A Combined Radiomics and Machine Learning Approach to Overcome the Clinicoradiologic Paradox in Multiple Sclerosis.

BACKGROUND AND PURPOSE: Conventional MR imaging explains only a fraction of the clinical outcome variance in multiple sclerosis. We aimed to evaluate machine learning models for disability prediction on the basis of radiomic, volumetric, and connectivity features derived from routine brain MR images. MATERIALS AND METHODS: In this retrospective cross-sectional study, 3T brain MR imaging studies of patients with multiple sclerosis, including 3D T1-weighted and T2-weighted FLAIR sequences, were selected from 2 institutions. T1-weighted images were processed to obtain volume, connectivity score (inferred from the T2 lesion location), and texture features for an atlas-based set of GM regions. The site 1 cohort was randomly split into training (n = 400) and test (n = 100) sets, while the site 2 cohort (n = 104) constituted the external test set. After feature selection of clinicodemographic and MR imaging-derived variables, different machine learning algorithms predicting disability as measured with the Expanded Disability Status Scale were trained and cross-validated on the training cohort and evaluated on the test sets. The effect of different algorithms on model performance was tested using the 1-way repeated-measures ANOVA. RESULTS: The selection procedure identified the 9 most informative variables, including age and secondary-progressive course and a subset of radiomic features extracted from the prefrontal cortex, subcortical GM, and cerebellum. The machine learning models predicted disability with high accuracy (r approaching 0.80) and excellent intra- and intersite generalizability (r ≥ 0.73). The machine learning algorithm had no relevant effect on the performance. CONCLUSIONS: The multidimensional analysis of brain MR images, including radiomic features and clinicodemographic data, is highly informative of the clinical status of patients with multiple sclerosis, representing a promising approach to bridge the gap between conventional imaging and disability.

Altered sensorimotor integration in multiple sclerosis: A combined neurophysiological and functional MRI study.

OBJECTIVE: To explore whether abnormal thalamic resting-state functional connectivity (rsFC) contributes to altered sensorimotor integration and hand dexterity impairment in multiple sclerosis (MS). METHODS: To evaluate sensorimotor integration, we recorded kinematic features of index finger abductions during somatosensory temporal discrimination threshold (STDT) testing in 36 patients with relapsing-remitting MS and 39 healthy controls (HC). Participants underwent a multimodal 3T structural and functional MRI protocol. RESULTS: Patients had lower index finger abduction velocity during STDT testing compared to HC. Thalamic rsFC with the precentral and postcentral gyri, supplementary motor area (SMA), insula, and basal ganglia was higher in patients than HC. Intrathalamic rsFC and thalamic rsFC with caudate and insula bilaterally was lower in patients than HC. Finger movement velocity positively correlated with intrathalamic rsFC and negatively correlated with thalamic rsFC with the precentral and postcentral gyri, SMA, and putamen. CONCLUSIONS: Abnormal thalamic rsFC is a possible substrate for altered sensorimotor integration in MS, with high intrathalamic rsFC facilitating finger movements and increased thalamic rsFC with the basal ganglia and sensorimotor cortex contributing to motor performance deterioration. SIGNIFICANCE: The combined study of thalamic functional connectivity and upper limb sensorimotor integration may be useful in identifying patients who can benefit from early rehabilitation to prevent upper limb motor impairment.