LATTICE: A Software Platform for Prospective and Retrospective Image Based Translational Research

PROJECT SUMMARY Imaging forms the backbone of living subjects researchLiving subjects research is both essential to the progress of translational medicine and very expensiveThe research community actively seeks to develop and validate new clinical endpoints to solve a range of etiologynatural historydiagnostic and prognostic problemsThis project aims to develop and commercialize LATTICEan Electronic Research RecordImage Management and Sharing Solutionand Deep Learning PlatformLATTICE is designed to increase the efficiency of imaging driven biomedical research and clinical trialsThis efficiency is accomplished first through a structured workflow that includes protocol managementsubject schedulingand records collection from multiple imaging modalitiesAccess to imaging and associated data within the same workflow simplifies the process for the research teamStructuring the data into a de identifiedprivacy managed Image Bank enables sharing for collaboration and re use for retrospective researchImage processing algorithms connected to the Image Bank facilitate batch analysiswhile the system also provides a platform for the development of new image based outcome measures and clinical endpointsA key objective of LATTICE is to enable investigators and collaborators to accelerate the translation of insights to the clinic with maximum efficiencySuccessful translation requires structuring the workflowrecord keepingand protocols into a rigoroustransparentreproducible and validated processLATTICE is designed to reduce the friction in translating successful research projects to the clinicResearchers in the Advanced Ocular Imaging ProgramAOIPat the Medical College of Wisconsin developed elements of LATTICE as separate technologiesThe Specific Aims of this proposal are directed to an integrated workflow addressing a broader set of objectivesThe AOIP LATTICE Electronic Research Record will be translated into a commercially managed repository and brought under regulatory Design ControlThe current AOIP Image Bank containingdeidentified retinal images will be integrated into the LATTICE workflowCriticallythis integration will allow the sharing of the Image Bank with external researchersThree retinal image process algorithms that operate on retinal images will integrate into this workflowThese algorithms include analysis of adaptive optics images of the fundusanalysis of the foveal avascular zone from optical coherence tomography angiographyOCTAand model based analysis of the fovea imaged with OCTA computational deep learning workflow will also be prototyped using a cloud based architectureThis final workflow will be constructed to demonstrate the feasibility of deploying a collaborative deep learning environment for the development of new clinical endpoints using sharedde identified imagesLATTICE will be a unique system for both prospective and retrospective translational researchLATTICE will make a profound impact on the cost of managing image based research and add leverage to translational research expenditures for moving insights into the clinic PROJECT NARRATIVE LATTICE is an innovative electronic research record and development platform for image based ophthalmic researchLATTICE is designed to reduce the cost of translational researchpromote the reuse of imagesand simplify the development and application of new techniques to analyze medical imagesLATTICE will integrate research workflow tools with a database ofretinal images and advanced image processing software to accelerate the process of translating eye research insights from the lab to the clinic