ABSTRACT
In this paper, we analyse the different advances in artificial intelligence (AI) approaches in multiple sclerosis (MS). AI applications in MS range across investigation of disease pathogenesis, diagnosis, treatment, and prognosis. A subset of AI, Machine learning (ML) models analyse various data sources, including magnetic resonance imaging (MRI), genetic, and clinical data, to distinguish MS from other conditions, predict disease progression, and personalize treatment strategies. Additionally, AI models have been extensively applied to lesion segmentation, identification of biomarkers, and prediction of outcomes, disease monitoring, and management. Despite the big promises of AI solutions, model interpretability and transparency remain critical for gaining clinician and patient trust in these methods. The future of AI in MS holds potential for open data initiatives that could feed ML models and increasing generalizability, the implementation of federated learning solutions for training the models addressing data sharing issues, and generative AI approaches to address challenges in model interpretability, and transparency. In conclusion, AI presents an opportunity to advance our understanding and management of MS. AI promises to aid clinicians in MS diagnosis and prognosis improving patient outcomes and quality of life, however ensuring the interpretability and transparency of AI-generated results is going to be key for facilitating the integration of AI into clinical practice.
Subject(s)
Artificial Intelligence , Multiple Sclerosis , Humans , Multiple Sclerosis/diagnosis , Multiple Sclerosis/therapy , Machine LearningABSTRACT
Complex diseases such as Multiple Sclerosis (MS) cover a wide range of biological scales, from genes and proteins to cells and tissues, up to the full organism. In fact, any phenotype for an organism is dictated by the interplay among these scales. We conducted a multilayer network analysis and deep phenotyping with multi-omics data (genomics, phosphoproteomics and cytomics), brain and retinal imaging, and clinical data, obtained from a multicenter prospective cohort of 328 patients and 90 healthy controls. Multilayer networks were constructed using mutual information for topological analysis, and Boolean simulations were constructed using Pearson correlation to identified paths within and among all layers. The path more commonly found from the Boolean simulations connects protein MK03, with total T cells, the thickness of the retinal nerve fiber layer (RNFL), and the walking speed. This path contains nodes involved in protein phosphorylation, glial cell differentiation, and regulation of stress-activated MAPK cascade, among others. Specific paths identified were subsequently analyzed by flow cytometry at the single-cell level. Combinations of several proteins (GSK3AB, HSBP1 or RS6) and immune cells (Th17, Th1 non-classic, CD8, CD8 Treg, CD56 neg, and B memory) were part of the paths explaining the clinical phenotype. The advantage of the path identified from the Boolean simulations is that it connects information about these known biological pathways with the layers at higher scales (retina damage and disability). Overall, the identified paths provide a means to connect the molecular aspects of MS with the overall phenotype.
Subject(s)
Multiple Sclerosis , Humans , Prospective Studies , Tomography, Optical Coherence/methods , Retina , Brain , Heat-Shock ProteinsABSTRACT
BACKGROUND: We investigated the association between changes in retinal thickness and cognition in people with MS (PwMS), exploring the predictive value of optical coherence tomography (OCT) markers of neuroaxonal damage for global cognitive decline at different periods of disease. METHOD: We quantified the peripapillary retinal nerve fibre (pRFNL) and ganglion cell-inner plexiform (GCIPL) layers thicknesses of 207 PwMS and performed neuropsychological evaluations. The cohort was divided based on disease duration (≤5 years or >5 years). We studied associations between changes in OCT and cognition over time, and assessed the risk of cognitive decline of a pRFNL≤88 µm or GCIPL≤77 µm and its predictive value. RESULTS: Changes in pRFNL and GCIPL thickness over 3.2 years were associated with evolution of cognitive scores, in the entire cohort and in patients with more than 5 years of disease (p<0.01). Changes in cognition were related to less use of disease-modifying drugs, but not OCT metrics in PwMS within 5 years of onset. A pRFNL≤88 µm was associated with earlier cognitive disability (3.7 vs 9.9 years) and higher risk of cognitive deterioration (HR=1.64, p=0.022). A GCIPL≤77 µm was not associated with a higher risk of cognitive decline, but a trend was observed at ≤91.5 µm in PwMS with longer disease (HR=1.81, p=0.061). CONCLUSIONS: The progressive retinal thinning is related to cognitive decline, indicating that cognitive dysfunction is a late manifestation of accumulated neuroaxonal damage. Quantifying the pRFNL aids in identifying individuals at risk of cognitive dysfunction.
