Incorporating global multiplicative decomposition and local statistical information for brain tissue segmentation and bias field estimation

Abstract

Medical image is a cornerstone of modern healthcare providing unique diagnostic. However, intensity nonuniformity is quite often found in medical images and unavoidably poses many challenges for precise image segmentation. In this paper, we present an incorporating global multiplicative decomposition and local statistical information level set technique for tissue segmentation and bias estimation that handles both high noise and intensity nonuniformity. An image can be factored into two multiplicative parts (namely, bias-free image and bias field), which are used to capture global intensity statistics. At the same time, our technique considers statistical information with not only the mean but also the variance. Pixel intensity generally fluctuates around its mean in a local region. The variance can adjust the disagreement of each pixel to its mean, and is explored to overcome the effects of intensity nonuniformity. Finally, the level set energy formulation is in the form of the global multiplicative decomposition and local statistical information. To verify the availability of our technique, we have thoroughly experimented on composite and real images. Our techniques are also applied to the lesion regions of brains. Experimental results display that our technique can segment different kinds of images with high noise and intensity nonuniformity more accurately, and outperforms other solutions in comparison.