Radiology is struggling. Exponentially increasing quantities of data make it difficult to index and search for relevant information when it's needed most. Radiologists' workload is also rapidly increasing, exacerbated by the global radiologist shortage. What's more, new treatments require more complex diagnoses. When faced with a difficult case, radiologists must currently wait to discuss with colleagues, consult reference books or guess search terms in text-based resources. This frustrating, time-consuming process leads to delays, missed findings and high overtime expense. That's why contextflow develops deep-learning based tools to help improve radiologists’ daily clinical workflows. The core technology is a 3D image-based search engine called SEARCH designed to help save time and money while increasing reporting quality and confidence. Simply select a region of interest in any scan (currently we work with lung CTs), and SEARCH immediately provides reference cases based on visual disease pattern detection, statistics, and medical literature necessary for differential diagnosis, allowing the radiologist to obtain information directly from the image itself, shortening their search time from 20 min to 2 sec. TRIAGE is another tool designed to save time during clinical routine. By automatically detecting disease patterns as soon as a scan is taken, TRIAGE allows doctors to better prioritize patients based on critical need. Both tools search for disease patterns that are present in COVID-19, and SEARCH provides distribution heatmaps of these patterns, which may be helpful during image interpretation, hence why we have quickly pivoted to develop new COVID-19 functionalities within the last month. Most importantly, both tools integrate into the radiologist’s current routine, making adoption easy. While most competitors can only support 1-3 patterns, contextflow SEARCH takes a very different approach than what is on the market, searching for 19 patterns and counting in lung CTs, offering a much more holistic view of the patient. In addition, we have a patent pending on how to efficiently return similar patient cases when searching vast amounts of 3D medical imaging data upon selecting a region of interest. Founded by a team of AI and medical imaging experts in July 2016, contextflow is a spin-off of the Medical University of Vienna (MUW), Technical University of Vienna (TU) and European research project KHRESMOI. We are currently in our proof of concept phase with 10 partner hospitals and clinics throughout Europe.