. Although this study was conducted in patients with an already established MS diagnosis, the diagnostic yield of the previously proposed 35% CVS proportion-based diagnostic threshold appears to be not affected. Overall these results suggest that the presence of VRF for CSVD should be taken into account during the CVS assessment.