Subject(s)
Cognitive Dysfunction , Multiple Sclerosis , Humans , Multiple Sclerosis/complications , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/pathology , Retinal Ganglion Cells/pathology , Retina/pathology , Tomography, Optical Coherence/methods , Cognitive Dysfunction/complications , Atrophy/pathologyABSTRACT
BACKGROUND: Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity. METHODS: We have analysed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centres, collecting disability scales at baseline and 2 years later. Imaging data included brain MRI and optical coherence tomography, and omics included genotyping, cytomics and phosphoproteomic data from peripheral blood mononuclear cells. Predictors of clinical outcomes were searched using Random Forest algorithms. Assessment of the algorithm performance was conducted in an independent prospective cohort of 271 MS patients from a single centre. RESULTS: We found algorithms for predicting confirmed disability accumulation for the different scales, no evidence of disease activity (NEDA), onset of immunotherapy and the escalation from low- to high-efficacy therapy with intermediate to high-accuracy. This accuracy was achieved for most of the predictors using clinical data alone or in combination with imaging data. Still, in some cases, the addition of omics data slightly increased algorithm performance. Accuracies were comparable in both cohorts. CONCLUSION: Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening.
Subject(s)
Multiple Sclerosis , Humans , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/therapy , Prospective Studies , Leukocytes, Mononuclear , Magnetic Resonance Imaging/methods , Patient Acuity , Machine LearningABSTRACT
T2-hyperintense lesions are the key imaging marker of multiple sclerosis (MS). Previous studies have shown that the white matter surrounding such lesions is often also affected by MS. Our aim was to develop a new method to visualize and quantify the extent of white matter tissue changes in MS based on relaxometry properties. We applied a fast, multi-parametric quantitative MRI approach and used a multi-component MR Fingerprinting (MC-MRF) analysis. We assessed the differences in the MRF component representing prolongedrelaxation time between patients with MS and controls and studied the relation between this component's volume and structural white matter damage identified on FLAIR MRI scans in patients with MS. A total of 48 MS patients at two different sites and 12 healthy controls were scanned with FLAIR and MRF-EPI MRI scans. MRF scans were analyzed with a joint-sparsity multi-component analysis to obtain magnetization fraction maps of different components, representing tissues such as myelin water, white matter, gray matter and cerebrospinal fluid. In the MS patients, an additional component was identified with increased transverse relaxation times compared to the white matter, likely representing changes in free water content. Patients with MS had a higher volume of the long- component in the white matter of the brain compared to healthy controls (B (95%-CI) = 0.004 (0.0006-0.008), p = 0.02). Furthermore, this MRF component had a moderate correlation (correlation coefficient R 0.47) with visible structural white matter changes on the FLAIR scans. Also, the component was found to be more extensive compared to structural white matter changes in 73% of MS patients. In conclusion, our MRF acquisition and analysis captured white matter tissue changes in MS patients compared to controls. In patients these tissue changes were more extensive compared to visually detectable white matter changes on FLAIR scans. Our method provides a novel way to quantify the extent of white matter changes in MS patients, which is underestimated using only conventional clinical MRI scans.
Subject(s)
Multiple Sclerosis , White Matter , Humans , White Matter/diagnostic imaging , White Matter/pathology , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/pathology , Magnetic Resonance Imaging/methods , Brain/diagnostic imaging , Brain/pathology , WaterABSTRACT
BACKGROUND: We aimed to describe the severity of the changes in brain diffusion-based connectivity as multiple sclerosis (MS) progresses and the microstructural characteristics of these networks that are associated with distinct MS phenotypes. METHODS: Clinical information and brain MRIs were collected from 221 healthy individuals and 823 people with MS at 8 MAGNIMS centres. The patients were divided into four clinical phenotypes: clinically isolated syndrome, relapsing-remitting, secondary progressive and primary progressive. Advanced tractography methods were used to obtain connectivity matrices. Then, differences in whole-brain and nodal graph-derived measures, and in the fractional anisotropy of connections between groups were analysed. Support vector machine algorithms were used to classify groups. RESULTS: Clinically isolated syndrome and relapsing-remitting patients shared similar network changes relative to controls. However, most global and local network properties differed in secondary progressive patients compared with the other groups, with lower fractional anisotropy in most connections. Primary progressive participants had fewer differences in global and local graph measures compared with clinically isolated syndrome and relapsing-remitting patients, and reductions in fractional anisotropy were only evident for a few connections. The accuracy of support vector machine to discriminate patients from healthy controls based on connection was 81%, and ranged between 64% and 74% in distinguishing among the clinical phenotypes. CONCLUSIONS: In conclusion, brain connectivity is disrupted in MS and has differential patterns according to the phenotype. Secondary progressive is associated with more widespread changes in connectivity. Additionally, classification tasks can distinguish between MS types, with subcortical connections being the most important factor.
Subject(s)
Demyelinating Diseases , Multiple Sclerosis, Relapsing-Remitting , Multiple Sclerosis , Humans , Multiple Sclerosis/diagnostic imaging , Brain/diagnostic imaging , Magnetic Resonance Imaging , Brain Mapping/methods , Phenotype , Multiple Sclerosis, Relapsing-Remitting/diagnostic imagingABSTRACT
The relationship between structural connectivity (SC) and functional connectivity (FC) captured from magnetic resonance imaging, as well as its interaction with disability and cognitive impairment, is not well understood in people with multiple sclerosis (pwMS). The Virtual Brain (TVB) is an open-source brain simulator for creating personalized brain models using SC and FC. The aim of this study was to explore SC-FC relationship in MS using TVB. Two different model regimes have been studied: stable and oscillatory, with the latter including conduction delays in the brain. The models were applied to 513 pwMS and 208 healthy controls (HC) from 7 different centers. Models were analyzed using structural damage, global diffusion properties, clinical disability, cognitive scores, and graph-derived metrics from both simulated and empirical FC. For the stable model, higher SC-FC coupling was associated with pwMS with low Single Digit Modalities Test (SDMT) score (F=3.48, P$\lt$0.05), suggesting that cognitive impairment in pwMS is associated with a higher SC-FC coupling. Differences in entropy of the simulated FC between HC, high and low SDMT groups (F=31.57, P$\lt$1e-5), show that the model captures subtle differences not detected in the empirical FC, suggesting the existence of compensatory and maladaptive mechanisms between SC and FC in MS.
Subject(s)
Cognitive Dysfunction , Multiple Sclerosis , Humans , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/pathology , Brain , Magnetic Resonance Imaging/methods , Brain Mapping/methods , Cognitive Dysfunction/diagnostic imaging , Cognitive Dysfunction/etiology , Cognitive Dysfunction/pathologyABSTRACT
Multisite machine-learning neuroimaging studies, such as those conducted by the ENIGMA Consortium, need to remove the differences between sites to avoid effects of the site (EoS) that may prevent or fraudulently help the creation of prediction models, leading to impoverished or inflated prediction accuracy. Unfortunately, we have shown earlier that current Methods Aiming to Remove the EoS (MAREoS, e.g., ComBat) cannot remove complex EoS (e.g., including interactions between regions). And complex EoS may bias the accuracy. To overcome this hurdle, groups worldwide are developing novel MAREoS. However, we cannot assess their effectiveness because EoS may either inflate or shrink the accuracy, and MAREoS may both remove the EoS and degrade the data. In this work, we propose a strategy to measure the effectiveness of a MAREoS in removing different types of EoS. FOR MAREOS DEVELOPERS, we provide two multisite MRI datasets with only simple true effects (i.e., detectable by most machine-learning algorithms) and two with only simple EoS (i.e., removable by most MAREoS). First, they should use these datasets to fit machine-learning algorithms after applying the MAREoS. Second, they should use the formulas we provide to calculate the relative accuracy change associated with the MAREoS in each dataset and derive an EoS-removal effectiveness statistic. We also offer similar datasets and formulas for complex true effects and EoS that include first-order interactions. FOR MACHINE-LEARNING RESEARCHERS, we provide an extendable benchmark website to show: a) the types of EoS they should remove for each given machine-learning algorithm and b) the effectiveness of each MAREoS for removing each type of EoS. Relevantly, a MAREoS only able to remove the simple EoS may suffice for simple machine-learning algorithms, whereas more complex algorithms need a MAREoS that can remove more complex EoS. For instance, ComBat removes all simple EoS as needed for predictions based on simple lasso algorithms, but it leaves residual complex EoS that may bias the predictions based on standard support vector machine algorithms.
