Gray matter MRI differentiates neuromyelitis optica from multiple sclerosis using random forest

Advanced Brain Imaging in Central Nervous System Demyelinating Diseases

In recent decades, advances in neuroimaging have profoundly transformed our comprehension of central nervous system demyelinating diseases. Remarkable technological progress has enabled the integration of cutting-edge acquisition and postprocessing techniques, proving instrumental in characterizing subtle focal changes, diffuse microstructural alterations, and macroscopic pathologic processes. This review delves into state-of-the-art modalities applied to multiple sclerosis, neuromyelitis optica spectrum disorders, and myelin oligodendrocyte glycoprotein antibody-associated disease. Furthermore, it explores how this dynamic landscape holds significant promise for the development of effective and personalized clinical management strategies, encompassing support for differential diagnosis, prognosis, monitoring treatment response, and patient stratification.

The diagnostic performance of AI-based algorithms to discriminate between NMOSD and MS using MRI features: A systematic review and meta-analysis

BACKGROUND

Magnetic resonance imaging [MRI] findings in Neuromyelitis optica spectrum disorder [NMOSD] and Multiple Sclerosis [MS] patients could lead us to discriminate toward them. For instance, U-fiber and Dawson's finger-type lesions are suggestive of MS, however linear ependymal lesions raise the possibility of NMOSD. Recently, artificial intelligence [AI] models have been used to discriminate between NMOSD and MS based on MRI features. In this study, we aim to systematically review the capability of AI algorithms in NMOSD and MS discrimination based on MRI features.

METHOD

We searched PubMed, Scopus, Web of Sciences, Embase, and IEEE databases up to August 2023. All studies that used AI-based algorithms to discriminate between NMOSD and MS using MRI features were included, without any restriction in time, region, race, and age. Data on NMOSD and MS patients, Aquaporin-4 antibodies [AQP4-Ab] status, diagnosis criteria, performance metrics (accuracy, sensitivity, specificity, and AUC), artificial intelligence paradigm, MR imaging, and used features were extracted. This study is registered with PROSPERO, CRD42023465265.

RESULTS

Fifteen studies were included in this systematic review, with sample sizes ranging between 53 and 351. 1,362 MS patients and 1,118 NMOSD patients were included in our systematic review. AQP4-Ab was positive in 94.9% of NMOSD patients in 9 studies. Eight studies used machine learning [ML] as a classifier, while 7 used deep learning [DL]. AI models based on only MRI or MRI and clinical features yielded a pooled accuracy of 82% (95% CI: 78-86%), sensitivity of 83% (95% CI: 79-88%), and specificity of 80% (95% CI: 75-86%). In subgroup analysis, using only MRI features yielded an accuracy, sensitivity, and specificity of 83% (95% CI: 78-88%), 81% (95% CI: 76-87%), and 84% (95% CI: 79-89%), respectively.

CONCLUSION

AI models based on MRI features showed a high potential to discriminate between NMOSD and MS. However, heterogeneity in MR imaging, model evaluation, and reporting performance metrics, among other confounders, affected the reliability of our results. Well-designed studies on multicentric datasets, standardized imaging and evaluation protocols, and detailed transparent reporting of results are needed to reach optimal performance.

Narcissus reflected: Grey and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

Despite the clinical significance of narcissistic personality, its neural bases have not been clarified yet, primarily because of methodological limitations of the previous studies, such as the low sample size, the use of univariate techniques and the focus on only one brain modality. In this study, we employed for the first time a combination of unsupervised and supervised machine learning methods, to identify the joint contributions of grey matter (GM) and white matter (WM) to narcissistic personality traits (NPT). After preprocessing, the brain scans of 135 participants were decomposed into eight independent networks of covarying GM and WM via parallel ICA. Subsequently, stepwise regression and Random Forest were used to predict NPT. We hypothesized that a fronto-temporo parietal network, mainly related to the default mode network, may be involved in NPT and associated WM regions. Results demonstrated a distributed network that included GM alterations in fronto-temporal regions, the insula and the cingulate cortex, along with WM alterations in cerebellar and thalamic regions. To assess the specificity of our findings, we also examined whether the brain network predicting narcissism could also predict other personality traits (i.e., histrionic, paranoid and avoidant personalities). Notably, this network did not predict such personality traits. Additionally, a supervised machine learning model (Random Forest) was used to extract a predictive model for generalization to new cases. Results confirmed that the same network could predict new cases. These findings hold promise for advancing our understanding of personality traits and potentially uncovering brain biomarkers associated with narcissism.

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Artificial intelligence (AI) is the branch of science aiming at creating algorithms able to carry out tasks that typically require human intelligence. In medicine, there has been a tremendous increase in AI applications thanks to increasingly powerful computers and the emergence of big data repositories. Multiple sclerosis (MS) is a chronic autoimmune condition affecting the central nervous system with a complex pathogenesis, a challenging diagnostic process strongly relying on magnetic resonance imaging (MRI) and a high and largely unexplained variability across patients. Therefore, AI applications in MS have the great potential of helping us better support the diagnosis, find markers for prognosis to eventually design more powerful randomised clinical trials and improve patient management in clinical practice and eventually understand the mechanisms of the disease. This topical review aims to summarise the recent advances in AI applied to MRI data in MS to illustrate its achievements, limitations and future directions.

CD11chigh B Cell Expansion Is Associated With Severity and Brain Atrophy in Neuromyelitis Optica

BACKGROUND AND OBJECTIVES

Neuromyelitis optica (NMO) is an autoimmune astrocytopathy mediated by anti-AQP4 antibody-producing B cells. Recently, a B-cell subset highly expressing CD11c and T-bet, originally identified as age-associated B cells, has been shown to be involved in the pathogenesis of various autoimmune diseases. The objective of this study was to determine the relationship between the frequency of CD11chigh B cells per CD19+ B cells in the peripheral blood of patients with NMO and the clinical profiles including the brain volume.

METHODS

In this observational study, 45 patients with anti-AQP4 antibody-positive NMO in remission and 30 healthy control subjects (HCs) were enrolled. Freshly isolated peripheral blood mononuclear cells were analyzed for immune cell phenotypes. The frequency of CD11chigh B cells per CD19+ B cells was assessed by flow cytometry and was evaluated in association with the clinical profiles of patients. Brain MRI data from 26 patients were included in the study for the analysis on the correlation between CD11chigh B-cell frequency and brain atrophy.

RESULTS

We found that the frequency of CD11chigh B cells in CD19+ B cells was significantly increased in patients with NMO compared with HCs. The expansion of CD11chigh B cells significantly correlated with EDSS, past relapse numbers, and disease duration. In addition, a higher frequency of CD11chigh B cells negatively correlated with total brain, white matter, and gray matter volumes and positively correlated with T2/FLAIR high lesion volumes. When the past clinical relapse episodes of patients with or without the expansion of CD11chigh B cells were compared, relapses in the brain occurred more frequently in patients with CD11chigh B-cell expansion. CD11chigh B cells had distinct features including expression of chemokine receptors associated with migration into peripheral inflammatory tissues and antigen presentation. CD11chigh B-cell frequency was positively correlated with T peripheral helper-1 (Tph-1) cell frequency.

DISCUSSION

Even during the relapse-free period, CD11chigh B cells could expand in the long disease context, possibly through the interaction with Tph-1 cells. The increased frequency of CD11chigh B cells associated with brain atrophy and disease severity, indicating that this cell population could be involved in chronic neuroinflammation in NMO.

