Level-set segmentation of brain tumors using a threshold-based speed function

The level set approach can be used as a powerful tool for 3D segmentation of a tumor to achieve an accurate estimation of its volume. A major challenge of such algorithms is to set the equation parameters, especially the speed function. In this paper, we introduce a threshold-based scheme that uses level sets for 3D tumor segmentation (TLS). In this scheme, the level set speed function is designed using a global threshold. This threshold is defined based on the idea of confidence interval and is iteratively updated throughout the evolution process. We propose two threshold-updating schemes, search-based and adaptive, that require different degrees of user involvement. TLS does not require explicit knowledge about the tumor and non-tumor density functions and can be implemented in an automatic or semi-automatic form depending on the complexity of the tumor shape. The proposed algorithm has been tested on magnetic resonance images of the head for tumor segmentation and its performance evaluated visually and quantitatively. The experimental results confirm the effectiveness of TLS and its superior performance when compared with a region-competition based method.