Browsing by Subject "transcranial magnetic stimulation (TMS)"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    How anatomical details affect noninvasive brain stimulation in computational models
    (2023-01) Mantell, Kathleen
    Noninvasive brain stimulation (NIBS) is an exciting field of study that is becoming increasingly popular for its many therapeutic uses. Two of the most widely used types of NIBS are transcranial electric and magnetic stimulation (TES and TMS). NIBS takes advantage of the electrical properties of neurons by modifying neuronal behavior through externally applied electric fields. This is achieved by either passing a current through two or more electrodes (TES) or inducing electric fields via a time varying magnetic field (TMS). Today, the biggest problems facing the NIBS field are the variability of responses in experiments and clinical settings and translating findings from animal studies to humans. To work to address these problems, we employ the power of computational modeling, specifically finite element method (FEM) modeling. FEM modeling allows us to build head models and simulate TMS and TES induced electric fields. However, there are many factors that go into building accurate models and it is not always clear how important they are in estimating the NIBS induced electric fields. Therefore, in this dissertation I explain how we look at three different factors in building FEM models: inclusion of stroke lesions in pediatric models, changing head model size, and inclusion of muscle tissue. In this work we found that stroke lesions greatly influence variability of the TMS induced electric field, either increasing or decreasing the electric field strength depending on the TMS coil location. This indicates that individualized head models are key to planning future experiments because the complex morphology does not allow us to make a simple prediction about the electric field. Next, we found that head size plays a significant role in NIBS induced electric fields, both in spherical models and non-human primate (NHP) models. For TES the electric field strength exponentially decreases with increasing head size. But the TMS induced electric field strength first increases with head size and then decreases after a critical point based on the TMS coil size. Finally, we determined that muscle tissue is an important feature in NHP models for TES simulations and it increases the electric field strength, but the percent change can be influenced by anisotropic properties of the muscle. Overall, these results from modeling nonstandard cases suggest that individualized modeling with careful consideration of the model setup is vital to accurately predicting NIBS induced electric fields.
  • Thumbnail Image
    Item
    Hyperdimensional Computing based Classification and Clustering: Applications to Neuropsychiatric Disorders
    (2023-12) Ge, Lulu
    Since its introduction in 1988, hyperdimensional computing (HDC), also referred to as vector symbolic architecture (VSA), has attracted significant attention. Using hypervectors as unique data points, this brain-inspired computational paradigm represents, transforms, and interprets data effectively. So far, the potential of HDC has been demonstrated: comparable performance to traditional machine learning techniques, high noise immunity, massive parallelism, high energy efficiency, fast learning/inference speed, one/few-shot learning ability, etc. In spite of HDC’s wide range of potential applications, relatively few studies have been conducted to demonstrate its applicability. To this end, this dissertation focuses on the application of HDC to neuropsychiatric disorders: (a) seizure detection and prediction, (b) brain graph classification, and (c) transcranial magnetic stimulation (TMS) treatment analysis. We also develop novel clustering algorithms using HDC that are more robust than the existing HDCluster algorithm. In order to detect and predict seizures, intracranial electroencephalography (iEEG) data are analyzed through the use of HDC-based local binary pattern (LBP) and power spectral density (PSD) encoding. Our study examines the effectiveness of utilizing all features as well as a small number of selected features. Our results indicate that HDC can be used for seizure detection, where PSD encoding is superior to LBP encoding. We observe that even three features are efficient in detecting seizures with PSD encoding. However, in order to pave the way for seizure prediction using HDC, more efficient features must be explored. For the classification of brain graphs, data from functional magnetic resonance imaging (fMRI) are analyzed. Brain graphs describe the functional brain connectome under varying brain states, and are generated from the fMRI data collected at rest and during tasks. The brain graph structure is assumed to vary from task to task and from task to no task. Participants are asked to execute emotional and gambling tasks, but no tasks are assigned during resting periods. GrapHD, an HDC-based graph representation, initially developed for object detection, is herein expanded for the application to brain graph classification. Experimental results demonstrate that GrapHD encoding has the capability of classifying the brain graphs for three binary classification problems: emotion vs. gambling, emotion vs. no-task, and gambling vs. no-task. Furthermore, GrapHD requires fewer memory resources as compared to the extant HDC-based encoding approaches. In terms of clustering, HDCluster, an HDC-based clustering algorithm, has been proposed in 2019. Originally designed to mimic the traditional k-means, HDCluster exhibits higher clustering performance across versatile datasets. However, we have identified that the performance of the HDCluster may be significantly influenced by the random seed used to generate the seed hypervectors. To mitigate the impact of this random seed, we propose more robust HDC-based clustering algorithms, designed to outperform HDCluster. Experimental results substantiate that our HDC-based algorithms are more robust and capable of achieving higher clustering performance than the HDCluster. In the analysis of TMS treatment, we conduct two specific tasks. One is to identify the clinical trajectory patterns for patients who suffer from major depressive disorder (MDD) (Clustering). Another is to predict MDD severity using 34 measured cognitive variables (Classification). For clustering, we propose a novel HDC-based algorithm that manipulates HDCluster to determine the number of clusters for a system of clinical trajectories. For classification, we utilize two HDC-based encoding algorithms and examine the impact of using either all features or selected features. Experimental results indicate that our HDC algorithm mirrors the clustering pattern of the classical algorithm. Additionally, the HDC-based classifier effectively predicts the concept of clinical response.