Large-scale automatic analysis of the OAI magnetic resonance image dataset

• funded by: NIH via subcontract for UNC Chapel Hill
• funding level: $331,603
• duration: 8/15/2017 - 04/30/2022, no-cost extension to 4/23.

The goal of this proposal is to optimize and to openly provide to the osteoarthritis community a new technology to rapidly and automatically measure cartilage thickness, appearance and changes on magnetic resonance images (MRI) of the knee for huge image databases. This will allow assessment of trajectories of cartilage loss over time and associations with clinical outcomes on an unprecedented scale; future work will focus on incorporating additional disease markers, ranging from MRI-derived biomarkers for bone and synovial lesions, to biochemical biomarkers, to genetic information. NCSU will develop novel, efficiently parallelized codes and tools for pairwise, group-wise and longitudinal analysis of high-resolution MR images suitable for large image repositories with the potential to produce highly reproducible diagnostic and monitoring capabilities by exploiting massively parallel computing on an HPC cluster and cloud facilities.

Publications:

• "Hummingbird: Efficient Performance Prediction for Executing Genomics Applications in the Cloud" by Utsab Ray, Vandhana Krishnany, Amir Bahmani, Cuiping Pan, Keith Bettinger, Philip Tsao, Frank Mueller, Michael Snyder in Computational Approaches for Cancer Workshop, Nov 2018.
• A Workflow Hierarchy-Aware Fault Tolerance System by Subhendu Behera, Dong H. Ahn, Stephen Herbein, Frank Mueller and Barry L. Rountree, Refereed Poster at Supercomputing (SC'20) Nov 2020.