Multiple sclerosis clinical forms classification with graph convolutional networks based on brain morphological connectivity

Multiple Sclerosis (MS) is an autoimmune disease that combines chronic inflammatory and neurodegenerative processes underlying different clinical forms of evolution, such as relapsing-remitting, secondary progressive, or primary progressive MS. This identification is usually performed by clinical evaluation at the diagnosis or during the course of the disease for the secondary progressive phase. In parallel, magnetic resonance imaging (MRI) analysis is a mandatory diagnostic complement. Identifying the clinical form from MR images is therefore a helpful and challenging task. Here, we propose a new approach for the automatic classification of MS forms based on conventional MRI (i.e., T1-weighted images) that are commonly used in clinical context. For this purpose, we investigated the morphological connectome features using graph based convolutional neural network. Our results obtained from the longitudinal study of 91 MS patients highlight the performance (F1-score) of this approach that is better than state-of-the-art as 3D convolutional neural networks. These results open the way for clinical applications such as disability correlation only using T1-weighted images.

oFVSD: a Python package of optimized forward variable selection decoder for high-dimensional neuroimaging data

The complexity and high dimensionality of neuroimaging data pose problems for decoding information with machine learning (ML) models because the number of features is often much larger than the number of observations. Feature selection is one of the crucial steps for determining meaningful target features in decoding; however, optimizing the feature selection from such high-dimensional neuroimaging data has been challenging using conventional ML models. Here, we introduce an efficient and high-performance decoding package incorporating a forward variable selection (FVS) algorithm and hyper-parameter optimization that automatically identifies the best feature pairs for both classification and regression models, where a total of 18 ML models are implemented by default. First, the FVS algorithm evaluates the goodness-of-fit across different models using the k-fold cross-validation step that identifies the best subset of features based on a predefined criterion for each model. Next, the hyperparameters of each ML model are optimized at each forward iteration. Final outputs highlight an optimized number of selected features (brain regions of interest) for each model with its accuracy. Furthermore, the toolbox can be executed in a parallel environment for efficient computation on a typical personal computer. With the optimized forward variable selection decoder (oFVSD) pipeline, we verified the effectiveness of decoding sex classification and age range regression on 1,113 structural magnetic resonance imaging (MRI) datasets. Compared to ML models without the FVS algorithm and with the Boruta algorithm as a variable selection counterpart, we demonstrate that the oFVSD significantly outperformed across all of the ML models over the counterpart models without FVS (approximately 0.20 increase in correlation coefficient, r, with regression models and 8% increase in classification models on average) and with Boruta variable selection algorithm (approximately 0.07 improvement in regression and 4% in classification models). Furthermore, we confirmed the use of parallel computation considerably reduced the computational burden for the high-dimensional MRI data. Altogether, the oFVSD toolbox efficiently and effectively improves the performance of both classification and regression ML models, providing a use case example on MRI datasets. With its flexibility, oFVSD has the potential for many other modalities in neuroimaging. This open-source and freely available Python package makes it a valuable toolbox for research communities seeking improved decoding accuracy.

Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorder using a deep learning model

Multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) are autoimmune inflammatory disorders of the central nervous system (CNS) with similar characteristics. The differential diagnosis between MS and NMOSD is critical for initiating early effective therapy. In this study, we developed a deep learning model to differentiate between multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) using brain magnetic resonance imaging (MRI) data. The model was based on a modified ResNet18 convolution neural network trained with 5-channel images created by selecting five 2D slices of 3D FLAIR images. The accuracy of the model was 76.1%, with a sensitivity of 77.3% and a specificity of 74.8%. Positive and negative predictive values were 76.9% and 78.6%, respectively, with an area under the curve of 0.85. Application of Grad-CAM to the model revealed that white matter lesions were the major classifier. This compact model may aid in the differential diagnosis of MS and NMOSD in clinical practice.

Personalized estimates of morphometric similarity in multiple sclerosis and neuromyelitis optica spectrum disorders

Brain morphometric alterations involve multiple brain regions on progression of the disease in multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) and exhibit age-related degenerative changes during the pathological aging. Recent advance in brain morphometry as measured using MRI have leveraged Person-Based Similarity Index (PBSI) approach to assess the extent of within-diagnosis similarity or heterogeneity of brain neuroanatomical profiles between individuals of healthy populations and validate in neuropsychiatric disorders. Brain morphometric changes throughout the lifespan would be invaluable for understanding regional variability of age-related structural degeneration and the substrate of inflammatory demyelinating disease. Here, we aimed to quantify the neuroanatomical profiles with PBSI measures of cortical thickness (CT) and subcortical volumes (SV) in 263 MS, 207 NMOSD, and 338 healthy controls (HC) from six separate central datasets (aged 11-80). We explored the between-group comparisons of PBSI measures, as well as the advancing age and sex effects on PBSI measures. Compared to NMOSD, MS showed a lower extent of within-diagnosis similarity. Significant differences in regional contributions to PBSI score were observed in 29 brain regions between MS and NMOSD (P < 0.05/164, Bonferroni corrected), of which bilateral cerebellum in MS and bilateral parahippocampal gyrus in NMOSD represented the highest divergence between the two patient groups, with a high similarity effect within each group. The PBSI scores were generally lower with advancing age, but their associations showed different patterns depending on the age range. For MS, CT profiles were significantly negatively correlated with age until the early 30 s (ρ = -0.265, P = 0.030), while for NMOSD, SV profiles were significantly negatively correlated with age with 51 year-old and older (ρ = -0.365, P = 0.008). The current study suggests that PBSI approach could be used to quantify the variation in brain morphometric changes in CNS inflammatory demyelinating disease, and exhibited a greater neuroanatomical heterogeneity pattern in MS compared with NMOSD. Our results reveal that, as an MR marker, PBSI may be sensitive to distribute the disease-associated grey matter diversity and complexity. Disease-driven production of regionally selective and age stage-dependency changes in the neuroanatomical profile of MS and NMOSD should be considered to facilitate the prediction of clinical outcomes and assessment of treatment responses.

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence

Multiple sclerosis (MS) is a neurological condition characterized by severe structural brain damage and by functional reorganization of the main brain networks that try to limit the clinical consequences of structural burden. Resting-state (RS) functional connectivity (FC) abnormalities found in this condition were shown to be variable across different MS phases, according to the severity of clinical manifestations. The article describes a system exploiting machine learning on RS FC matrices to discriminate different MS phenotypes and to identify relevant functional connections for MS stage characterization. To this end, the system exploits some mathematical properties of covariance-based RS FC representation, which can be described by a Riemannian manifold. The classification performance of the proposed framework was significantly above the chance level for all MS phenotypes. Moreover, the proposed system was successful in identifying relevant RS FC alterations contributing to an accurate phenotype classification.

Patterns of inflammation, microstructural alterations, and sodium accumulation define multiple sclerosis subtypes after 15 years from onset

Introduction

Conventional MRI is routinely used for the characterization of pathological changes in multiple sclerosis (MS), but due to its lack of specificity is unable to provide accurate prognoses, explain disease heterogeneity and reconcile the gap between observed clinical symptoms and radiological evidence. Quantitative MRI provides measures of physiological abnormalities, otherwise invisible to conventional MRI, that correlate with MS severity. Analyzing quantitative MRI measures through machine learning techniques has been shown to improve the understanding of the underlying disease by better delineating its alteration patterns.

