Objective, MRI biomarkers for pre-symptomatic detection of autism spectrum disorder at 6 months old: commercial software development and optimization

Project Summary Autism Spectrum DisorderASDis a broad diagnosis for a disorder characterized by symptoms affecting repetitive behaviorsocial communicationand cognitive abilityinchildren in the US is affected with ASDCenters for Disease Control and Preventionand the likelihood that a child will be affected with ASD istimes higher if they have a sibling with ASDTraditionallydiagnosis occurs most frequently between agetoand severe ASD can be diagnosed as early asmonthsThe infant brain is most plastic and susceptible to intervention in the first year of lifeAs suchthere exists an infant population that is either diagnosed too late to receive a more effective intervention or with a false negative diagnosisor bothThusearlier prediction of the development of ASD can deliver improved likelihood of favorable outcomesThis Fast Track proposal seeks to developstandardizeand commercialize software methods and algorithms for neurobehavioral disorder predictioncreating objective biomarkers in a space dominated by subjective neurobehavioral testing and providing a software as a medical device that is a singleintegratedeasy to use solution for MRI processinganalysisand syndrome predictionTo create a Minimum Viable ProductMVPwe willpull existingacademically vetted methods and software into a commercial design control processPhase ISAverify the integratedfull stack solution on a set of IBIS Network data sets stored in the National Database for Autism ResearchNDARand evaluate potential sources of classification errorPhase ISAand conduct an Alpha release to IBIS Network sites for user interface and human factors feedbackPhase ISAWe will build the MVP into a commercially viable product as weexpand the utility of the pipeline to accommodate data sets not acquired at IBIS Network sitesoptimize manual Quality ControlQCworkflows through semi automated user interface designintegrate cortical surface areacortical volumefunctional connectivityand other measurements into a common user interface and workflowmigrate image processingmachine learningand database infrastructure to cloud based tools that can scale on demandand iterate on the user experience given Alpha feedbackPhase IISAevaluate synthetic data designed to approximate results from multiple MRI scanner types and signal to noise ratio conditions to ensure broad applicability of the software in clinical settingsexpand the utility of the machine learning feature analysis and classification to include additional features and evaluate non binary feature spacesconduct latent variable analysis to identify one or more scale metrics for ASD predictionand vet the new metrics through a thorough review of IBIS Network data and comparison with Alpha release resultsPhase IIISAand develop a data report for clinical use and patient educationconduct a Beta release test across IBIS Network sites and at least one non IBIS Network siteand perform formal software verification and validation to prepare for broader distribution of the software platformPhase IIISANarrative MRI technology is rapidly advancing our understanding of how the brain develops in the presence of neurobehavioral disorders like Autism Spectrum DisorderASDThis Fast Track proposal seeks to developstandardizeand commercialize software methods and algorithms for ASD prediction using structural and functional MRI data acquired on infantscreating objective biomarkers in a space dominated by subjective neurobehavioral testing and providing a software as a medical device that is a singleintegratedeasy to use solution for MRI processinganalysisand prediction of syndrome developmentThis technology will provide first of its kindobjectivebrain based biomarkers that will enable development of effectiveearly interventions and improve the standard of care for infants at high risk of developing ASD