OTHER FUNCTIONS SCALABLE AUTOMATED BRAIN TUMOR SEGMENTATION

Infotech Soft, Inc., Miami FL

Investigators

Abstract

Brain tumor segmentation in Magnetic Resonance Imaging is an important task for neurosurgeons, oncologists, and radiologists to assess disease burden and measure tumor response to treatment. In 2008, over 237,000 individuals worldwide are estimated to have been diagnosed with malignant brain and central nervous system tumors with over 174,000 deaths. Detection of brain tumors with the exact location and orientation is extremely important for effective diagnosis, treatment planning, and analysis of treatment effectiveness; however, manual delineation of the tumor takes considerable time and is prone to error and wide variability. The overall goal of this proposal is to develop a scalable and automated approach for the segmentation of brain tumors based on Hidden Markov Models (HMMs). The objectives of the project are: 1) Develop a tumor segmentation approach based on a novel utilization of HMMs for automated segmentation of multi-sequence brain MRI data for accurate and robust determination of tumor volume; 2) Design a MapReduce model for the HMM-based brain tumor segmentation approach to enable scalable development of the segmentation processes in a cluster environment; 3) Evaluate the HMM-based brain tumor segmentation framework in terms of accuracy, robustness, and performance in the context of multi-sequence MRI data.