Machine Intelligence/Data Science in Medical Imaging of Breast Cancer and COVID-19
Join Dr. Maryellen L. Giger at the April NCI Imaging and Informatics Community Webinar for a discussion on the development, validation, database needs, and ultimate future implementation of artificial intelligence (AI) in the clinical radiology workflow, which will include case studies of breast cancer and COVID-19.
AI in medical imaging involves research in task-based discovery, predictive modeling, and robust clinical translation. Quantitative radiomic analyses, an extension of computer-aided detection and computer-aided diagnosis methods, are yielding novel image-based tumor characteristics, (i.e., signatures that may ultimately contribute to the design of patient-specific cancer diagnostics and treatments).
Beyond human-engineered features, deep convolutional neural networks (CNN) are being investigated in the diagnosis of disease through radiography, ultrasound, and MRIs. The method of extracting characteristic radiomic features of a lesion and/or background can be referred to as “virtual biopsies.” For radiologists, various AI methods are evolving with the potential to aid as second, concurrent, or primary autonomous readers. In addition, performance evaluations, as well as considerations of robustness and repeatability, are necessary to enable translation.
Dr. Giger is the A.N. Pritzker Distinguished Service Professor of Radiology, Committee on Medical Physics, and the College at the University of Chicago. Her AI research in breast cancer for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she has used these “virtual biopsies” in imaging-genomics association studies. She has extended her AI experience in medical imaging research to include the analysis of COVID-19 on CT and chest radiographs and is the primary principal investigator for the NIBIB-funded Medical Imaging and Data Resource Center.