“Investigating Musculoskeletal Disease Using Opportunistic Clinical CT Data: The Body Composition and Bone Platform (BCAB-CT).”
The aim of our study is to develop an open-source, python-based software package to analyze bone density, bone structure, muscle volume and density, and body composition from clinical CT images. To facilitate future analyses of extremely large clinical datasets, this software will store deidentified scans, segmentation masks and other analysis byproducts to train machine learning models for automated analysis of CT scan data.
Principal Investigators: Dr. Galateia Kazakia, Dr. Thomas Lang
"Maximizing Markerless Motion Capture Data Processing Speed: Enabling Efficient Reporting"
Markerless motion capture is a quickly growing technology for collecting high quality movement biomechanics. Although, the time required to analyze and create reports from collected data can limit the application of markerless motion capture in field settings. This project takes a three-fold approach to reducing the amount of time needed between data collection and report generation. We will identify the influence of data collection structure and data processing hardware on analysis time, before creating a data analysis pipeline that streamlines overall data reporting.
Principal Investigator: Nathan Edwards, PhD TSAC-F
Co-PIs: Joshua Hagen, PhD, Jaclyn Caccese, PhD, James Onate, AT PhD FNATA