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.

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25, 256 MRI scans from 6, 314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing.