Radiomics models based on cortical damages for identification of multiple sclerosis with cognitive impairment.

BACKGROUND: Cognitive impairment (CI) is a common symptom in multiple sclerosis (MS) patients. Cortical damages can be closely associated with cognitive network dysfunction and clinically significant CI in MS. So, in this study, We aimed to develop a radiomics model to efficiently identify the MS patients with CI based on clinical data and cortical damages. METHODS: One hundred and eighteen patients with MS were divided into CI and normal cognitive (NC) cohorts (62/56) as defined by the Montreal Cognitive Assessment (MoCA). All participants were randomly divided into train and test sets with a ratio of 7:3. The radiomic features were selected by using the least absolute shrinkage and selection operator (LASSO) method. The discrimination models were built with the support vector machines (SVM) by the clinical data, radiomic features, and merge data, respectively. And the patients were further divided according to each cognitive domain including memory, visuospatial, language, attention and executive, and each domain model was applied by the most suitable classifier. RESULTS: A total of 2298 features were extracted, of which 36 were finally selected. The merge model showed the greatest performance with the area under the curve (AUC) of 0.86 (95 % confidence interval: 0.81-0.91), accuracy (ACC) of 0.78, sensitivity of 0.79 and specificity of 0.77 in test cohort. However, although the visuospatial domain model showed the highest AUC of 0.71 (95 % confidence interval: 0.61-0.81) among five domain models, other domain models did not meet satisfactory results with a relatively low AUC, ACC, sensitivity and specificity. CONCLUSIONS: The radiomics model based on clinical data and cortical damages had a great potential to identify the MS patients with CI for clinical cognitive assessment.

Radiomics derived from T2-FLAIR: the value of 2- and 3-classification tasks for different lesions in multiple sclerosis.

Background: White matter (WM) lesions can be classified into contrast enhancement lesions (CELs), iron rim lesions (IRLs), and non-iron rim lesions (NIRLs) based on different pathological mechanism in relapsing-remitting multiple sclerosis (RRMS). The application of radiomics established by T2-FLAIR to classify WM lesions in RRMS is limited, especially for 3-class classification among CELs, IRLs, and NIRLs. Methods: A total of 875 WM lesions (92 CELs, 367 IRLs, 416 NIRLs) were included in this study. The 2-class classification was only performed between IRLs and NIRLs. For the 2- and 3-class classification tasks, all the lesions were randomly divided into training and testing sets with a ratio of 8:2. We used least absolute shrinkage and selection operator (LASSO), reliefF algorithm, and mutual information (MI) for feature selection, then eXtreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) were used to establish discrimination models. Finally, the area under the curve (AUC), accuracy, sensitivity, specificity, and precision were used to evaluate the performance of the models. Results: For the 2-class classification model, LASSO classifier with RF model showed the best discrimination performance with the AUC of 0.893 (95% CI: 0.838-0.942), accuracy of 0.813, sensitivity of 0.833, specificity of 0.781, and precision of 0.851. However, the 3-class classification model of LASSO with XGBoost displayed the highest performance with the AUC of 0.920 (95% CI: 0.887-0.950), accuracy of 0.796, sensitivity of 0.839, specificity of 0.881, and precision of 0.846. Conclusions: Radiomics models based on T2-FLAIR images have the potential for discriminating among CELs, IRLs, and NIRLs in RRMS.

Cross-sectional and longitudinal evaluation of white matter microstructure damage and cognitive correlations by automated fibre quantification in relapsing-remitting multiple sclerosis patients.

