AutoRegister: A system for enhancing the accuracy of tumor change detection

PROJECT SUMMARY This project proposes to continue the development of AutoRegisterTMan integrated software based system for enhancing the accuracy of tumor change detectionThe intent of the system is to automate the alignment of a patient s brain scan with that of a prior scan such that subsequent offline tumor measurements do not have error introduced solely by differing slice orientationsWhile similar to current technologiessuch as Siemens AutoAlignthe proposed technology is not sensitive to the inherent noise of such genericlandmark based techniquesAutoRegisterTM exemplifies personalized medicineit uses the patient s previous data as its own referenceAdditionallythe proposed technology is based upon a novel registration algorithm that is robust to atypical anatomysuch as a tumorwhich often adversely affects techniques such as AutoAlignIn the United Statesthere are an estimateddeaths per year due to tumors in the primary central nervous systemStandard and experimental therapies rely on accurate measurement of tumor size change to assess treatment response and guide clinical decision making during treatment and clinical trialsThe project will continue to translate existing technology developed by CorticoMetrics and the Martinos Center for Biomedical Imaging at the Massachusetts General HospitalMGHOur objectives are tocreate a commercial readyand regulatory compliantsoftware medical device based on work conducted in Phase Ifurther develop our reference integration with Siemens MRI scanners for validationdemonstration and research purposesandcontinue to gather validation data with the ongoing assistance of Phase I collaborators conducting imaging of glioblastoma patientsand by establishing new collaborationsAutoRegisterTM employs a novelD MR image registration algorithm designed by advisors DrsReuter and Fischlwhich achieves highly accurate alignment both within subject and within modalityand ignores brainimaging voxels for which no feasible matches exists due to inherent changessuch as tumor tissue and surrounding localized mass or edema effectsThe co PI on the projectDrvan der Kouweis a renowned MRI head motion correction expert and is the original creator of SiemensAutoAlignthe closest competitor to the CorticoMetricsAutoRegisterTM system