Rapid Mode Estimation for 3D Brain MRI Tumor Segmentation

The efficient definition of the tumor area is crucial in brain tumor resection planning. But current methods embedded in computer aided diagnosis systems can be time consuming, while the initialization of the segmentation mask may be possible. In this work, we develop a method for rapid automated segmentation of brain tumors.

The main contribution of our work is an efficient method to initialize the segmentation by casting it as nonparametric density mode estimation, and developing a Branch and Bound-based method to efficiently find the mode (maximum) of the density function. Our technique is exact, has guaranteed convergence to the global optimum, and scales logarithmically in the volume dimensions by virtue of recursively subdividing the search space through Branch-and-Bound and Dual-Tress data structures.

This estimated mode provides our system with an initial tumor hypothesis which is then refined by graph-cuts to provide a sharper outline of the tumor area.

We demonstrate a 12-fold acceleration with respect to a standard mean-shift implementation, allowing us to accelerate tumor detection to a level that would facilitate a high-degree brain tumor resection planning.