Technology and Development Project 3c
Michael McNitt-Gray (University of California-Los Angeles), Berkman Sahiner (FDA), and Karen Drukker (University of Chicago)
Development of benchmarking methods for the various technology assessment and clinical tasks in COVID-19 research and translation.
MIDRC-MetricTree brought to you by Technology Development Project 3c/d
Critical Evaluation.
COVID-related proceedings papers from the SPIE Medical Imaging meeting, February 2021, were tabulated according to tasks and performance metrics. Potential limitations and pitfalls of some of these performance metrics were noted and will be incorporated in our recommendations.
Decision support.
Let us help you find the right metrics to evaluate performance of your AI/machine learning algorithm!
We are developing a decision tree tool to recommend appropriate performance metrics for different machine learning tasks. The purpose of this decision tree tool is to give advice to researchers on how to efficiently and effectively evaluate performance of their AI methods. Visit our decision tree.
Members:
Karen Drukker, PhD, University of Chicago, Tingting Hu, PhD, US Food and Drug Administration, Grace Hyun Kim, PhD, University of California Los Angeles, Michael McNitt-Gray, PhD,(lead), University of California Los Angeles, Berkman Sahiner, PhD, US Food and Drug Administration, Emily Townley, AAPM