Context-sensitive Classication Forests for Segmentation of Brain Tumor Tissues
Darko Zikic, Ben Glocker, Ender Konukoğlu, Jamie Shotton, Antonio Criminisi, Dingding Ye, Çağatay Demiralp, Owen Thomas, Tilak Das, R. Jena, Stephen John Price · 2012
We describe our submission to the Brain Tumor Segmenta- tion Challenge (BraTS) at MICCAI 2012, which is based on our method for tissue-specic segmentation of high-grade brain tumors (3). The main idea is to cast the segmentation as a classication task, and use the discriminative power of context information. We realize this idea by equipping a classication forest (CF) with spatially non-local features to represent the data, and by providing the CF with initial probability estimates for the single tissue classes as additional input (along-side the MRI channels). The initial probabilities are patient-specic, and com- puted at test time based on a learned model of intensity. Through the combination of the initial probabilities and the non-local features, our approach is able to capture the context information for each data point. Our method is fully automatic, with segmentation run times in the range of 1-2 minutes per patient. We evaluate the submission by cross- validation on the real and synthetic, high- and low-grade tumor BraTS data sets.