Accurate quantification of neurologic disease over time

ongoing

A research discovery has little relevance if it never makes an impact on its target users. A key challenge for radiology is that very few diagnostic innovations end up changing clinical practice. Most clinical decision-making processes follow the same hypothesis-driven approach where the association between a biomarker and disease status are assessed by trial-and-error. By forcing the patients’ data into traditional paradigms, we are inherently making poor use of the available information. Moreover, a new drug or change in treatment have little impact if the intervention is initiated at a late stage. For a patient with short life expectancy, this scenario is unacceptable. A new diagnostic paradigm is needed to catch disease status before it becomes symptomatic. Based on the work of an ERC Starting Grant, we introduce a new paradigm for clinical neuroimaging, coined synthetic biomaps, where artificial intelligence brings to life hidden information stored in diagnostic images. As an intelligent decision-support system, CHRONOS is a fully developed software prototype that enhance classical image analyses with synthetic biomaps to produce smarter and better diagnoses of disease. We showcase how a growing brain tumor change the entire architecture of the brain more than six months before these changes are observed by traditional means. This innovative step will allow the treating physician to make the correct clinical decisions at an unprecedented and early timepoint. We have integrated our invention in a hospital-approved digital framework that allows our clinical experts to validate the technology and demonstrate its clinical value. Our initial market analysis and a favorable search report show that a substantial commercial value can be realized by positioning CHRONOS at the center of a wider strategy of a new company to introduce sibling AI-imaging solutions. Τhis project aims to set the stage for an investor ready spinout company based on the CHRONOS technology.