Methods

In this retrospective study, a cohort of healthy controls (HC) and MS patients with different subtypes, followed up 15 years from clinically isolated syndrome (CIS), was analyzed to produce a multi-modal set of quantitative MRI features encompassing relaxometry, microstructure, sodium ion concentration, and tissue volumetry. Random forest classifiers were used to train a model able to discriminate between HC, CIS, relapsing remitting (RR) and secondary progressive (SP) MS patients based on these features and, for each classification task, to identify the relative contribution of each MRI-derived tissue property to the classification task itself.

Results and discussion

Average classification accuracy scores of 99 and 95% were obtained when discriminating HC and CIS vs. SP, respectively; 82 and 83% for HC and CIS vs. RR; 76% for RR vs. SP, and 79% for HC vs. CIS. Different patterns of alterations were observed for each classification task, offering key insights in the understanding of MS phenotypes pathophysiology: atrophy and relaxometry emerged particularly in the classification of HC and CIS vs. MS, relaxometry within lesions in RR vs. SP, sodium ion concentration in HC vs. CIS, and microstructural alterations were involved across all tasks.

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.

Differentiating Multiple Sclerosis From AQP4-Neuromyelitis Optica Spectrum Disorder and MOG-Antibody Disease With Imaging

BACKGROUND AND OBJECTIVES

Relapsing-remitting multiple sclerosis (RRMS), aquaporin-4 antibody-positive neuromyelitis optica spectrum disorder (AQP4-NMOSD), and myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD) may have overlapping clinical features. There is an unmet need for imaging markers that differentiate between them when serologic testing is unavailable or ambiguous. We assessed whether imaging characteristics typical of MS discriminate RRMS from AQP4-NMOSD and MOGAD, alone and in combination.

METHODS

Adult, nonacute patients with RRMS, APQ4-NMOSD, and MOGAD and healthy controls were prospectively recruited at the National Hospital for Neurology and Neurosurgery (London, United Kingdom) and the Walton Centre (Liverpool, United Kingdom) between 2014 and 2019. They underwent conventional and advanced brain, cord, and optic nerve MRI and optical coherence tomography (OCT).

RESULTS

A total of 91 consecutive patients (31 RRMS, 30 APQ4-NMOSD, and 30 MOGAD) and 34 healthy controls were recruited. The most accurate measures differentiating RRMS from AQP4-NMOSD were the proportion of lesions with the central vein sign (CVS) (84% vs 33%, accuracy/specificity/sensitivity: 91/88/93%, p < 0.001), followed by cortical lesions (median: 2 [range: 1-14] vs 1 [0-1], accuracy/specificity/sensitivity: 84/90/77%, p = 0.002) and white matter lesions (mean: 39.07 [±25.8] vs 9.5 [±14], accuracy/specificity/sensitivity: 78/84/73%, p = 0.001). The combination of higher proportion of CVS, cortical lesions, and optic nerve magnetization transfer ratio reached the highest accuracy in distinguishing RRMS from AQP4-NMOSD (accuracy/specificity/sensitivity: 95/92/97%, p < 0.001). The most accurate measures favoring RRMS over MOGAD were white matter lesions (39.07 [±25.8] vs 1 [±2.3], accuracy/specificity/sensitivity: 94/94/93%, p = 0.006), followed by cortical lesions (2 [1-14] vs 1 [0-1], accuracy/specificity/sensitivity: 84/97/71%, p = 0.004), and retinal nerve fiber layer thickness (RNFL) (mean: 87.54 [±13.83] vs 75.54 [±20.33], accuracy/specificity/sensitivity: 80/79/81%, p = 0.009). Higher cortical lesion number combined with higher RNFL thickness best differentiated RRMS from MOGAD (accuracy/specificity/sensitivity: 84/92/77%, p < 0.001).

DISCUSSION

Cortical lesions, CVS, and optic nerve markers achieve a high accuracy in distinguishing RRMS from APQ4-NMOSD and MOGAD. This information may be useful in clinical practice, especially outside the acute phase and when serologic testing is ambiguous or not promptly available.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that selected conventional and advanced brain, cord, and optic nerve MRI and OCT markers distinguish adult patients with RRMS from AQP4-NMOSD and MOGAD.

Combining Clinical and Genetic Data to Predict Response to Fingolimod Treatment in Relapsing Remitting Multiple Sclerosis Patients: A Precision Medicine Approach

A personalized approach is strongly advocated for treatment selection in Multiple Sclerosis patients due to the high number of available drugs. Machine learning methods proved to be valuable tools in the context of precision medicine. In the present work, we applied machine learning methods to identify a combined clinical and genetic signature of response to fingolimod that could support the prediction of drug response. Two cohorts of fingolimod-treated patients from Italy and France were enrolled and divided into training, validation, and test set. Random forest training and robust feature selection were performed in the first two sets respectively, and the independent test set was used to evaluate model performance. A genetic-only model and a combined clinical-genetic model were obtained. Overall, 381 patients were classified according to the NEDA-3 criterion at 2 years; we identified a genetic model, including 123 SNPs, that was able to predict fingolimod response with an AUROC= 0.65 in the independent test set. When combining clinical data, the model accuracy increased to an AUROC= 0.71. Integrating clinical and genetic data by means of machine learning methods can help in the prediction of response to fingolimod, even though further studies are required to definitely extend this approach to clinical applications.

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.

Identifying different cognitive phenotypes and their relationship with disability in neuromyelitis optica spectrum disorder

Background

The existence, frequency, and features of cognitive impairment (CI) in patients with neuromyelitis optica spectrum disorder (NMOSD) are still debated. A precise classification and characterization of cognitive phenotypes in patients with NMOSD are lacking.

Methods

A total of 66 patients with NMOSD and 22 healthy controls (HCs) underwent a neuropsychological assessment. Latent profile analysis (LPA) on cognitive test z scores was used to identify cognitive phenotypes, and ANOVA was used to define the clinical features of each phenotype. Univariate and multivariate analyses were used to explore the predictors of severe CI, and a corresponding nomogram was created to visualize the predictive model.

Results

LPA results suggested four distinct meaningful cognitive phenotypes in NMOSD: preserved cognition (n = 20, 30.3%), mild-attention (n = 21, 31.8%), mild-multidomain (n = 18, 27.3%), and severe-multidomain (n = 7, 10.6%). Patients with the last three phenotypes were perceived to have CI, which accounts for 67.6% of patients with NMOSD. Patients with NMOSD and worse cognitive function were older (p < 0.001) and had lower educational levels (p < 0.001), later clinical onset (p = 0.01), worse Expanded Disability Status Scale scores (p = 0.001), and poorer lower-limb motor function (Timed 25-Foot Walk, p = 0.029; 12-item Multiple Sclerosis Walking Scale [MSWS-12], p < 0.001). Deterioration of Nine-Hole Peg Test (odds ratio, OR: 1.115 [1, 1.243], p = 0.05) and MSWS-12 (OR: 1.069 [1.003, 1.139], p = 0.04) were the independent risk factors for severe cognitive dysfunction. Finally, a nomogram was built based on the entire cohort and the above factors to serve as a useful tool for clinicians to evaluate the risk of severe cognitive dysfunction.

