Neuroinformatics platform using machine learning and content-based image retrieval for neuroscience image data

This project aims to develop NeuroManageran innovative neuroinformatics platform for advanced parsingstoringaggregatinganalyzing and sharing of complex neuroscience image dataA core technology that we will develop in NeuroManager will be Image Content Analysis for Retrieval Using SemanticsICARUSa novelintelligent neuroimage curation system that will enable image retrieval based on visual appearance or by semantic conceptICARUS will use machine learning applied to content based image retrievalCBIRto build and refine models that summarize microscopic and macroscopic image appearance and automatically assign semantic concepts to neuroimagesNeuroscience research generates extensivemultifaceted data that is considerably under utilized because access to original raw data is typically maintained by the source labOn the other handthere are many advantages in sharing complex image data in neuroscience researchincluding the opportunity for separate analysis of raw data by other scientists from another perspective and improved reproducibility of scientific studies and their resultsUnfortunatelynone of the neuroscience data sharing options that exist today fulfill all the needs of neuroscientistsTo solve this problemNeuroManager will include the following distinctsignificant innovationsiversatility for handling two dimensionalDand three dimensional neuroimaging data sets from animal models and humansiifunctionality to share complex datasets that extends secureprivacy controlled paradigms from institutionallaboratory based and even public domainsiiiflexibility to implement NeuroManager within an institute s IT infrastructureor on most cloud based virtualized environments including AzureGoogle Cloud Services and Amazon Web Servicesivand most importantlythe ICARUS technology for CBIR in neuroimaging data setsThe benefit of NeuroManager for the neuroscience research communitypharmacological and biotechnological Randamp Dand society in general will be to foster collaboration between scientists and institutionspromoting innovation through combined expertise in an interdisciplinary atmosphereThis will open new horizons for better understanding the neuropathology associated with several human neuropsychiatric and neurological conditions at various levelsi emacroscopicallymicroscopicallysubcellularly and functionallyultimately leading to an improved basis for developing novel treatment and prevention strategies for complex brain diseasesIn Phase I we will prove feasibility of this novel technology by developing prototype software that will perform CBIR onD whole slide images of coronal sections of entire mouse brains from ongoing research projects of our collaboratorsWork in Phase II will focus on developing the commercial software product that will include all of the innovations mentioned aboveA competing technology with comparable functionalityaddressing the full breadth of needs for modern neuroscience researchis currently not available commercially or otherwise Narrative There are many advantages in sharing complex image data in neuroscience researchincluding the opportunity for separate analysis of raw data by other scientists from another perspective and improved reproducibility of scientific studies and their resultshowever none of the neuroscience data sharing options that exist today fulfill all the needs of neuroscientistsThis project commercializes an innovative software for sophisticated advanced parsingstoringaggregatinganalyzing and sharing of complex neuroscience image dataincluding a novelintelligent neuroimage curation system that will enable content based neuroscience image search powered by machine learningthereby opening new horizons in neuroscience research collaborationsThis system will allow researchers to make new discoveries based on new studies that are currently not feasibleultimately providing the basis for developing novel treatments to prevent and fight complex brain diseases