Student Theses
Date of Award
Spring 5-19-2026
Document Type
Thesis
Language
English
First Advisor
Professor Vinay A. Vaishampayan
Second Advisor
Professor Xin Jiang
Third Advisor
Professor Lihong Li
Abstract
This thesis presents a comprehensive framework for the automated tracking and visualization of articulatory movements based on magnetic resonance imaging (MRI) data. A well-known data analysis tool for markerless pose estimation, known as DeepLabCut, is investigated for this purpose. The performance of this tool is enhanced through the design and implementation of a pre-processor. DeepLabCut is a markerless pose estimation toolbox based on deep learning, which overcomes the issue of making manual annotations frame-by-frame. Limitations from manually marking the MRI images are addressed by implementing transfer learning with convolutional neural networks to achieve accurate, user-defined articulator tracking without markers. Current clinical and research approaches to assessing articulation rely on invasive markerbased tracking systems which significantly hinders applicability in routine medical imaging workflows. In addition, existing pose estimation methods are not optimized for medical imaging data or user-defined anatomical features in constrained MRI environments. This thesis develops and validates the automated tracking framework specifically adapted for MRI articulator data, enabling objective, quantifiable assessment of articulation for clinical diagnosis, treatment monitoring, and motor control research.
Recommended Citation
De George, Michael, "Visualization and Marker-less Tracking of User-Defined Pre-Processed MRI Articulator Data Using Deep Learning" (2026). CUNY Academic Works.
https://academicworks.cuny.edu/si_etds/23
Included in
Biomedical Commons, Biomedical Devices and Instrumentation Commons, Signal Processing Commons, Systems and Integrative Engineering Commons
Comments
Faculty signature was verified and then removed for privacy and security purposes