Grant: Project Grant

This study addresses the challenges in diagnosing and treating osteoarthritis (OA), a joint disease lacking proven preventative treatments. Although joint motion is a key contributor to OA, current methods to assess joint motion are limited. Consequently, the causes of OA and joint degeneration are not understood. Dual fluoroscopy (DF) technology offers high-precision assessment of 3D joint motion using X-ray video, but its manual and time-consuming workflow has mainly restricted DF use to research of healthy joints. This research aims to overcome these obstacles and enhance our understanding of joint motion across the spectrum of healthy to OA. The goals of this research are to: 1. Automate our DF equipment setup and data processing 2. Demonstrate the ability of automated DF to quantify motion in healthy joints 3. Investigate how quantitative results from DF can be used to detect early signs of OA We will use engineering principles and machine learning to develop a seamless pipeline for automatic DF equipment setup and data processing. This automation will decrease data processing time from multiple days of labor-intensive processing to hours of automated processing, which will allow us to conduct more research, faster. This automation will also allow us to look at how healthy joints move compared to joints with deterioration or OA, which could help doctors diagnose and monitor disease. Finally, we will create a user-friendly software program that shows the bone motion obtained from DF. This software will allow doctors to interact with a patient's bone motion to improve individualized surgical planning. These technological advancements will revolutionize OA diagnosis, disease monitoring, and treatment planning for patients. Furthermore, these advancements will help us identify the causes of OA, pursue larger epidemiological studies about joint disease, and develop and test treatments that prevent or slow joint degeneration.