Subject(s)
Algorithms , Benchmarking , Humans , Machine Learning , Brain/diagnostic imaging , NeuroimagingABSTRACT
Introduction: Beyond mood abnormalities, bipolar disorder (BD) includes cognitive impairments that worsen psychosocial functioning and quality of life. These deficits are especially severe in older adults with BD (OABD), a condition expected to represent most individuals with BD in the upcoming years. Restoring the psychosocial functioning of this population will thus soon represent a public health priority. To help tackle the problem, the Bipolar and Depressive Disorders Unit at the Hospital Clínic of Barcelona has recently adapted its Functional Remediation (FR) program to that population, calling it FROA-BD. However, while scarce previous studies localize the neural mechanisms of cognitive remediation interventions in the dorsal prefrontal cortex, the specific mechanisms are seldom unknown. In the present project, we will investigate the neural correlates of FR-OABD to understand its mechanisms better and inform for potential optimization. The aim is to investigate the brain features and changes associated with FROA-BD efficacy. Methods: Thirty-two individuals with OABD in full or partial remission will undergo a magnetic resonance imaging (MRI) session before receiving FR-OABD. After completing the FR-OABD intervention, they will undergo another MRI session. The MRI sessions will include structural, diffusion-weighted imaging (DWI), functional MRI (fMRI) with working memory (n-back) and verbal learning tasks, and frontal spectroscopy. We will correlate the pre-post change in dorsolateral and dorsomedial prefrontal cortices activation during the n-back task with the change in psychosocial functioning [measured with the Functioning Assessment Short Test (FAST)]. We will also conduct exploratory whole-brain correlation analyses between baseline or pre-post changes in MRI data and other clinical and cognitive outcomes to provide more insights into the mechanisms and explore potential brain markers that may predict a better treatment response. We will also conduct separate analyses by sex. Discussion: The results of this study may provide insights into how FROA-BD and other cognitive remediations modulate brain function and thus could optimize these interventions.
ABSTRACT
The consequences of extremely intense long-term exercise for brain health remain unknown. We studied the effects of strenuous exercise on brain structure and function, its dose-response relationship, and mechanisms in a rat model of endurance training. Five-week-old male Wistar rats were assigned to moderate (MOD) or intense (INT) exercise or a sedentary (SED) group for 16 weeks. MOD rats showed the highest motivation and learning capacity in operant conditioning experiments; SED and INT presented similar results. In vivo MRI demonstrated enhanced global and regional connectivity efficiency and clustering as well as a higher cerebral blood flow (CBF) in MOD but not INT rats compared with SED. In the cortex, downregulation of oxidative phosphorylation complex IV and AMPK activation denoted mitochondrial dysfunction in INT rats. An imbalance in cortical antioxidant capacity was found between MOD and INT rats. The MOD group showed the lowest hippocampal brain-derived neurotrophic factor levels. The mRNA and protein levels of inflammatory markers were similar in all groups. In conclusion, strenuous long-term exercise yields a lesser improvement in learning ability than moderate exercise. Blunting of MOD-induced improvements in CBF and connectivity efficiency, accompanied by impaired mitochondrial energetics and, possibly, transient local oxidative stress, may underlie the findings in intensively trained rats.
Subject(s)
Physical Conditioning, Animal , Rats , Animals , Male , Rats, Wistar , Physical Conditioning, Animal/physiology , Oxidative Stress , Antioxidants , BrainABSTRACT
Multiple sclerosis (MS) is a chronic autoimmune disease characterized by demyelinating lesions that are often visible on magnetic resonance imaging (MRI). Segmentation of these lesions can provide imaging biomarkers of disease burden that can help monitor disease progression and the imaging response to treatment. Manual delineation of MRI lesions is tedious and prone to subjective bias, while automated lesion segmentation methods offer objectivity and speed, the latter being particularly important when analysing large datasets. Lesion segmentation can be broadly categorised into two groups: cross-sectional methods, which use imaging data acquired at a single time-point to characterise MRI lesions; and longitudinal methods, which use imaging data from the same subject acquired at two or more different time-points to characterise lesions over time. The main objective of longitudinal segmentation approaches is to more accurately detect the presence of new MS lesions and the growth or remission of existing lesions, which may be effective biomarkers of disease progression and treatment response. This paper reviews articles on longitudinal MS lesion segmentation methods published over the past 10 years. These are divided into traditional machine learning methods and deep learning techniques. PubMed articles using longitudinal information and comparing fully automatic two time point segmentations in any step of the process were selected. Nineteen articles were reviewed. There is an increasing number of deep learning techniques for longitudinal MS lesion segmentation that are promising to help better understand disease progression.
