Development of perivascular space mapping toolset as a diagnostic aid for Alzheimer's disease

Project Summary Alzheimer’s disease (AD) is a devastating disease that affects millions of Americans and imposes a huge socio- economic burden. AD-related cognitive decline is associated with the accumulation of Amyloid plaques and tau tangles, which are insufficiently cleared by brain clearance pathways. Perivascular space (PVS) clearance health plays a substantial role in the net clearance of metabolic waste from the brain. Human magnetic resonance imaging (MRI) studies have shown that the integrity of the PVS, is a marker of brain clearance health and its alteration is an important feature of AD pathology. Another important clinical relevance of PVS in AD has been emerged by the introduction of the first classes of amyloid clearing treatments (e.g., Biogen:Aduhelm or Eisai:Lecanemab). Alzheimer’s patients with cerebral amyloid angiopathy comorbidity have high likelihood of manifesting an adverse event called, amyloid related imaging abnormalities (ARIA). PVS is a diagnostic criterion for cerebral amyloid angiopathy (based on BOSTON criteria 2.0). AD patients are required to go through MRI before and during the treatment for ARIA monitoring and PVS assessment is an integral part of the monitoring. PVS integrity is therefore an important clinical feature in Alzheimer’s disease and vascular dementia. Hence, a tool that allows non-invasive in-vivo mapping of PVS from clinical MRI is of high significance to aid AD diagnosis and disease monitoring. Such tool, however, does not exist. Current clinical routine to investigate PVS is based on counting total number of observed PVS in MRI by neuro-radiologists, which is non-specific, rater-dependent, and does not capture the distribution, whole extent of PVS change nor volumetric features of the PVS. In practice, this technique is time consuming and laborious. These limitations in part have prevented neurologists from adopting PVS quantification into their clinical routine. NeuroScope has developed computational techniques for mapping and quantifying PVS morphology from MRI, which enables automated and accurate quantification of PVS across the brain without the need for time consuming manual intervention. NeuroScope tools were clinically and technically validated (Phase-I-STTR deliverables), with >99.8% test-retest reliability, sensitivity, and specificity of >98% and >93%, respectively. Our patent application on our tools was also submitted in Feb 2021 and their executable stable version have been implemented on our cloud server. NeuroScope is now ready to build the commercial ecosystem that enables interaction with potential customers. The goal of this proposal is to develop the IT infrastructure required to commercialize our PVS mapping technologies and to submit FDA 510(K) application. Our main customers are pharmaceutical companies and hospital radiology sectors. The IT infrastructure is required to provide service in clinical trials and the FDA approval is required to expand our market domain to clinical diagnostics. NeuroScope has identified potential customers and have already made significant progress. Several industry leading companies shown interest in our technology.