Cognitive impairments are frequently evident early in the course of psychosis, often before illness onset and having substantial impact on functional outcomes. However, this has not yet produced markers with sufficient sensitivity and specificity to predict outcomes at the level of the individual or facilitate early intervention. This project will address this need by applying normative models ('cognitive growth charting') to cognitive measures derived from tens of thousands of healthy individuals and thousands of individuals with psychosis from four European countries in order to infer early risk factors and predict functioning in psychosis at the individual level. We will go beyond symptoms and assess functioning broadly using measures that meaningfully reflect the quality of life of individuals with psychosis. We will: (i) develop deep learning technology to enable cognitive data from studies with heterogeneous cognitive data to be aggregated; (ii) map lifespan variation across multiple cognitive domains and precisely place individuals within population norms (iii) integrate these with neurobiology in order to precisely stratify cohorts, predict progression at the individual level and identify genetic and environmental factors that modulate developmental trajectories both preceding and following illness onset. Our project will be guided throughout by extensive engagement with lived experience experts.

The growth and extensible research in active implantable medical devices (AIMDs) have provided the opportunity for continuous and remote monitoring of patients with chronic illness. But the major technological challenge is that most of the implants operate on batteries with limited durability. It is difficult to replace these implants as human tissues grow around them and requires surgeries for their removal, which are costly and stressful for the patients. Moreover, battery replacement surgeries require hospital stays which is an additional risk in this era of pandemics like COVID-19. So, the sustainability and eventual fate of implantable medical devices depends on its capability for long-term use. Most of the AIMDs are equipped with wireless communication systems for data transfer, device monitoring and reprogramming. In this regard, I propose that energy harvesting from radio frequency (RF) signals for a wireless communication system provides a new paradigm called Simultaneous Wireless Information and Power Transmission (SWIPT) that can allow the wireless implant nodes to recharge their batteries from the RF data signals. In the literature, SWIPT has been studied for in-door and outdoor environment and has investigated transmission of high energy levels with large antenna dimensions for harvesting energy. There have been no studies in the literature for investigating SWIPT within the human body. My research project will explore and untap the potential of SWIPT for the human body environment. The major outcomes of the project include: 1) optimum energy-capacity function and the end-to-end analytical model of SWIPT for deep implants; 2) hardware design of SWIPT for implant communication systems; and 3) feasibility of the novel SWIPT architecture for medical implant technology by in-vitro liquid phantom models and in-vivo living animal experimental studies. The new fundamental knowledge developed from the project could be applied to multiple other domains.

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.

Even the perfect cancer drug must reach its target to have an effect. The ImPRESS project main objective is to develop a novel imaging paradigm coined Restricted Perfusion Imaging (RPI) to reveal - for the first time in humans - vascular restrictions in solid cancers caused by mechanical solid stress, and use RPI to demonstrate that alleviating this force will repair the cancerous microenvironment and improve therapeutic response. Delivery of anti-cancer drugs to the tumor is critically dependent on a functional vascular bed. Developing biomarkers that can measure how mechanical forces in a solid tumor impair perfusion and promotes therapy resistance is essential for treatment of disease. The ImPRESS project is based on the following observations; (I) pre-clinical work suggests that therapies targeting the tumor microenvironment and extracellular matrix may enhance drug delivery by decompressing tumor vessels; (II) results from animal models may not be transferable because compressive forces in human tumors in vivo can be many times higher; and (III) there are no available imaging technologies for medical diagnostics of solid stress in human cancers. Using RPI, ImPRESS will conduct a comprehensive series of innovative studies in brain cancer patients to answer three key questions: (Q1) Can we image vascular restrictions in human cancers and map how the vasculature changes with tumor growth or treatment? (Q2) Can we use medical engineering to image solid stress in vivo? (Q3) Can RPI show that matrix-depleting drugs improve patient response to conventional chemo- and radiation therapy as well as new targeted therapies? The ImPRESS project holds a unique position to answer these questions by our unrivaled experience with advanced imaging of cancer patients. With successful delivery, ImPRESS will have a direct impact on patient treatment and establish an imaging paradigm that will pave the way for new scientific knowledge on how to revitalize cancer therapies.