Conclusions

We introduced a classification scheme for CI and highlighted that the deterioration of upper- and lower-limb motor disability potentially predicts cognitive phenotypes in NMOSD.

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.

Development and validation of a simple and practical method for differentiating MS from other neuroinflammatory disorders based on lesion distribution on brain MRI

There is an unmet need to develop practical methods for differentiating multiple sclerosis (MS) from other neuroinflammatory disorders using standard brain MRI. To develop a practical approach for differentiating MS from neuromyelitis optica spectrum disorder (NMOSD) and MOG antibody-associated disorder (MOGAD) with brain MRI, we first identified lesion locations in the brain that are suggestive of MS-associated demyelination ("MS Lesion Checklist") and compared frequencies of brain lesions in the "MS Lesion Checklist" locations in a development sample of patients (n = 82) with clinically definite MS, NMOSD, and MOGAD. Patients with MS were more likely than patients with non-MS to have lesions in 3 locations only: anterior temporal horn (p < 0.0001), periventricular ("Dawson's finger") (p < 0.0001), and cerebellar hemisphere (p = 0.02). These three lesion locations were used as predictor variables in a multivariable regression model for discriminating MS from non-MS. The model had area under the curve (AUC) of 0.853 (95% confidence interval: 0.76-0.945), sensitivity of 87.1%, and specificity of 72.5%. We then used an independent validation sample with equal representation of MS and NMOSD/MOGAD cases (n = 97) to validate our prediction model. In the validation sample, the model was 76.3% accurate in discriminating MS from non-MS. Our simple method for predicting MS versus NMOSD/MOGAD only requires a neuroradiologist or clinician to ascertain the presence of lesions in three locations on conventional MRI sequences. It can therefore be readily applied in the real-world setting for training and clinical practice.

Volumetric Brain Loss Correlates With a Relapsing MOGAD Disease Course

Background

Myelin oligodendrocyte glycoprotein antibody disorders (MOGAD) have evolved as a distinct group of inflammatory, demyelinating diseases of the CNS. MOGAD can present with a monophasic or relapsing disease course with distinct clinical manifestations.However, data on the disease course and disability outcomes of these patients are scarce. We aim to compare brain volumetric changes for MOGAD patients with different disease phenotypes and HCs.

Methods

Brain magnetic resonance imaging (MRI) scans and clinical data were obtained for 22 MOGAD patients and 22 HCs. Volumetric brain information was determined using volBrain and MDbrain platforms.

Results

We found decreased brain volume in MOGAD patients compared to HCs, as identified in volume of total brain, gray matter, white matter and deep gray matter (DGM) structures. In addition, we found significantly different volumetric changes between patients with relapsing and monophasic disease course, with significantly decreased volume of total brain and DGM, cerebellum and hippocampus in relapsing patients during the first year of diagnosis. A significant negative correlation was found between EDSS and volume of thalamus.

Conclusions

Brain MRI analyses revealed volumetric differences between MOGAD patients and HCs, and between patients with different disease phenotypes. Decreased gray matter volume during the first year of diagnosis, especially in the cerebrum and hippocampus of MOGAD patients was associated with relapsing disease course.

Multimodal magnetic resonance imaging quantification of gray matter alterations in relapsing-remitting multiple sclerosis and neuromyelitis optica spectrum disorder

Herein, we combined neurite orientation dispersion and density imaging (NODDI) and synthetic magnetic resonance imaging (SyMRI) to evaluate the spatial distribution and extent of gray matter (GM) microstructural alterations in patients with relapsing-remitting multiple sclerosis (RRMS) and neuromyelitis optica spectrum disorder (NMOSD). The NODDI (neurite density index [NDI], orientation dispersion index [ODI], and isotropic volume fraction [ISOVF]) and SyMRI (myelin volume fraction [MVF]) measures were compared between age- and sex-matched groups of 30 patients with RRMS (6 males and 24 females; mean age, 51.43 ± 8.02 years), 18 patients with anti-aquaporin-4 antibody-positive NMOSD (2 males and 16 females; mean age, 52.67 ± 16.07 years), and 19 healthy controls (6 males and 13 females; mean age, 51.47 ± 9.25 years) using GM-based spatial statistical analysis. Patients with RRMS showed reduced NDI and MVF and increased ODI and ISOVF, predominantly in the limbic and paralimbic regions, when compared with healthy controls, while only increases in ODI and ISOVF were observed when compared with NMOSD. Compared to NDI and MVF, the changes in ODI and ISOVF were observed more widely, including in the cerebellar cortex. These abnormalities were associated with disease progression and disability. In contrast, patients with NMOSD only showed reduced NDI mainly in the cerebellar, limbic, and paralimbic cortices when compared with healthy controls and patients with RRMS. Taken together, our study supports the notion that GM pathologies in RRMS are distinct from those of NMOSD. However, owing to the limitations of the study, the results should be cautiously interpreted.

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.

Dynamic topology analysis for spatial patterns of multifocal lesions on MRI

Quantitatively analysing the spatial patterns of multifocal lesions on clinical MRI is an important step towards a better understanding of the disease and for precision medicine, which is yet to be properly explored by feature engineering and deep learning methods. Network science addresses this issue by explicitly modeling the inter-lesion topology. However, the construction of the informative graph with optimal edge sparsity and quantification of community graph structures are the current challenges in network science. In this paper, we address these challenges with a novel Dynamic Topology Analysis framework on the basis of persistent homology, aiming to investigate the predictive values of global geometry and local clusters of multifocal lesions. Firstly, Dynamic Hierarchical Network is proposed to construct informative global and community-level topology over multi-scale networks from sparse to dense. Multi-scale global topology is constructed with a nested sequence of Rips complexes, from which a new K-simplex Filtration is designed to generate a higher-level topological abstraction for community identification based on the connectivity of k-simplices in the Rips Complex. Secondly, to quantify multi-scale community structures, we design a new Decomposed Community Persistence algorithm to track the dynamic evolution of communities, and then summarise the evolutionary communities incorporated with a customisable descriptor. The quantified community features are encapsulated with global geometric invariants for topological pattern analysis. The proposed framework was evaluated on both diagnostic differentiation and prognostic prediction for multiple sclerosis that is a typical multifocal disease, and achieved ROC_AUC 0.875 and 0.767, respectively, outperforming seven state-of-the-art persistent homology methods and the reported performance of six feature engineering and deep learning methods.

Deep grey matter injury in multiple sclerosis: a NAIMS consensus statement

Although multiple sclerosis has traditionally been considered a white matter disease, extensive research documents the presence and importance of grey matter injury including cortical and deep regions. The deep grey matter exhibits a broad range of pathology and is uniquely suited to study the mechanisms and clinical relevance of tissue injury in multiple sclerosis using magnetic resonance techniques. Deep grey matter injury has been associated with clinical and cognitive disability. Recently, MRI characterization of deep grey matter properties, such as thalamic volume, have been tested as potential clinical trial end points associated with neurodegenerative aspects of multiple sclerosis. Given this emerging area of interest and its potential clinical trial relevance, the North American Imaging in Multiple Sclerosis (NAIMS) Cooperative held a workshop and reached consensus on imaging topics related to deep grey matter. Herein, we review current knowledge regarding deep grey matter injury in multiple sclerosis from an imaging perspective, including insights from histopathology, image acquisition and post-processing for deep grey matter. We discuss the clinical relevance of deep grey matter injury and specific regions of interest within the deep grey matter. We highlight unanswered questions and propose future directions, with the aim of focusing research priorities towards better methods, analysis, and interpretation of results.