Subject(s)
Multiple Sclerosis , Cross-Sectional Studies , Disease Progression , Humans , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Magnetic Resonance Spectroscopy , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis/pathologyABSTRACT
In recent years, research on network analysis applied to MRI data has advanced significantly. However, the majority of the studies are limited to single networks obtained from resting-state fMRI, diffusion MRI, or gray matter probability maps derived from T1 images. Although a limited number of previous studies have combined two of these networks, none have introduced a framework to combine morphological, structural, and functional brain connectivity networks. The aim of this study was to combine the morphological, structural, and functional information, thus defining a new multilayer network perspective. This has proved advantageous when jointly analyzing multiple types of relational data from the same objects simultaneously using graph- mining techniques. The main contribution of this research is the design, development, and validation of a framework that merges these three layers of information into one multilayer network that links and relates the integrity of white matter connections with gray matter probability maps and resting-state fMRI. To validate our framework, several metrics from graph theory are expanded and adapted to our specific domain characteristics. This proof of concept was applied to a cohort of people with multiple sclerosis, and results show that several brain regions with a synchronized connectivity deterioration could be identified.
ABSTRACT
(1) Background: The evolution and predictors of cognitive impairment (CI) in multiple sclerosis (MS) are poorly understood. We aimed to define the temporal dynamics of cognition throughout the disease course and identify clinical and neuroimaging measures that predict CI. (2) Methods: This paper features a longitudinal study with 212 patients who underwent several cognitive examinations at different time points. Dynamics of cognition were assessed using mixed-effects linear spline models. Machine learning techniques were used to identify which baseline demographic, clinical, and neuroimaging measures best predicted CI. (3) Results: In the first 5 years of MS, we detected an increase in the z-scores of global cognition, verbal memory, and information processing speed, which was followed by a decline in global cognition and memory (p < 0.05) between years 5 and 15. From 15 to 30 years of disease onset, cognitive decline continued, affecting global cognition and verbal memory. The baseline measures that best predicted CI were education, disease severity, lesion burden, and hippocampus and anterior cingulate cortex volume. (4) Conclusions: In MS, cognition deteriorates 5 years after disease onset, declining steadily over the next 25 years and more markedly affecting verbal memory. Education, disease severity, lesion burden, and volume of limbic structures predict future CI and may be helpful when identifying at-risk patients.
ABSTRACT
Quantitative diffusion imaging techniques enable the characterization of tissue microstructural properties of the human brain "in vivo", and are widely used in neuroscientific and clinical contexts. In this review, we present the basic physical principles behind diffusion imaging and provide an overview of the current diffusion techniques, including standard and advanced techniques as well as their main clinical applications. Standard diffusion tensor imaging (DTI) offers sensitivity to changes in microstructure due to diseases and enables the characterization of single fiber distributions within a voxel as well as diffusion anisotropy. Nonetheless, its inability to represent complex intravoxel fiber topologies and the limited biological specificity of its metrics motivated the development of several advanced diffusion MRI techniques. For example, high-angular resolution diffusion imaging (HARDI) techniques enabled the characterization of fiber crossing areas and other complex fiber topologies in a single voxel and supported the development of higher-order signal representations aiming to decompose the diffusion MRI signal into distinct microstructure compartments. Biophysical models, often known by their acronym (e.g., CHARMED, WMTI, NODDI, DBSI, DIAMOND) contributed to capture the diffusion properties from each of such tissue compartments, enabling the computation of voxel-wise maps of axonal density and/or morphology that hold promise as clinically viable biomarkers in several neurological and neuroscientific applications; for example, to quantify tissue alterations due to disease or healthy processes. Current challenges and limitations of state-of-the-art models are discussed, including validation efforts. Finally, novel diffusion encoding approaches (e.g., b-tensor or double diffusion encoding) may increase the biological specificity of diffusion metrics towards intra-voxel diffusion heterogeneity in clinical settings, holding promise in neurological applications.
