Quantitative susceptibility maps from magnetic resonance images can provide both prognostic and diagnostic information in multiple sclerosis, a neurodegenerative disease characterized by the formation of lesions in white matter brain tissue. In particular, susceptibility maps provide adequate contrast to distinguish between "rim" lesions, surrounded by deposited paramagnetic iron, and "non-rim" lesion types. These paramagnetic rim lesions (PRLs) are an emerging biomarker in multiple sclerosis. Much effort has been devoted to both detection and segmentation of such lesions to monitor longitudinal change. As paramagnetic rim lesions are rare, addressing this problem requires confronting the class imbalance between rim and non-rim lesions. We produce synthetic quantitative susceptibility maps of paramagnetic rim lesions and show that inclusion of such synthetic data improves classifier performance and provide a multi-channel extension to generate accompanying contrasts and probabilistic segmentation maps. We exploit the projection capability of our trained generative network to demonstrate a novel denoising approach that allows us to train on ambiguous rim cases and substantially incr
In this paper we first establish several integral identities. These integrals are of the form \[\int_0^1 x^{an+b} f(x)\,dx\quad (a\in\{1,2\},\ b\in\{-1,-2\})\] where $f(x)$ is a single-variable multiple polylogarithm function or $r$-variable multiple polylogarithm function or Kaneko--Tsumura A-function (this is a single-variable multiple polylogarithm function of level two). We find that these integrals can be expressed in terms of multiple zeta (star) values and their related variants (multiple $t$-values, multiple $T$-values, multiple $S$-values etc.), and multiple harmonic (star) sums and their related variants (multiple $T$-harmonic sums, multiple $S$-harmonic sums etc.). Using these integral identities, we prove many explicit evaluations of Kaneko--Yamamoto multiple zeta values and their related variants. Further, we derive some relations involving multiple zeta (star) values and their related variants.
Background: Gait and balance impairment can profoundly impact people with multiple sclerosis (PwMS). Objectives: To evaluate the analytical and clinical validity of the U-Turn Test (UTT), a smartphone-based assessment of dynamic balance in PwMS. Methods: The GaitLab study (ISRCTN15993728) enrolled adult PwMS (EDSS 0.0-6.5). PwMS performed the UTT in a gait laboratory (supervised) using 6 smartphones at different wear locations and daily during a two-week remote period (unsupervised) using one smartphone (belt front). Median turn speed was computed per UTT. In the supervised setting, turn detection accuracy of smartphones was compared to motion capture (mocap) via F1 scores. Agreement between smartphone- and mocap-derived turn speed was assessed by Bland-Altman and ICC(3,1). In the unsupervised setting, test-retest reliability (ICC[2,1]) and correlations with Timed 25-Foot Walk (T25FW), EDSS, Ambulation Score, 12-item Multiple Sclerosis Walking Scale (MSWS-12), and Activities-specific Balance Confidence scale (ABC) were evaluated. Results: Ninety-six PwMS were included. Turn speed was comparable across supervised (1.44 rad/s) and unsupervised settings (1.47 rad/s). In the supervised
Literature on machine learning for multiple sclerosis has primarily focused on the use of neuroimaging data such as magnetic resonance imaging and clinical laboratory tests for disease identification. However, studies have shown that these modalities are not consistent with disease activity such as symptoms or disease progression. Furthermore, the cost of collecting data from these modalities is high, leading to scarce evaluations. In this work, we used multi-dimensional, affordable, physical and smartphone-based performance outcome measures (POM) in conjunction with demographic data to predict multiple sclerosis disease progression. We performed a rigorous benchmarking exercise on two datasets and present results across 13 clinically actionable prediction endpoints and 6 machine learning models. To the best of our knowledge, our results are the first to show that it is possible to predict disease progression using POMs and demographic data in the context of both clinical trials and smartphone-base studies by using two datasets. Moreover, we investigate our models to understand the impact of different POMs and demographics on model performance through feature ablation studies. We a
Quantifying the complex/multifractal organization of the brain signals is crucial to fully understanding the brain processes and structure. In this contribution, we performed the multifractal analysis of the electroencephalographic (EEG) data obtained from a controlled multiple sclerosis (MS) study, focusing on the correlation between the degree of multifractality, disease duration, and disability level. Our results reveal a significant correspondence between the complexity of the time series and multiple sclerosis development, quantified respectively by scaling exponents and the Expanded Disability Status Scale (EDSS). Namely, for some brain regions, a well-developed multifractality and little persistence of the time series were identified in patients with a high level of disability, whereas the control group and patients with low EDSS were characterised by persistence and monofractality of the signals. The analysis of the cross-correlations between EEG signals supported these results, with the most significant differences identified for patients with EDSS $> 1$ and the combined group of patients with EDSS $\leq 1$ and controls. No association between the multifractality and di
This report summarizes the outcomes of the ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation (MSLesSeg). The competition aimed to develop methods capable of automatically segmenting multiple sclerosis lesions in MRI scans. Participants were provided with a novel annotated dataset comprising a heterogeneous cohort of MS patients, featuring both baseline and follow-up MRI scans acquired at different hospitals. MSLesSeg focuses on developing algorithms that can independently segment multiple sclerosis lesions of an unexamined cohort of patients. This segmentation approach aims to overcome current benchmarks by eliminating user interaction and ensuring robust lesion detection at different timepoints, encouraging innovation and promoting methodological advances.
