Showing papers by "Rajanikant Panda published in 2019"

Machine learning identifies “rsfMRI epilepsy networks” in temporal lobe epilepsy

Abstract: Experimental models have provided compelling evidence for the existence of neural networks in temporal lobe epilepsy (TLE). To identify and validate the possible existence of resting-state “epilepsy networks,” we used machine learning methods on resting-state functional magnetic resonance imaging (rsfMRI) data from 42 individuals with TLE. Probabilistic independent component analysis (PICA) was applied to rsfMRI data from 132 subjects (42 TLE patients + 90 healthy controls) and 88 independent components (ICs) were obtained following standard procedures. Elastic net-selected features were used as inputs to support vector machine (SVM). The strengths of the top 10 networks were correlated with clinical features to obtain “rsfMRI epilepsy networks.” SVM could classify individuals with epilepsy with 97.5% accuracy (sensitivity = 100%, specificity = 94.4%). Ten networks with the highest ranking were found in the frontal, perisylvian, cingulo-insular, posterior-quadrant, thalamic, cerebello-thalamic, and temporo-thalamic regions. The posterior-quadrant, cerebello-thalamic, thalamic, medial-visual, and perisylvian networks revealed significant correlation (r > 0.40) with age at onset of seizures, the frequency of seizures, duration of illness, and a number of anti-epileptic drugs. IC-derived rsfMRI networks contain epilepsy-related networks and machine learning methods are useful in identifying these networks in vivo. Increased network strength with disease progression in these “rsfMRI epilepsy networks” could reflect epileptogenesis in TLE. • ICA of resting-state fMRI carries disease-specific information about epilepsy. • Machine learning can classify these components with 97.5% accuracy. • “Subject-specific epilepsy networks” could quantify “epileptogenesis” in vivo.

Reappearance of Command-Following Is Associated With the Recovery of Language and Internal-Awareness Networks: A Longitudinal Multiple-Case Report.

Abstract: The recovery of patients with disorders of consciousness is a real challenge, especially at the chronic stage. After a severe brain injury, patients can regain some slight signs of consciousness, while not being able to functionally communicate. This entity is called the minimally conscious state (MCS), which has been divided into MCS- and MCS+, respectively based on the absence or presence of language-related signs of consciousness. In this series of cases we aimed to describe retrospectively the longitudinal recovery of specific language-related behaviors using neuroimaging measurement in severely brain-injured patients. Among 209 chronic MCS patients admitted to our center from 2008 to 2018, 19 were assessed at two time points by means of behavioral and neuroimaging assessments. Three of them met our inclusion criteria and were diagnosed as MCS- during their first stay and had recovered command-following when they were reassessed (i.e., MCS+). As compared to their first assessments, when the three patients were in a MCS+, they showed less hypometabolism and/or higher gray matter volume in brain regions such as the precuneus and thalamus, as well as the left caudate and temporal/angular cortices known to be involved in various aspects of semantics. According to these preliminary results, the reappearance of language-related behaviors was concomitant with the recovery of metabolism and gray matter in neural regions that have been associated with self-consciousness and language processing. Prospective studies should be conducted to deepen our understanding of the neural correlates of the recovery of language-related behaviors in chronic MCS.