Webinar: Accelerating Image-Based Knee Osteoarthritis Research Using Deep Learning, Part 1 of 2
Using deep learning to automatically assess individuals' disease status from medical images is an active area of research that is poised to change how outcomes are measured in our field. In this webinar, Kevin Thomas from Stanford University discusses his research on using deep learning models to automatically analyze knee X-rays and MRIs of individuals with osteoarthritis. His models produced results that agreed with experts as closely as experts agree with one another. He also shares tips and tricks for conducting similar analyses in your own research.
This webinar is offered jointly with the Restore Center (https://restore.stanford.edu/), an NIH-funded Medical Rehabilitation Research Resource Network Center at Stanford University.
Watch Part 2 of this webinar that covers strategies for training high-performing deep learning models using examples from our osteoarthritis research: • Webinar: Accelerating Image-Based Knee Ost...
Additional resources:
Visit our website that's running machine learning-based tools for both X-ray and MRI analysis (https://kl.stanford.edu/)
Docker container for the X-ray algorithm: https://github.com/stanfordnmbl/kneen...
Github repository for the code for the segmentation, T2 calculations, and comparison of results of the MR-based model: https://github.com/kathoma/AutomaticK...
Publications:
Automated Classification of Radiographic Knee Osteoarthritis Severity Using Deep Neural Networks (https://pubs.rsna.org/doi/full/10.114...)
Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning (https://arxiv.org/abs/2012.12406)