In this study we investigate the Percolation Hypothesis for Multiple Sclerosis Progression. The methodology relies on cross-reference analysis centered around a question: What is the evidence for a Percolation/phase-transition hypothesis in Multiple Sclerosis (MS), especially the idea that the RRMS dynamic balance can abruptly break akin to crossing a percolation threshold into SPMS? We identify theoretical models invoking percolation/critical thresholds, network/connectome studies assessing percolation robustness or threshold-like behavior, clinical markers showing thresholds or early-warning signals, and counter-evidence arguing for gradual/continuum transitions.
Background: An early diagnosis together with an accurate disease progression monitoring of multiple sclerosis is an important component of successful disease management. Prior studies have established that multiple sclerosis is correlated with speech discrepancies. Early research using objective acoustic measurements has discovered measurable dysarthria. Objective: To determine the potential clinical utility of machine learning and deep learning/AI approaches for the aiding of diagnosis, biomarker extraction and progression monitoring of multiple sclerosis using speech recordings. Methods: A corpus of 65 MS-positive and 66 healthy individuals reading the same text aloud was used for targeted acoustic feature extraction utilizing automatic phoneme segmentation. A series of binary classification models was trained, tuned, and evaluated regarding their Accuracy and area-under-curve. Results: The Random Forest model performed best, achieving an Accuracy of 0.82 on the validation dataset and an area-under-curve of 0.76 across 5 k-fold cycles on the training dataset. 5 out of 7 acoustic features were statistically significant. Conclusion: Machine learning and artificial intelligence in a
In this paper, a class of reaction-diffusion equations for Multiple Sclerosis is presented. These models are derived by means of a diffusive limit starting from a proper kinetic description, taking account of the underlying microscopic interactions among cells. At the macroscopic level, we discuss the necessary conditions for Turing instability phenomena and the formation of two-dimensional patterns, whose shape and stability are investigated by means of a weakly nonlinear analysis. Some numerical simulations, confirming and extending theoretical results, are proposed for a specific scenario.
Prognosis on the occurrence of relapses in individuals with Relapsing-Remitting Multiple Sclerosis (RRMS), the most common subtype of Multiple Sclerosis (MS), could support individualized decisions and disease management and could be helpful for efficiently selecting patients in future randomized clinical trials. There are only three previously published prognostic models on this, all of them with important methodological shortcomings. We aim to present the development, internal validation, and evaluation of the potential clinical benefit of a prognostic model for relapses for individuals with RRMS using real world data. We followed seven steps to develop and validate the prognostic model. Finally, we evaluated the potential clinical benefit of the developed prognostic model using decision curve analysis. We selected eight baseline prognostic factors: age, sex, prior MS treatment, months since last relapse, disease duration, number of prior relapses, expanded disability status scale (EDSS), and gadolinium enhanced lesions. We also developed a web application where the personalized probabilities to relapse within two years are calculated automatically. The optimism-corrected c-stati
Objective: Identifying disability-related brain changes is important for multiple sclerosis (MS) patients. Currently, there is no clear understanding about which pathological features drive disability in single MS patients. In this work, we propose a novel comprehensive approach, GAMER-MRIL, leveraging whole-brain quantitative MRI (qMRI), convolutional neural network (CNN), and an interpretability method from classifying MS patients with severe disability to investigating relevant pathological brain changes. Methods: One-hundred-sixty-six MS patients underwent 3T MRI acquisitions. qMRI informative of microstructural brain properties was reconstructed, including quantitative T1 (qT1), myelin water fraction (MWF), and neurite density index (NDI). To fully utilize the qMRI, GAMER-MRIL extended a gated-attention-based CNN (GAMER-MRI), which was developed to select patch-based qMRI important for a given task/question, to the whole-brain image. To find out disability-related brain regions, GAMER-MRIL modified a structure-aware interpretability method, Layer-wise Relevance Propagation (LRP), to incorporate qMRI. Results: The test performance was AUC=0.885. qT1 was the most sensitive measu
