Brain MRI Screening Tool with Federated Learning

Stoklasa, Roman, Stathopoulos, Ioannis, Karavasilis, Efstratios, Efstathopoulos, Efstathios, Dostál, Marek, Keřkovský, Miloš, Kozubek, Michal, Serio, Luigi

arXiv.org Artificial Intelligence 

The goal of our work is to develop a Screening Tool, software that would automatically evaluate all brain MRI scans In clinical practice, we often see significant delays between in a given hospital, and which would produce pre-diagnostic MRI scans and the diagnosis made by radiologists, even for reports for radiologists. Based on such reports, radiologists severe cases. In some cases, this may be caused by the lack could easily decide which examinations need to be processed of additional information and clues, so even the severe cases sooner and with higher priority, or, they might decide to process need to wait in the queue for diagnosis. This can be avoided if the "easy cases" first (i.e., cases that can be completed there is an automatic software tool, which would supplement quickly and easily), to increase diagnostic throughput. The additional information, alerting radiologists that the particular ultimate goal is to help decrease the waiting time between the patient may be a severe case. We are presenting an automatic scan and the diagnosis, especially for severe cases, by assisting brain MRI Screening Tool and we are demonstrating its capabilities radiologists to work more efficiently with better prioritization.