Application of deep-learning to the seronegative side of the NMO spectrum

OBJECTIVES

To apply a deep-learning algorithm to brain MRIs of seronegative patients with neuromyelitis optica spectrum disorders (NMOSD) and NMOSD-like manifestations and assess whether their structural features are similar to aquaporin-4-seropositive NMOSD or multiple sclerosis (MS) patients.

PATIENTS AND METHODS

We analyzed 228 T2- and T1-weighted brain MRIs acquired from aquaporin-4-seropositive NMOSD (n = 85), MS (n = 95), aquaporin-4-seronegative NMOSD [n = 11, three with anti-myelin oligodendrocyte glycoprotein antibodies (MOG)], and aquaporin-4-seronegative patients with NMOSD-like manifestations (idiopathic recurrent optic neuritis and myelitis, n = 37), who were recruited from February 2010 to December 2019. Seventy-three percent of aquaporin-4-seronegative patients with NMOSD-like manifestations also had a clinical follow-up (median duration of 4 years). The deep-learning neural network architecture was based on four 3D convolutional layers. It was trained and validated on MRI scans of aquaporin-4-seropositive NMOSD and MS patients and was then applied to aquaporin-4-seronegative NMOSD and NMOSD-like manifestations. Assignment of unclassified aquaporin-4-seronegative patients was compared with their clinical follow-up.

RESULTS

The final algorithm differentiated aquaporin-4-seropositive NMOSD and MS patients with an accuracy of 0.95. All aquaporin-4-seronegative NMOSD and 36/37 aquaporin-4-seronegative patients with NMOSD-like manifestations were classified as NMOSD. Anti-MOG patients had a similar probability of being NMOSD or MS. At clinical follow-up, one unclassified aquaporin-4-seronegative patient evolved to MS, three developed NMOSD, and the others did not change phenotype.

CONCLUSIONS

Our findings support the inclusion of aquaporin4-seronegative patients into NMOSD and suggest a possible expansion to aquaporin-4-seronegative unclassified patients with NMOSD-like manifestations. Anti-MOG patients are likely to have intermediate brain features between NMOSD and MS.

Contrasting the brain imaging features of MOG-antibody disease, with AQP4-antibody NMOSD and multiple sclerosis

Background:

Identifying magnetic resonance imaging (MRI) markers in myelin-oligodendrocytes-glycoprotein antibody-associated disease (MOGAD), neuromyelitis optica spectrum disorder-aquaporin-4 positive (NMOSD-AQP4) and multiple sclerosis (MS) is essential for establishing objective outcome measures.

Objectives:

To quantify imaging patterns of central nervous system (CNS) damage in MOGAD during the remission stage, and to compare it with NMOSD-AQP4 and MS.

Methods:

20 MOGAD, 19 NMOSD-AQP4, 18 MS in remission with brain or spinal cord involvement and 18 healthy controls (HC) were recruited. Volumetrics, lesions and cortical lesions, diffusion-imaging measures, were analysed.

Results:

Deep grey matter volumes were lower in MOGAD (p = 0.02) and MS (p = 0.0001), compared to HC and were strongly correlated with current lesion volume (MOGAD R = −0.93, p < 0.001, MS R = −0.65, p = 0.0034). Cortical/juxtacortical lesions were seen in a minority of MOGAD, in a majority of MS and in none of NMOSD-AQP4. Non-lesional tissue fractional anisotropy (FA) was only reduced in MS (p = 0.01), although focal reductions were noted in NMOSD-AQP4, reflecting mainly optic nerve and corticospinal tract pathways.

Conclusion:

MOGAD patients are left with grey matter damage, and this may be related to persistent white matter lesions. NMOSD-AQP4 patients showed a relative sparing of deep grey matter volumes, but reduced non-lesional tissue FA. Observations from our study can be used to identify new markers of damage for future multicentre studies.

Differentiation between multiple sclerosis and neuromyelitis optica spectrum disorders by multiparametric quantitative MRI using convolutional neural network

Multiple sclerosis and neuromyelitis optica spectrum disorders are both neuroinflammatory diseases and have overlapping clinical manifestations. We developed a convolutional neural network model that differentiates between the two based on magnetic resonance imaging data. Thirty-five patients with relapsing-remitting multiple sclerosis and eighteen age-, sex-, disease duration-, and Expanded Disease Status Scale-matched patients with anti-aquaporin-4 antibody-positive neuromyelitis optica spectrum disorders were included in this study. All patients were scanned on a 3-T scanner using a multi-dynamic multi-echo sequence that simultaneously measures R1 and R2 relaxation rates and proton density. R1, R2, and proton density maps were analyzed using our convolutional neural network model. To avoid overfitting on a small dataset, we aimed to separate features of images into those specific to an image and those common to the group, based on SqueezeNet. We used only common features for classification. Leave-one-out cross validation was performed to evaluate the performance of the model. The area under the receiver operating characteristic curve of the developed convolutional neural network model for differentiating between the two disorders was 0.859. The sensitivity to multiple sclerosis and neuromyelitis optica spectrum disorders, and accuracy were 80.0%, 83.3%, and 81.1%, respectively. In conclusion, we developed a convolutional neural network model that differentiates between multiple sclerosis and neuromyelitis optica spectrum disorders, and which is designed to avoid overfitting on small training datasets. Our proposed algorithm may facilitate a differential diagnosis of these diseases in clinical practice.

3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations

Background

Magnetic resonance imaging (MRI) has a wide range of applications in medical imaging. Recently, studies based on deep learning algorithms have demonstrated powerful processing capabilities for medical imaging data. Previous studies have mostly focused on common diseases that usually have large scales of datasets and centralized the lesions in the brain. In this paper, we used deep learning models to process MRI images to differentiate the rare neuromyelitis optical spectrum disorder (NMOSD) from multiple sclerosis (MS) automatically, which are characterized by scattered and overlapping lesions.

Methods

We proposed a novel model structure to capture 3D MRI images’ essential information and converted them into lower dimensions. To empirically prove the efficiency of our model, firstly, we used a conventional 3-dimensional (3D) model to classify the T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) images and proved that the traditional 3D convolutional neural network (CNN) models lack the learning capacity to distinguish between NMOSD and MS. Then, we compressed the 3D T2-FLAIR images by a two-view compression block to apply two different depths (18 and 34 layers) of 2D models for disease diagnosis and also applied transfer learning by pre-training our model on ImageNet dataset.

Results

We found that our models possess superior performance when our models were pre-trained on ImageNet dataset, in which the models’ average accuracies of 34 layers model and 18 layers model were 0.75 and 0.725, sensitivities were 0.707 and 0.708, and specificities were 0.759 and 0.719, respectively. Meanwhile, the traditional 3D CNN models lacked the learning capacity to distinguish between NMOSD and MS.

Conclusion

The novel CNN model we proposed could automatically differentiate the rare NMOSD from MS, especially, our model showed better performance than traditional3D CNN models. It indicated that our 3D compressed CNN models are applicable in handling diseases with small-scale datasets and possess overlapping and scattered lesions.