Multiple sclerosis is a neurological disorder in which the myelin sheaths of axons are damaged by the immune response. We report here a three-dimensional structural analysis of brain and spinal cord tissues of a mouse model of multiple sclerosis, known as experimental autoimmune encephalomyelitis (EAE). EAE-induced mice were raised with or without administration of fingolimod, which is used in the treatment of multiple sclerosis. Brains and spinal cords dissected from the EAE mice were lyophilized so as to reconstitute the intrinsic contrast of tissue elements, such as axons, in X-ray images. Three-dimensional structures of the brain hemispheres and spinal cords of the EAE mice were visualized with synchrotron radiation microtomography. Microtomographic cross sections reconstructed from the X-ray images revealed dilation of capillary vessels and vacuolation in the spinal cord of the EAE mice. Vacuolation was also observed in the cerebellum, suggesting that the neuroinflammatory response progressed in the brain. The vessel networks and vacuolation lesions in the spinal cords were modelled by automatically tracing the three-dimensional image in order to analyze the tissue structures
Multiple sclerosis is a chronic autoimmune disease that affects the central nervous system. Understanding multiple sclerosis progression and identifying the implicated brain structures is crucial for personalized treatment decisions. Deformation-based morphometry utilizes anatomical magnetic resonance imaging to quantitatively assess volumetric brain changes at the voxel level, providing insight into how each brain region contributes to clinical progression with regards to neurodegeneration. Utilizing such voxel-level data from a relapsing multiple sclerosis clinical trial, we extend a model-agnostic feature importance metric to identify a robust and predictive feature set that corresponds to clinical progression. These features correspond to brain regions that are clinically meaningful in MS disease research, demonstrating their scientific relevance. When used to predict progression using classical survival models and 3D convolutional neural networks, the identified regions led to the best-performing models, demonstrating their prognostic strength. We also find that these features generalize well to other definitions of clinical progression and can compensate for the omission of h
Magnetic resonance imaging is a fundamental tool to reach a diagnosis of multiple sclerosis and monitoring its progression. Although several attempts have been made to segment multiple sclerosis lesions using artificial intelligence, fully automated analysis is not yet available. State-of-the-art methods rely on slight variations in segmentation architectures (e.g. U-Net, etc.). However, recent research has demonstrated how exploiting temporal-aware features and attention mechanisms can provide a significant boost to traditional architectures. This paper proposes a framework that exploits an augmented U-Net architecture with a convolutional long short-term memory layer and attention mechanism which is able to segment and quantify multiple sclerosis lesions detected in magnetic resonance images. Quantitative and qualitative evaluation on challenging examples demonstrated how the method outperforms previous state-of-the-art approaches, reporting an overall Dice score of 89% and also demonstrating robustness and generalization ability on never seen new test samples of a new dedicated under construction dataset.
Background: Recent studies have shown a decrease in annualised relapse rates (ARRs) in placebo groups of randomised controlled trials (RCTs) in relapsing multiple sclerosis (RMS). Methods: We conducted a systematic literature search of RCTs in RMS. Data on eligibility criteria and baseline characteristics were extracted and tested for significant trends over time. A meta-regression was conducted to estimate their contribution to the decrease of trial ARRs over time. Results: We identified 56 studies. Patient age at baseline (p < 0.001), mean duration of multiple sclerosis (MS) at baseline (p = 0.048), size of treatment groups (p = 0.003), Oxford Quality Scale scores (p = 0.021), and the number of eligibility criteria (p<0.001) increased significantly, whereas pre-trial ARR (p = 0.001), the time span over which pre-trial ARR was calculated (p < 0.001), and the duration of placebo-controlled follow-up (p = 0.006) decreased significantly over time. In meta-regression of trial placebo ARR, the temporal trend was found to be insignificant, with major factors explaining the variation: pre-trial ARR, the number of years used to calculate pre-trial ARR and study duration. Conclusi
Magnetic resonance imaging (MRI) plays a vital role in the scientific investigation and clinical management of multiple sclerosis. Analyses of binary multiple sclerosis lesion maps are typically "mass univariate" and conducted with standard linear models that are ill suited to the binary nature of the data and ignore the spatial dependence between nearby voxels (volume elements). Smoothing the lesion maps does not entirely eliminate the non-Gaussian nature of the data and requires an arbitrary choice of the smoothing parameter. Here we present a Bayesian spatial model to accurately model binary lesion maps and to determine if there is spatial dependence between lesion location and subject specific covariates such as MS subtype, age, gender, disease duration and disease severity measures. We apply our model to binary lesion maps derived from $T_2$-weighted MRI images from 250 multiple sclerosis patients classified into five clinical subtypes, and demonstrate unique modeling and predictive capabilities over existing methods.
