MRI measurement of brain tumor response: comparison of visual metric and automatic segmentation

Feature extraction for MRI segmentation

Magnetic resonance images (MRIs) of the brain are segmented to measure the efficacy of treatment strategies for brain tumors. To date, no reproducible technique for measuring tumor size is available to the clinician, which hampers progress of the search for good treatment protocols. Many segmentation techniques have been proposed, but the representation (features) of the MRI data has received little attention. A genetic algorithm (GA) search was used to discover a feature set from multi-spectral MRI data. Segmentations were performed using the fuzzy c-means (FCM) clustering technique. Seventeen MRI data sets from five patients were evaluated. The GA feature set produces a more accurate segmentation. The GA fitness function that achieves the best results is the Wilks's lambda statistic when applied to FCM clusters. Compared to linear discriminant analysis, which requires class labels, the same or better accuracy is obtained by the features constructed from a GA search without class labels, allowing fully operator independent segmentation. The GA approach therefore provides a better starting point for the measurement of the response of a brain tumor to treatment.

Split-and-merge segmentation of magnetic resonance medical images: performance evaluation and extension to three dimensions

Intensity- or edge-based methods of segmentation are often insufficiently robust to be applied to images containing complex anatomical objects, such as those seen in high-resolution magnetic resonance imaging systems. Split-and-merge techniques attempt to overcome these difficulties by using homogeneity measures. Simple modifications to the basic 2D split-and-merge method, based on the principles of simulated annealing and controlled boundary elimination, are developed and discussed. Simulated annealing reduced the number of regions by 22% with a further reduction of 21% achieved through boundary elimination. Smoother regional boundaries are also produced. These methods are extended to true 3D and quantitatively compared with their 2D counterparts. The main advantage of 3D methods is that they produce segmented volumes by directly preserving the connectivity between slices, whereas in 2D, segments have to be grouped together in a post-split-and-merge process. Finally, the properties of the 3D approach are demonstrated by the automatic quantitation of brain ventricle volume, producing estimates to within 7% of validated manual methods.

Automatic tumor segmentation using knowledge-based techniques

A system that automatically segments and labels glioblastoma-multiforme tumors in magnetic resonance images (MRI's) of the human brain is presented. The MRI's consist of T1-weighted, proton density, and T2-weighted feature images and are processed by a system which integrates knowledge-based (KB) techniques with multispectral analysis. Initial segmentation is performed by an unsupervised clustering algorithm. The segmented image, along with cluster centers for each class are provided to a rule-based expert system which extracts the intracranial region. Multispectral histogram analysis separates suspected tumor from the rest of the intracranial region, with region analysis used in performing the final tumor labeling. This system has been trained on three volume data sets and tested on thirteen unseen volume data sets acquired from a single MRI system. The KB tumor segmentation was compared with supervised, radiologist-labeled "ground truth" tumor volumes and supervised k-nearest neighbors tumor segmentations. The results of this system generally correspond well to ground truth, both on a per slice basis and more importantly in tracking total tumor volume during treatment over time.