Hayit Greenspan – “AI for COVID-19: Developing the “Corona-Score” for patient monitoring using Deep Learning CT Image Analysis”
AI for COVID-19: Developing the “Corona-Score” for patient monitoring using Deep Learning CT Image Analysis
Prof. Hayit Greenspan – Tel Aviv University
In this talk I will show AI-based automated CT image analysis tools that show promise in supporting the detection of COVID_19 manifestations as well as in the quantification of disease burden. As such they need to be considered as a key tool in the diagnosis, and monitoring of CVID-19 patients.
In the last several years, Deep Learning computer-aided detection and diagnosis tools are being developed to support the detection, segmentation and the characterization tasks of the radiologist. Strong results have been achieved in this fast-advancing field, with the key challenge to build robust learning capabilities is the very limited expert-annotated datasets. I will present novel methods being developed in the medical imaging community to solve these data challenges. I will then show the translations of these tools towards the rapid development of a solution for the COVID-19 pandemic.
Utilizing the deep-learning image analysis system developed, we achieved classification results of above 95% AUC in the analysis of Coronavirus vs Non-coronavirus cases in thoracic CT studies, with an example working point of 98.2% sensitivity and 92.2% specificity. For Coronavirus patients the system outputs quantitative opacity measurements and a visualization of the opacities in a slice-based “heat map” or a 3D volume display. A suggested “Corona-score” measures the progression of patients over time.
Bio: Hayit Greenspan is a Full Professor of Biomedical Engineering in the Faculty of Engineering, Tel-Aviv University. Dr. Greenspan received the B.S. and M.S. degrees in Electrical Engineering (EE) from the Technion, and the Ph.D. degree in EE from CALTECH – California Institute of Technology. She was a Postdoc with the CS Division at U.C. Berkeley following which she joined Tel-Aviv University. From 2008 until 2011, she was a visiting Professor at Stanford University, Department of Radiology, Faculty of Medicine. She was also a visiting researcher at IBM Research in the Multi-modal Mining for Healthcare group, in Almaden CA.
Prof. Greenspan has 200 publications in leading international journals and conferences (h-index 47) and has received several awards and patents. She is member of several journal and conference program committees, including SPIE medical imaging, IEEE_ISBI and MICCAI. Hayit Chaired the Workshop sessions at MICCAI 2019 in Shenzhen, China, and served as a Program Chair for IEEE_ISBI in 2020. She served as an Associate Editor for the IEEE Trans on Medical Imaging (TMI) journal. In 2016 she was the Lead Co-editor for a Special issue on Deep Learning in Medical Imaging in IEEE TMI. In 2017 she Co-edited an Elsevier Academic Press book on Deep learning for Medical Image Analysis (”Most successful Title Published” in 2018). Recently she was titled as one of the Top-30 Women AI leaders in Drug Discovery and Advanced Healthcare, by Deep Knowledge Analytics (www.ai-pharma.dka.global/top-30-women).