Deep Learning-Based Method to Differentiate Neuromyelitis Optica Spectrum Disorder From Multiple Sclerosis

Background: Differentiating neuromyelitis optica spectrum disorder (NMOSD) from multiple sclerosis (MS) is crucial in the field of diagnostics because, despite their similarities, the treatments for these two diseases are substantially different, and disease-modifying treatments for MS can worsen NMOSD. As brain magnetic resonance imaging (MRI) is an important tool to distinguish the two diseases, extensive research has been conducted to identify the defining characteristics of MRI images corresponding to these two diseases. However, the application of such research in clinical practice is still limited. In this study, we investigate the applicability of a deep learning-based algorithm for differentiating NMOSD from MS.

Methods: In this study, we included 338 participants (213 patients with MS, 125 patients with NMOSD) who visited the Asan medical center between February 2009 and February 2020. A 3D convolutional neural network, which is a deep learning-based algorithm, was trained using fluid-attenuated inversion recovery images and clinical information of the participants. The performance of the final model in differentiating NMOSD from MS was evaluated and compared with that of two neurologists.

Results: The deep learning-based model exhibited an area under the receiver operating characteristic curve of 0.82 (95% CI, 0.75–0.89). It differentiated NMOSD from MS with an accuracy of 71.1% (sensitivity = 87.8%, specificity = 61.6%), which is comparable to that exhibited by the neurologists. The intra-rater reliability of the two neurologists was moderate (κ = 0.47, 0.50), which was in contrast with the consistent classification of the deep learning-based model.

Conclusion: The proposed model was verified to be capable of differentiating NMOSD from MS with accuracy comparable to that of neurologists, exhibiting the advantage of consistent classification. As a result, it can aid differential diagnosis between two important central nervous system inflammatory diseases in clinical practice.

Cortical Thinning and Ventricle Enlargement in Neuromyelitis Optica Spectrum Disorders

Background: In neuromyelitis optica spectrum disorders (NMOSDs), inflammation is not the sole driver of accumulation of disability; neurodegeneration is another important pathological process. We aim to explore different patterns of cortical atrophy and ventricular enlargement in NMOSD.

Methods: We retrospectively analyzed a cohort of 230 subjects, comprising 55 healthy controls (HCs), 85 multiple sclerosis (MS), and 90 NMOSD patients from Tianjin Medical University General Hospital and Beijing Tiantan Hospital. Different compartments of the brain (total gray, cortex, subcortex gray, and ventricle volume) were evaluated with the FreeSurfer. Multiple linear regressions were adopted to explore associations between cortex volume and predict factors.

Results: Compared with HCs, NMOSD, and MS displayed an enlarged lateral and third ventricle (p < 0.001), whereas expansion of the fourth ventricle was observed in MS rather than NMOSD (p = 0.321). MS and NMOSD patients exhibited cortical thinning in comparison with HCs. However, pronounced cortical atrophy were only significant in pre-cuneus, parahippocampal, and lateral occipital lobe between MS and NMOSD. Patients with NMOSD had decreased local gyrification index in orbitofrontal and pre-cuneus lobe, and reduced pial surface area. Linear regression analysis revealed cortex volume were predicated by advanced age (standardized β = −0.404, p = 0.001) as well as prolonged disease history (standardized β = −0.311, p = 0.006).

Conclusion: NMOSD exhibited global cortex atrophy with enlarged lateral and third ventricles. Moreover, cortex volume is associated with age and disease duration.

AI in Radiology: Where are we today in Multiple Sclerosis Imaging?

Background MR imaging is an essential component in managing patients with Multiple sclerosis (MS). This holds true for the initial diagnosis as well as for assessing the clinical course of MS. In recent years, a growing number of computer tools were developed to analyze imaging data in MS. This review gives an overview of the most important applications with special emphasis on artificial intelligence (AI).

Methods Relevant studies were identified through a literature search in recognized databases, and through parsing the references in studies found this way. Literature published as of November 2019 was included with a special focus on recent studies from 2018 and 2019.

Results There are a number of studies which focus on optimizing lesion visualization and lesion segmentation. Some of these studies accomplished these tasks with high accuracy, enabling a reproducible quantitative analysis of lesion loads. Some studies took a radiomics approach and aimed at predicting clinical endpoints such as the conversion from a clinically isolated syndrome to definite MS. Moreover, recent studies investigated synthetic imaging, i. e. imaging data that is not measured during an MR scan but generated by a computer algorithm to optimize the contrast between MS lesions and brain parenchyma.

Conclusion Computer-based image analysis and AI are hot topics in imaging MS. Some applications are ready for use in clinical routine. A major challenge for the future is to improve prediction of expected disease courses and thereby helping to find optimal treatment decisions on an individual level. With technical improvements, more questions arise about the integration of new tools into the radiological workflow.

Key Points: 

Citation Format

The latest diagnostic criteria and treatment options for neuromyelitis optica

Neuromyelitis optica, also known as Devic disease, is an autoimmune disorder that affects the spinal cord and optic nerve. This atypical demyelinating syndrome can be difficult to diagnose and responds poorly to treatments that are used for multiple sclerosis, a similar demyelinating disease. This article discusses the epidemiology, pathophysiology, clinical presentation, latest diagnostic criteria, and treatment options for neuromyelitis optica and neuromyelitis spectrum disorders.

Differentiate aquaporin-4 antibody negative neuromyelitis optica spectrum disorders from multiple sclerosis by multimodal advanced MRI techniques

BACKGROUND

It is clinically essential to distinguish aquaporin-4 antibody (AQP4-Ab) negative neuromyelitis optica spectrum disorders (NMOSD) and multiple sclerosis (MS) because of different therapeutic strategies. Since clinical and lesion features may not allow the distinction, we aimed to identify advanced imaging features that could improve the distinction between two disorders.

METHODS

Multimodal imaging measures included fractional anisotropy, mean, axial, radial diffusivity (MD, AD, RD) and kurtosis (MK, AK, RK) from diffusion kurtosis imaging; functional connectivity strength (FCS) and density, regional homogeneity, amplitude of low frequency fluctuations from resting-state functional MRI; gray matter volume from structural MRI; and cerebral blood flow from arterial spin labeling imaging. Voxel-wise comparisons were performed to identify inter-group differences in imaging measures, and the performance of differentiating these two disorders was estimated by receiver operating characteristic curves.

RESULTS

Compared to MS, patients with AQP4-Ab negative NMOSD showed decreased MD and AD but increased MK and AK in white matter regions; and reduced FCS in the occipital cortex (P < 0.05, FWE corrected). The joint-use of these five imaging measures distinguished the two disorders with an accuracy of 94% (P < 0.001, 95%CI = 0.84-0.98). Other imaging measures showed no significant differences between the two patient groups.

CONCLUSIONS

The study showed less white matter damage and a more severe functional disconnection of the occipital cortex in patients with AQP4-Ab negative NMOSD compared to MS. The combined use of diffusion and functional connectivity could facilitate a better distinction between NMO and MS with seronegative AQP4-Ab in clinical management.

Prediction of pulmonary pressure after Glenn shunts by computed tomography-based machine learning models

OBJECTIVES

This study aimed to develop non-invasive machine learning classifiers for predicting post-Glenn shunt patients with low and high risks of a mean pulmonary arterial pressure (mPAP) > 15 mmHg based on preoperative cardiac computed tomography (CT).