Subject(s)
Diffusion Magnetic Resonance Imaging , Diffusion Tensor Imaging , Brain/diagnostic imaging , HumansABSTRACT
Quadrantanopia caused by inadvertent severing of Meyer's Loop of the optic radiation is a well-recognised complication of temporal lobectomy for conditions such as epilepsy. Dissection studies indicate that the anterior extent of Meyer's Loop varies considerably between individuals. Quantifying this for individual patients is thus an important step to improve the safety profile of temporal lobectomies. Previous attempts to delineate Meyer's Loop using diffusion MRI tractography have had difficulty estimating its full anterior extent, required manual ROI placement, and/or relied on advanced diffusion sequences that cannot be acquired routinely in most clinics. Here we present CONSULT: a pipeline that can delineate the optic radiation from raw DICOM data in a completely automated way via a combination of robust pre-processing, segmentation, and alignment stages, plus simple improvements that bolster the efficiency and reliability of standard tractography. We tested CONSULT on 696 scans of predominantly healthy participants (539 unique brains), including both advanced acquisitions and simpler acquisitions that could be acquired in clinically acceptable timeframes. Delineations completed without error in 99.4% of the scans. The distance between Meyer's Loop and the temporal pole closely matched both averages and ranges reported in dissection studies for all tested sequences. Median scan-rescan error of this distance was 1 mm. When tested on two participants with considerable pathology, delineations were successful and realistic. Through this, we demonstrate not only how to identify Meyer's Loop with clinically feasible sequences, but also that this can be achieved without fundamental changes to tractography algorithms or complex post-processing methods.
Subject(s)
Diffusion Tensor Imaging/methods , Image Interpretation, Computer-Assisted/methods , Visual Pathways/anatomy & histology , Visual Pathways/diagnostic imaging , Adult , Anterior Temporal Lobectomy/methods , Female , Humans , Male , Preoperative Care/methods , Young AdultABSTRACT
The spatio-temporal characteristics of grey matter (GM) impairment in multiple sclerosis (MS) are poorly understood. We used a new surface-based diffusion MRI processing tool to investigate regional modifications of microstructure, and we quantified volume loss in GM in a cohort of patients with MS classified into three groups according to disease duration. Additionally, we investigated the relationship between GM changes with disease severity. We studied 54 healthy controls and 247 MS patients classified regarding disease duration: MS1 (less than 5 years, n = 67); MS2 (5-15 years, n = 107); and MS3 (more than15 years, n = 73). We compared GM mean diffusivity (MD), fractional anisotropy (FA) and volume between groups, and estimated their clinical associations. Regional modifications in diffusion measures (MD and FA) and volume did not overlap early in the disease, and became widespread in later phases. We found higher MD in MS1 group, mainly in the temporal cortex, and volume reduction in deep GM and left precuneus. Additional MD changes were evident in cingulate and occipital cortices in the MS2 group, coupled to volume reductions in deep GM and parietal and frontal poles. Changes in MD and volume extended to more than 80% of regions in MS3 group. Conversely, increments in FA, with very low effect size, were observed in the parietal cortex and thalamus in MS1 and MS2 groups, and extended to the frontal lobe in the later group. MD and GM changes were associated with white matter lesion load and with physical and cognitive disability. Microstructural integrity loss and atrophy present differential spatial predominance early in MS and accrual over time, probably due to distinct pathogenic mechanisms that underlie tissue damage.
Subject(s)
Gray Matter/pathology , Multiple Sclerosis/pathology , Adult , Anisotropy , Atrophy/pathology , Diffusion Tensor Imaging , Female , Humans , Male , Organ Size , Recurrence , White Matter/pathologyABSTRACT
BACKGROUND: To develop a regression neural network for the reconstruction of lesion probability maps on Magnetic Resonance Fingerprinting using echo-planar imaging (MRF-EPI) in addition to [Formula: see text], [Formula: see text], NAWM, and GM- probability maps. METHODS: We performed MRF-EPI measurements in 42 patients with multiple sclerosis and 6 healthy volunteers along two sites. A U-net was trained to reconstruct the denoised and distortion corrected [Formula: see text] and [Formula: see text] maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps. RESULTS: WM lesions were predicted with a dice coefficient of [Formula: see text] and a lesion detection rate of [Formula: see text] for a threshold of 33%. The network jointly enabled accurate [Formula: see text] and [Formula: see text] times with relative deviations of 5.2% and 5.1% and average dice coefficients of [Formula: see text] and [Formula: see text] for NAWM and GM after binarizing with a threshold of 80%. CONCLUSION: DL is a promising tool for the prediction of lesion probability maps in a fraction of time. These might be of clinical interest for the WM lesion analysis in MS patients.
