This collaborative research project is comprised of MIDRC investigators from the University of Chicago and Moffitt Cancer Center who are investigating and developing open AI/ML algorithms for explainability and visualization of COVID, as well as exploring lessons learned from collaborations amongst the disciplines of radiology, medical imaging physics and computer science in confronting a global crisis such as COVID-19. The machine intelligence algorithms being developed by these investigators will ultimately contribute to the diagnosis, prognosis, response assessment and clinical decision making on thoracic radiographs and CTs for COVID-19 and other emerging problems in biomedicine. CRP 10-authored articles have been published in Medical Physics and the Journal of Medical Imaging.

Current plans include

• Develop machine intelligence for assessing image-based changes over time and assisting in clinical decision making of prognosis and response assessment of long COVID-19 on MRI and ultrasound images, especially of the brain and cardiac systems.

• Investigate and provide open algorithms for explainability/visualization of long COVID-19 AI on multi-modalities including CXR, CT, MRI, and ultrasound images, especially of the brain and cardiac systems.

• Rigorously evaluate and rapidly translate these findings to clinical practice to enable the urgent goals of MIDRC.