This project proposes to continue the development of AutoRegisterTM: an integrated software-based system for enhancing the accuracy of tumor change detection. The 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 orientations. While similar to current technologies, such as Siemens AutoAlign, the proposed technology is not sensitive to the inherent noise of such generic, landmark-based techniques. AutoRegisterTM exemplifies personalized medicine: it uses the patient's previous data as its own reference. Additionally, the proposed technology is based upon a novel registration algorithm that is robust to atypical anatomy, such as a tumor, which often adversely affects techniques such as AutoAlign. In the United States, there are an estimated 13,000 deaths per year due to tumors in the primary central nervous system. Standard and experimental therapies rely on accurate measurement of tumor size change to assess treatment response and guide clinical decision-making during treatment and clinical trials. The project will continue to translate existing technology developed by CorticoMetrics and the Martinos Center for Biomedical Imaging at the Massachusetts General Hospital (MGH). Our objectives are to: 1) create a commercial-ready, and regulatory-compliant, software medical device based on work conducted in Phase I; 2) further develop our reference integration with Siemens MRI scanners for validation, demonstration and research purposes; and 3) continue to gather validation data with the ongoing assistance of Phase I collaborators conducting imaging of glioblastoma patients, and by establishing new collaborations. AutoRegisterTM employs a novel 3D MR image registration algorithm designed by advisors Drs. Reuter and Fischl, which achieves highly accurate alignment both within-subject and within-modality, and ignores brain- imaging voxels for which no feasible matches exists due to inherent changes, such as tumor tissue and surrounding localized mass or edema effects. The co-PI on the project, Dr. van der Kouwe, is a renowned MRI head-motion correction expert and is the original creator of Siemens' AutoAlign: the closest competitor to the CorticoMetrics' AutoRegisterTM system.
In clinical practice, detecting change in the size of a brain tumor is critical for diagnosis and treatment. However this remains a challenging task for surgeons and oncologists. Accurate measurement of a tumor using magnetic resonance imaging (MRI) is adversely affected by differences in the position of the patient's head at the time of each scan, typically spaced weeks or months apart. The proposed technology, AutoRegisterTM, greatly reduces this source of measurement variation with minimal change to the workflow of a neuroradiologist, allowing significantly more accurate tracking of tumor change than is currently possible.
