Combining Outlier Detection with Random Walker for Automatic Brain Tumor Segmentation

The diagnosis of brain neoplasms has been facilitated by the emerging of high-quality imaging techniques, such as Magnetic Resonance Imaging (MRI), while the combination of several sequences from conventional and advanced protocols has increased the diagnostic information. Treatment planning and therapy follow-up require the detection of neoplastic and edematous tissue boundaries, a very time consuming task when manually performed by medical experts based on the 3D MRI data. Automating the detection process is challenging, due to the high diversity in appearance of neoplastic tissue among different patients and, in many cases, similarity between neoplastic and normal tissue. In this paper, we propose an automatic brain tumor segmentation method based on a multilabel multiparametric random walks approach initialized by an outlier detection scheme. Segmentation assessment is performed by measuring spatial overlap between automatic segmentation and manual segmentation performed by medical experts. Good agreement is observed in most of the 26 cases for both neoplastic and edematous tissue. The highest achieved overlapping values were 0.74 and 0.79 for neoplastic and edematous tissue, respectively.