EuroSafe Imaging 2020
Action 12 - Information for and communication with patients, Artificial Intelligence, eHealth, Management, CT, Digital radiography, PACS, Computer Applications-General, Dosimetry, Radiation safety, Cancer, Retrospective, Diagnostic or prognostic study, Multicentre study
D. Koff, O. Boursalie, R. Samavi, T. E. Doyle
Medical imaging is a powerful clinical tool that allows health professionals to diagnose their patients without subjecting them to invasive surgery. Although the benefits of medical imaging exams are significant, there are ionizing radiation risks associated with every imaging exam that needs to be considered. Existing cancer risk models such as the linear-no-threshold (LNT) model  extrapolate the risk from high radiation exposure to the low-dose radiation emitted by medical imaging (Fig. 1). However, the effect of radiation risk from high to low levels remains experimentally unchallenged. In addition, health professionals are uncertain about how to factor a patient’s past radiation exposure when considering an imaging exam . Therefore, there is a need for the development of an analysis platform for improved radiation benefit-risk-dialogue.
We are currently developing a decision support system using deep learning to provide real-time risk assessment of radiation exposure from medical imaging relative to a patient’s medical history. In this study, we provide an overview of our decision support system. Our system will allow patients, radiologists, and medical researchers to evaluate if the benefits of performing the imaging study outweigh the potential cancer risks  from low dose radiation, which has increased in terms of frequency and dose over the last decade . Health professionals can then determine if the patient should proceed with conducting the imaging or resort to a lower-dose or non-ionizing modality. In addition, we propose an architecture to ensure the confidentiality and integrity of the sensitive health data being analyzed .