METHODS

This retrospective study included 96 patients with functional single ventricle who underwent a bidirectional Glenn procedure between November 1, 2009, and July, 31, 2017. All patients underwent post-procedure CT, followed by cardiac catheterization. Overall, 23 morphologic parameters were manually extracted from cardiac CT images for each patient. The Mann-Whitney U or chi-square test was applied to select the most significant predictors. Six machine learning algorithms including logistic regression, Naive Bayes, random forest (RF), linear discriminant analysis, support vector machine, and K-nearest neighbor were used for modeling. These algorithms were independently trained on 100 train-validation random splits with a 3:1 ratio. Their average performance was evaluated by area under the curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

Seven CT morphologic parameters were selected for modeling. RF obtained the best performance, with mean AUC of 0.840 (confidence interval [CI] 0.832-0.850) and 0.787 (95% CI 0.780-0.794); sensitivity of 0.815 (95% CI 0.797-0.833) and 0.778 (95% CI 0.767-0.788), specificity of 0.766 (95% CI 0.748-0.785) and 0.746 (95% CI 0.735-0.757); and accuracy of 0.782 (95% CI 0.771-0.793) and 0.756 (95% CI 0.748-0.764) in the training and validation cohorts, respectively.

CONCLUSIONS

The CT-based RF model demonstrates a good performance in the prediction of mPAP, which may reduce the need for right heart catheterization in post-Glenn shunt patients with suspected mPAP > 15 mmHg.

KEY POINTS

• Twenty-three candidate descriptors were manually extracted from cardiac computed tomography images, and seven of them were selected for subsequent modeling. • The random forest model presents the best predictive performance for pulmonary pressure among all methods. • The computed tomography-based machine learning model could predict post-Glenn shunt pulmonary pressure non-invasively.

Subcortical structural abnormalities in female neuromyelitis optica patients with neuropathic pain

Neuromyelitis optica (NMO) is a disease characterised by severe relapses of optic neuritis and longitudinally extensive transverse myelitis and it has a strong female predilection. Pain is one of the most typical symptom in NMO. However, few studies have been conducted to examine the neuropathic pain mechanism of NMO patients or gender-specific effects using magnetic resonance imaging technique. A total of 38 female patients with NMO, 28 with pain (NMOWP) and 10 without pain (NMOWoP), were classified using the Brief Pain Inventory (BPI); 22 healthy females were also recruited. We used the FSL Image Registration and Segmentation Toolbox (FIRST) for subcortical region volumes quantifications, and voxel-based morphometry analysis for cortical gray matter (GM) volume, to examine the brain morphology in NMOWP patients. In addition, correlation test between structural measurements of NMO patients and clinical indexes was also performed. The results showed: 1) no significant differences in cortical GM density between the NMOWP and NMOWoP groups; 2) significantly smaller hippocampus and pallidum volumes in the NMOWP group compared with the NMOWoP group; 3) significant negative correlation between the average BPI and volumes of the accumbens nucleus and thalamus in NMO patients. These results revealed that structural abnormality exists in NMO female patients who have pain, with significant implications for our understanding of the brain morphology in NMO patients with pain.

Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation

Machine learning-based imaging diagnostics has recently reached or even surpassed the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on 3D convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS), the most widespread autoimmune neuroinflammatory disease. MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients (n = 76) and healthy controls (n = 71). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of CNN models transparent, which could serve to justify classification decisions for clinical review, verify diagnosis-relevant features and potentially gather new disease knowledge.

Paediatric multiple sclerosis: a new era in diagnosis and treatment

Multiple sclerosis is a chronic immune-mediated demyelinating disease of the central nervous system. The diagnosis of multiple sclerosis in children, as in adults, requires evidence of dissemination of inflammatory activity in more than one location in the central nervous system (dissemination in space) and recurrent disease over time (dissemination in time). The identification of myelin oligodendrocyte glycoprotein antibodies (MOG-Ab) and aquaporin-A antibodies (AQP4-Ab), and the subsequent discovery of their pathogenic mechanisms, have led to a shift in the classification of relapsing demyelinating syndromes. This is reflected in the 2017 revised criteria for the diagnosis of multiple sclerosis, which emphasizes the exclusion of multiple sclerosis mimics and aims to enable earlier diagnosis and thus treatment initiation. The long-term efficacy of individual therapies initiated in children with multiple sclerosis is hard to evaluate, owing to the small numbers of patients who have the disease, the relatively high number of patients who switch therapy, and the need for long follow-up studies. Nevertheless, an improvement in prognosis with a globally reduced annual relapse rate in children with multiple sclerosis is now observed compared with the pretreatment era, indicating a possible long-term effect of therapies. Given the higher relapse rate in children compared with adults, and the impact multiple sclerosis has on cognition in the developing brain, there is a question whether rapid escalation or potent agents should be used in children, while the short- and long-term safety profiles of these drugs are being established. With the results of the first randomized controlled trial of fingolimod versus interferon-β1a in paediatric multiple sclerosis published in 2018 and several clinical trials underway, there is hope for further progress in the field of paediatric multiple sclerosis. WHAT THIS PAPER ADDS: Early and accurate diagnosis of multiple sclerosis is crucial. The discovery of antibody-mediated demyelination has changed the diagnosis and management of relapsing demyelination syndromes. Traditional escalation therapy is being challenged by induction therapy.

Advances in brain imaging in multiple sclerosis

Brain imaging is increasingly used to support clinicians in diagnosing multiple sclerosis (MS) and monitoring its progression. However, the role of magnetic resonance imaging (MRI) in MS goes far beyond its clinical application. Indeed, advanced imaging techniques have helped to detect different components of MS pathogenesis in vivo, which is now considered a heterogeneous process characterized by widespread damage of the central nervous system, rather than multifocal demyelination of white matter. Recently, MRI biomarkers more sensitive to disease activity than clinical disability outcome measures, have been used to monitor response to anti-inflammatory agents in patients with relapsing-remitting MS. Similarly, MRI markers of neurodegeneration exhibit the potential as primary and secondary outcomes in clinical trials for progressive phenotypes. This review will summarize recent advances in brain neuroimaging in MS from the research setting to clinical applications.

Predicting prognosis of endometrioid endometrial adenocarcinoma on the basis of gene expression and clinical features using Random Forest

Traditional clinical features are not sufficient to accurately judge the prognosis of endometrioid endometrial adenocarcinoma (EEA). Molecular biological characteristics and traditional clinical features are particularly important in the prognosis of EEA. The aim of the present study was to establish a predictive model that considers genes and clinical features for the prognosis of EEA. The clinical and RNA sequencing expression data of EEA were derived from samples from The Cancer Genome Atlas (TCGA) and Peking University People's Hospital (PKUPH; Beijing, China). Samples from TCGA were used as the training set, and samples from the PKUPH were used as the testing set. Variable selection using Random Forests (VSURF) was used to select the genes and clinical features on the basis of TCGA samples. The RF classification method was used to establish the prediction model. Kaplan-Meier curves were tested with the log-rank test. The results from this study demonstrated that on the basis of TCGA samples, 11 genes and the grade were selected as the input features. In the training set, the out-of-bag (OOB) error of RF model-1, which was established using the '11 genes', was 0.15; the OOB error of RF model-2, which was established using the 'grade', was 0.39; and the OOB error of RF model-3, established using the '11 genes and grade', was 0.15. In the testing set, the classification accuracy of RF model-1, model-2 and model-3 was 71.43, 66.67 and 80.95%, respectively. In conclusion, to the best of our knowledge, the VSURF was used to select features relevant to EEA prognosis, and an EEA predictive model combining genes and traditional features was established for the first time in the present study. The prediction accuracy of the RF model on the basis of the 11 genes and grade was markedly higher than that of the RF models established by either the 11 genes or grade alone.

