This paper presents a novel level set approach to simultaneous tissue segmentation and bias correction of Magnetic Resonance Imaging (MRI) images. We first model the distribution of intensity belonging to each tissue as a Gaussian distribution with spatially varying mean and variance. Then a sliding window is used to transform the intensity domain to another domain, where the distribution overlap between different tissues is significantly suppressed. A maximum likelihood objective function is defined for each point in the transformed domain, which is then integrated over the entire domain to form a variational level set formulation. Tissue segmentation and bias correction are simultaneously achieved via a level set evolution process. The proposed method is robust to initialization, thereby allowing automatic applications. Experiments on images of various modalities demonstrated the superior performance of the proposed approach over state-of-the-art methods.