Alzheimer's Amyloid and Tau Pathology Staging and Clinical Impact Prediction Using Multi-Modal MRI Pattern Classification

SUMMARY This Phase I grant will use innovative machine learning approaches and brain image data to address the critical need to identify the presence and extent of Alzheimer s disease pathology for clinical diagnosis and treatment evaluationMisdiagnosis rates currently exceedand diagnosis is not available in early stages of diseaseimpeding patient care and the development of effective treatmentsCombining innovations in machine learning with recently available information from tau PET imagingclassifier and regression models will be developed that can predict amyloid plaque and tau distributionusing structural and or functional magnetic resonance imagingMRIsequencesThese advances can greatly improve the earlyaccurate diagnosis of Alzheimer s diseaseenable the selection of patients for clinical trialsand aid in the development of effective new therapeuticsIn the first Specific Aimmultivariate machine learning classifiers will be developed using structural MRIfunctional MRIASLand FDG PET as a comparator to characterize amyloid and tau pathology and disease stage in patients with Alzheimer s disease ranging from presymptomatic through dementia stagesSecondwithin classifier and across classifier performance will be evaluated with respect to the objectives todiscriminate subjects with amyloid and tau pathologyprovide a metric of tau burden and spatial distribution using MRI and FDG PET modalitiesand identify neurodegenerative patterns that may reflect differences in clinical severity among patients with the same tau burden and distributionIn additionthe relationship between classifier scores and cognitive endpoints will be evaluatedThirdsimilar classifiers will be developed using structural MRI and FDG PET to characterize amyloid and CSF tau burden in a genetically predisposedearly onset AD populationand findings compared to those in the late onset AD populationThis work makes use of data acquired in the Alzheimer s Disease Neuroimaging InitiativeADNIthe DIAN study of early onset autosomal dominant Alzheimer s DiseaseADADand additional data setsInnovations of this work includeprediction of tau burden and distribution using imaging measures of neurodegenerationapplication of our machine learning methods and optimization to recently available modalities and measuresunique approaches in machine learning optimization and classifier designand the inclusion of Late Onset Alzheimer s DiseaseLOADand ADAD data sets and initial comparison between these forms of ADAchievement of these aims will result in diagnostic and prognostic image analysis tools to aid in accurate diagnosis and prognosis supporting patient care and the clinical evaluation of therapeutic interventions NARRATIVE! This Phase I grant uses innovative machine learning approaches and brain image data to address the critical need to diagnose the presence and extent of Alzheimer s disease pathology for clinical diagnosis and treatment evaluationUsing sophisticated software toolsalgorithms will be developed that can predict the amount of amyloid plaque and the distribution of aggregated tautwo hallmarks of Alzheimer s diseaseusing magnetic resonance imagingMRIthat is widely used in clinical trials and in the clinicThese advances can greatly improve the earlyaccurate diagnosis of Alzheimer s diseaseenable the selection of patients for clinical trialsand aid in the development of urgently needed effective therapeutics