The purpose of this study was to characterize whole-brain white matter (WM) fibre tracts by automated fibre quantification (AFQ), capture subtle changes cross-sectionally and longitudinally in relapsing-remitting multiple sclerosis (RRMS) patients and explore correlations between these changes and cognitive performance A total of 114 RRMS patients and 71 healthy controls (HCs) were enrolled and follow-up investigations were conducted on 46 RRMS patients. Fractional anisotropy (FA), mean diffusion (MD), axial diffusivity (AD), and radial diffusivity (RD) at each node along the 20 WM fibre tracts identified by AFQ were investigated cross-sectionally and longitudinally in entire and pointwise manners. Partial correlation analyses were performed between the abnormal metrics and cognitive performance. At baseline, compared with HCs, patients with RRMS showed a widespread decrease in FA and increases in MD, AD, and RD among tracts. In the pointwise comparisons, more detailed abnormalities were localized to specific positions. At follow-up, although there was no significant difference in the entire WM fibre tract, there was a reduction in FA in the posterior portion of the right superior longitudinal fasciculus (R_SLF) and elevations in MD and AD in the anterior and posterior portions of the right arcuate fasciculus (R_AF) in the pointwise analysis. Furthermore, the altered metrics were widely correlated with cognitive performance in RRMS patients. RRMS patients exhibited widespread WM microstructure alterations at baseline and alterations in certain regions at follow-up, and the altered metrics were widely correlated with cognitive performance in RRMS patients, which will enhance our understanding of WM microstructure damage and its cognitive correlation in RRMS patients.

Interpretable and Intuitive Machine Learning Approaches for Predicting Disability Progression in Relapsing-Remitting Multiple Sclerosis Based on Clinical and Gray Matter Atrophy Indicators.

RATIONALE AND OBJECTIVES: To investigate whether clinical and gray matter (GM) atrophy indicators can predict disability in relapsing-remitting multiple sclerosis (RRMS) and to enhance the interpretability and intuitiveness of a predictive machine learning model. MATERIALS AND METHODS: 145 and 50 RRMS patients with structural MRI and at least 1-year follow-up Expanded Disability Status Scale (EDSS) results were retrospectively enrolled and placed in the discovery and external test cohorts, respectively. Six clinical and radiomics feature-based machine learning classifiers were trained and tested to predict disability progression in the discovery cohort and validated in the external test set. Partial dependence plot (PDP) analysis and a Shiny web application were conducted to enhance the interpretability and intuitiveness. RESULTS: In the discovery cohort, 98 patients had disability stability, and 47 patients were classified as having disability progression. In the external test set, 35 patients were disability stable, and 15 patients had disability progression. Models trained with both clinical and radiomics features (area under the curve (AUC), 0.725-0.950) outperformed those trained with clinical (AUC, 0.600-0.740) or radiomics features only (AUC, 0.615-0.945). Among clinical+ radiomics feature models, the logistic regression (LR) classifier-based model performed best, with an AUC of 0.950. Only the radiomics feature-only models were applied in the external test set due to the data collection problem and showed fair performance, with AUCs ranging from 0.617 to 0.753. PDP analysis showed that female patients and those with lower volume, surface area, and symbol digit modalities test (SDMT) scores; greater mean curvature and age; and no disease modifying therapy (DMT) had increased probabilities of disease progression. Finally, a Shiny web application (https://lauralin1104.shinyapps.io/LRshiny/) was developed to calculate the risk of disability progression. CONCLUSION: Interpretable and intuitive machine learning approaches based on clinical and GM atrophy indicators can help physicians predict disability progression in RRMS patients for clinical decision-making and patient management.

Multimodal Investigation of Deep Gray Matter Nucleus in Patients with Multiple Sclerosis and Their Clinical Correlations: A Multivariate Pattern Analysis Study.

Deep gray matter (DGM) nucleus are involved in patients with multiple sclerosis (MS) and are strongly associated with clinical symptoms. We used machine learning approach to further explore microstructural alterations in DGM of MS patients. One hundred and fifteen MS patients and seventy-one healthy controls (HC) underwent brain MRI. The fractional anisotropy (FA), mean diffusivity (MD), quantitative susceptibility value (QSV) and volumes of the caudate nucleus (CN), putamen (PT), globus pallidus (GP), and thalamus (TH) were measured. Multivariate pattern analysis, based on a machine-learning algorithm, was applied to investigate the most damaged regions. Partial correlation analysis was used to investigate the correlation between MRI quantitative metrics and clinical neurological scores. The area under the curve of FA-based classification model was 0.83, while they were 0.93 for MD and 0.81 for QSV. The Montreal cognitive assessment scores were correlated with the volume of the DGM and the expanded disability status scale scores were correlated with the MD of the GP and PT. The study results indicated that MS patients had involvement of DGM with the CN being the most affected. The atrophy of DGM in MS patients mainly affected cognitive function and the microstructural damage of DGM was mainly correlated with clinical disability.