Subject(s)
Deep Learning , Echo-Planar Imaging , Multiple Sclerosis/diagnostic imaging , White Matter/diagnostic imaging , Brain Mapping , Humans , Leukoencephalopathies/diagnostic imaging , Neural Networks, Computer , ProbabilityABSTRACT
BACKGROUND: Fractal geometry measures the morphology of the brain and detects CNS damage. We aimed to assess the longitudinal changes on brain's fractal geometry and its predictive value for disease worsening in patients with Multiple Sclerosis (MS). METHODS: We prospectively analyzed 146 consecutive patients with relapsing-remitting MS with up to 5 years of clinical and brain MRI (3 T) assessments. The fractal dimension and lacunarity were calculated for brain regions using box-counting methods. Longitudinal changes were analyzed in mixed-effect models and the risk of disability accumulation were assessed using Cox Proportional Hazard regression analysis. RESULTS: There was a significant decrease in the fractal dimension and increases of lacunarity in different brain regions over the 5-year follow-up. Lower cortical fractal dimension increased the risk of disability accumulation for the Expanded Disability Status Scale [HR 0.9734, CI 0.8420-0.9125; Harrell C 0.59; Wald p 0.038], 9-hole peg test [HR 0.9734, CI 0.8420-0.9125; Harrell C 0.59; Wald p 0.0083], 2.5% low contrast vision [HR 0.4311, CI 0.2035-0.9133; Harrell C 0.58; Wald p 0.0403], symbol digit modality test [HR 2.215, CI 1.043-4.705; Harrell C 0.65; Wald p 0.0384] and MS Functional Composite-4 [HR 0.55, CI 0.317-0.955; Harrell C 0.59; Wald p 0.0029]. CONCLUSIONS: Fractal geometry analysis of brain MRI identified patients at risk of increasing their disability in the next five years.
Subject(s)
Multiple Sclerosis, Relapsing-Remitting , Multiple Sclerosis , Brain/diagnostic imaging , Disability Evaluation , Disease Progression , Fractals , Humans , Magnetic Resonance Imaging , Multiple Sclerosis/diagnostic imaging , Multiple Sclerosis, Relapsing-Remitting/diagnostic imagingABSTRACT
PURPOSE: To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning. METHODS: MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of T1 and T2∗ in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF T1 and T2∗ parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the T1 and T2∗ parametric maps, and the WM and GM probability maps. RESULTS: Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for T1 (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for T2∗ (deviations 6.0%). CONCLUSIONS: MRF is a fast and robust tool for quantitative T1 and T2∗ mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.
Subject(s)
Deep Learning , White Matter , Brain/diagnostic imaging , Humans , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Magnetic Resonance Spectroscopy , Phantoms, Imaging , Reproducibility of Results , White Matter/diagnostic imagingABSTRACT
OBJECTIVE: To investigate the incidence of coronavirus disease 2019 (COVID-19) in a single-center cohort of patients with MS and to explore the contribution of their comorbidities and therapies to the outcome. METHODS: A cross-sectional mixed-method study was conducted involving an email-based, self-administered questionnaire sent on May 21, 2020, to 586 patients with MS followed at the MS Unit of Hospital Clinic, University of Barcelona, along with telephone interview, and review of electronic medical records until June 18, 2020. The cumulative incidence of confirmed COVID-19 (positive PCR or antibody test) and all COVID-19 cases (confirmed and suspected) from the start of the pandemic was compared with the population estimates for Barcelona. RESULTS: A total of 407 patients (69.5%) completed the survey. Most of the responders (67%) were female. The responders had a median age of 48 years (range 19-86), relapsing-remitting disease (84%), at least 1 comorbidity (45%), and were on disease-modifying therapy (DMT; 74.7%). COVID-19 was confirmed in 5 patients (1.2%) and suspected in 46 (11.3%). The cumulative incidence of confirmed COVID-19 cases was similar to that of the general population but was almost 2-fold higher when all cases were considered (p < 0.001). Six patients (11.7%) were hospitalized, of which 5 had good recovery and 1 died. Hospitalized patients were more frequently male, had diabetes and had progressive forms of MS (p < 0.05). DMT was not associated with the risk of infection or the outcome. CONCLUSIONS: In the studied MS cohort, the incidence of COVID-19 was higher than that of the general population; however, most patients did not require hospitalization and had a good outcome despite the frequent presence of comorbidities and treatment with DMT.