Multiple Sclerosis (MS) is a chronic disease developed in human brain and spinal cord, which can cause permanent damage or deterioration of the nerves. The severity of MS disease is monitored by the Expanded Disability Status Scale (EDSS), composed of several functional sub-scores. Early and accurate classification of MS disease severity is critical for slowing down or preventing disease progression via applying early therapeutic intervention strategies. Recent advances in deep learning and the wide use of Electronic Health Records (EHR) creates opportunities to apply data-driven and predictive modeling tools for this goal. Previous studies focusing on using single-modal machine learning and deep learning algorithms were limited in terms of prediction accuracy due to the data insufficiency or model simplicity. In this paper, we proposed an idea of using patients' multimodal longitudinal and longitudinal EHR data to predict multiple sclerosis disease severity at the hospital visit. This work has two important contributions. First, we describe a pilot effort to leverage structured EHR data, neuroimaging data and clinical notes to build a multi-modal deep learning framework to predict
Assessment of lesions and their longitudinal progression from brain magnetic resonance (MR) images plays a crucial role in diagnosing and monitoring multiple sclerosis (MS). Machine learning models have demonstrated a great potential for automated MS lesion segmentation. Training such models typically requires large-scale high-quality datasets that are consistently annotated. However, MS imaging datasets are often small, segregated across multiple sites, with different formats (cross-sectional or longitudinal), and diverse annotation styles. This poses a significant challenge to train a unified MS lesion segmentation model. To tackle this challenge, we present SegHeD, a novel multi-dataset multi-task segmentation model that can incorporate heterogeneous data as input and perform all-lesion, new-lesion, as well as vanishing-lesion segmentation. Furthermore, we account for domain knowledge about MS lesions, incorporating longitudinal, spatial, and volumetric constraints into the segmentation model. SegHeD is assessed on five MS datasets and achieves a high performance in all, new, and vanishing-lesion segmentation, outperforming several state-of-the-art methods in this field.
Multiple sclerosis is a disease that affects the brain and spinal cord, it can lead to severe disability and has no known cure. The majority of prior work in machine learning for multiple sclerosis has been centered around using Magnetic Resonance Imaging scans or laboratory tests; these modalities are both expensive to acquire and can be unreliable. In a recent paper it was shown that disease progression can be predicted effectively using performance outcome measures and demographic data. In our work we build on this to investigate the modeling side, using continuous time models to predict progression. We benchmark four continuous time models using a publicly available multiple sclerosis dataset. We find that the best continuous model is often able to outperform the best benchmarked discrete time model. We also carry out an extensive ablation to discover the sources of performance gains, we find that standardizing existing features leads to a larger performance increase than interpolating missing features.
Background: Recently, we introduced solar related geomagnetic disturbances (GMD) as a potential environmental risk factor for multiple sclerosis (MS). The aim of this study was to test probable correlation between solar activities and GMD with long-term variations of MS incidence. Methods: After a systematic review, we studied the association between alterations in solar wind velocity (Vsw) and planetary A index (Ap, a GMD index) with MS incidence in Tehran and western Greece, during the 23rd solar cycle (1996-2008), by an ecological-correlational study. Results: We found moderate to strong correlations among MS incidence of Tehran with Vsw (Rs=0.665, p=0.013), with one year delay, and also with Ap (Rs=0.864, p=0.001) with 2 year delay. There were very strong correlations among MS incidence data of Greece with Vsw (R=0.906, p<0.001) and with Ap (R=0.844, p=0.001), both with one year lag. Conclusion: It is the first time that a hypothesis has introduced an environmental factor that may describe MS incidence alterations; however, it should be reminded that correlation does not mean necessarily the existence of a causal relationship. Important message of these findings for research