We present a novel methodology for the automated segmentation of Glioblastoma Multiforme tumors given only a high-resolution
T1 post-contrast enhanced channel, which is routinely done in clinical MR acquisitions. The main
contribution of the paper is the integration of contextual filter responses, to obtain a better class separation of abnormal
and normal brain tissues, into the multilevel segmentation by weighted aggregation (SWA) algorithm. The SWA
algorithm uses neighboring voxel intensities to form an affinity between the respective voxels. The affinities are then
recursively computed for all the voxel pairs in the given image and a series of cuts are made to produce segments that
contain voxels with similar intensity properties. SWA provides a fast method of partitioning the image, but does not
produce segments with meaning. Thus, a contextual filter response component was integrated to label the aggregates as
tumor or non-tumor. The contextual filter responses were computed via texture filter responses based on the gray level
co-occurrence matrix (GLCM) method. The GLCM results in texture features that are used to quantify the visual
appearance of the tumor versus normal tissue. Our results indicate the benefit of incorporating contextual features and
applying non-linear classification methods to segment and classify the complex case of grade 4 tumors.
This work focuses on image retrieval utilizing principal component analysis (PCA) and linear discriminant analysis (LDA) techniques for brain tumors from Magnetic Resonance (MR) studies. The research has been broken into three stages. Stage 1 consists of developing the PCA and LDA algorithms to be used for content based image retrieval (CBIR) systems. Stage 2 consists of evaluation of PCA and LDA algorithms on synthetic tumor images with added noise and shading artifacts. Stage 3 consists of tailoring the algorithm specifically for automated detection and CBIR system of MR contrast enhancing tumors matching a given query image. The algorithm has been developed and tested successfully for synthetic tumor images and actual contrast enhanced tumors. We hope to integrate the PCA and LDA algorithms to perform an indexing of the tumor shapes derived from actual MR images. Two relevant indices: size and location will also be used to index the data.