Research Project
9967445
Project Summary Differentiation of tumor recurrence from radiation-induced necrosis (RN) is a critical step in the follow-up management of patients treated with stereotactic radiosurgery for brain tumor. A non-invasive method that is robust in discriminating RN from recurrent tumor using non-invasive method such as MRI is of a significant value for patients and physicians. The hypothesis of this proposed project is that advanced Machine-learning (ML) and image analysis of different MRI imaging information may hold potential for accurately detecting the difference between RN and recurrence of brain tumor is a substantial challenge in the daily practice in Neuro-Oncology. Furthermore, there is a need to study feasibility of translating our ongoing works in brain tumor volume quantitation into potential imaging device. Consequently, this Administrative Supplement propose the following Specific Aims for this study: Aim 1: To develop novel methods to discriminate RN from tumor recurrence in MRI. Aim 2: To develop and prepare a fast track SBIR proposal (Phase I and II combined) to be submitted soon after this Administrative Supplemental funding expires. If successful, robust discrimination of radiation-induced RN and tumor recurrence will make our current brain tumor and abnormal tissue volume segmentation methods and tools more robust and ready for use in the radiology and oncology practices. Furthermore, the planned SBIR project funding will lead the way to fully explore the possibility of launching a commercial software technology for brain tumor volume quantitation imaging device development.