Misdiagnosis of multiple sclerosis: Impact of the 2017 McDonald criteria on clinical practice

Misdiagnosis of multiple sclerosis (MS) (the incorrect assignment of a diagnosis of MS) remains a problem in contemporary clinical practice. Studies indicate that misdiagnosed patients are often exposed to prolonged unnecessary health care risks and morbidity. The recently published 2017 revision of the McDonald criteria for the diagnosis of MS provides an opportunity to consider the effect of these revisions on the problem of MS misdiagnosis. The 2017 McDonald criteria include several new recommendations to reduce potential for misdiagnoses. The criteria should be used for the types of patients in which validation studies were performed, specifically those patients who present with typical demyelinating syndromes. MRI lesion characteristics were defined for which McDonald criteria would be expected to perform with accuracy. However, 2017 revisions, which now include assessment for cortical lesions, and the inclusion of symptomatic lesions and positive oligoclonal bands for the fulfillment of diagnostic criteria, may have the potential to lead to misdiagnosis of MS if not applied appropriately. While the 2017 McDonald criteria integrate issues relating to MS misdiagnosis and incorporate specific recommendations for its prevention more prominently than prior criteria, the interpretation of clinical and radiologic assessments upon which these criteria depend will continue to allow misdiagnoses. In patients with atypical clinical presentations, the revised McDonald criteria may not be readily applied. In those situations, further evaluation or monitoring rather than immediate diagnosis of MS is prudent.

Characterization of relapsing-remitting multiple sclerosis patients using support vector machine classifications of functional and diffusion MRI data

Multiple Sclerosis patients' clinical symptoms do not correlate strongly with structural assessment done with traditional magnetic resonance images. However, its diagnosis and evaluation of the disease's progression are based on a combination of this imaging analysis complemented with clinical examination. Therefore, other biomarkers are necessary to better understand the disease. In this paper, we capitalize on machine learning techniques to classify relapsing-remitting multiple sclerosis patients and healthy volunteers based on machine learning techniques, and to identify relevant brain areas and connectivity measures for characterizing patients. To this end, we acquired magnetic resonance imaging data from relapsing-remitting multiple sclerosis patients and healthy subjects. Fractional anisotropy maps, structural and functional connectivity were extracted from the scans. Each of them were used as separate input features to construct support vector machine classifiers. A fourth input feature was created by combining structural and functional connectivity. Patients were divided in two groups according to their degree of disability and, together with the control group, three group pairs were formed for comparison. Twelve separate classifiers were built from the combination of these four input features and three group pairs. The classifiers were able to distinguish between patients and healthy subjects, reaching accuracy levels as high as 89% ± 2%. In contrast, the performance was noticeably lower when comparing the two groups of patients with different levels of disability, reaching levels below 63% ± 5%. The brain regions that contributed the most to the classification were the right occipital, left frontal orbital, medial frontal cortices and lingual gyrus. The developed classifiers based on MRI data were able to distinguish multiple sclerosis patients and healthy subjects reliably. Moreover, the resulting classification models identified brain regions, and functional and structural connections relevant for better understanding of the disease.

The Role of Advanced Magnetic Resonance Imaging Techniques in Multiple Sclerosis Clinical Trials

Magnetic resonance imaging has been crucial in the development of anti-inflammatory disease-modifying treatments. The current landscape of multiple sclerosis clinical trials is currently expanding to include testing not only of anti-inflammatory agents, but also neuroprotective, remyelinating, neuromodulating, and restorative therapies. This is especially true of therapies targeting progressive forms of the disease where neurodegeneration is a prominent feature. Imaging techniques of the brain and spinal cord have rapidly evolved in the last decade to permit in vivo characterization of tissue microstructural changes, connectivity, metabolic changes, neuronal loss, glial activity, and demyelination. Advanced magnetic resonance imaging techniques hold significant promise for accelerating the development of different treatment modalities targeting a variety of pathways in MS.

Multimodal characterization of gray matter alterations in neuromyelitis optica

OBJECTIVE

To investigate structural and functional alterations of gray matter (GM) and examine their clinical relevance in neuromyelitis optica (NMO) using multimodal magnetic resonance imaging (MRI) techniques.

METHODS

A total of 35 NMO and 36 healthy controls (HC) were recruited in this study. Cortical lesions were investigated by double inversion recovery technique. Five voxel-wise MRI measurements were obtained for each participant in the GM including gray matter volume (GMV), fractional anisotropy (FA), mean diffusivity (MD), amplitude of low-frequency fluctuation (ALFF), and weighted functional connectivity strength (wFCS). Between-group differences, cross-modality relationships, and MRI-clinical correlations were examined.

RESULTS

No cortical lesions were found in NMO. Compared to HC, NMO patients exhibited significantly decreased GMV in deep GM and cortical regions involving visual function and cognition. Diffusion GM abnormalities were widespread in the patients. Decreased ALFF and wFCS were observed in the patients in sensorimotor, visual, cognition, and cerebellar sites. GM structural alterations were correlated with cognitive but not physical disability scores of the patients.

CONCLUSION

Despite the lack of focal cortical lesions, patients with NMO exhibit both structural and functional alterations of GM in cerebrum and cerebellum that predominantly involve deep GM, visual, motor, and cognitive regions. GM alterations are associated with cognitive impairment but not physical disability.

MRI evaluation of thalamic volume differentiates MS from common mimics

Objective:

To determine whether MRI evaluation of thalamic volume differentiates MS from other disorders that cause MRI white matter abnormalities.

Methods:

There were 40 study participants: 10 participants with MS without additional comorbidities for white matter abnormalities (MS − c); 10 participants with MS with additional comorbidities for white matter abnormalities (MS + c); 10 participants with migraine, MRI white matter abnormalities, and no additional comorbidities for white matter abnormalities (Mig − c); and 10 participants previously incorrectly diagnosed with MS (Misdx). T1-magnetization-prepared rapid gradient-echo and T2-weighted three-dimensional fluid attenuation inversion recovery sequences were acquired on a Phillips Achieva d-Stream 3T MRI, and scans were randomly ordered and de-identified for a blinded reviewer who performed MRI segmentation using LesionTOADS.

Results:

Mean normalized thalamic volume differed among the 4 cohorts (analysis of variance, p = 0.005) and was smaller in the 20 MS participants compared with the 20 non-MS participants (p < 0.001), smaller in MS − c compared with Mig − c (p = 0.03), and smaller in MS + c compared with Misdx (p = 0.006). The sensitivity and specificity were both 0.75 for diagnosis of MS with a thalamic volume <0.0077.

Conclusions:

MRI volumetric evaluation of the thalamus, but not other deep gray-matter structures, differentiated MS from other diseases that cause white matter abnormalities and are often mistaken for MS. Evaluation for thalamic atrophy may improve accuracy for diagnosis of MS as an adjunct to additional radiologic criteria. Thalamic volumetric assessment by MRI in larger cohorts of patients undergoing evaluation for MS is needed, along with the development of automated and easily applied volumetric assessment tools for future clinical application.

Classification of evidence:

This study provides Class III evidence that MRI evaluation of thalamic volume differentiates MS from other diseases that cause white matter abnormalities.