The Effect of Spectral Resolution Upon the Accuracy of Brain Tumor Segmentation from Multi-Spectral MRI Data

Abstract

Ensemble learning methods are frequently employed for brain tumor segmentation from multi-spectral MRI data. These techniques often require involving several hundreds of computed features for the characterization of the voxels, causing a rise in the necessary storage space by two order of magnitude. Processing such amounts of data also represents a serious computational burden. Under such circumstances it is useful to optimize the feature generation process. This paper proposes to establish the optimal spectral resolution of multispectral MRI data based feature values that allows for the best achievable brain tumor segmentation accuracy without causing unnecessary computational load and storage space waste. Experiments revealed that an 8-bit spectral resolution of the MRI-based feature data is sufficient to obtain the best possible accuracy of ensemble learning methods, while it allows for 50% reduction of the storage space required by the segmentation procedure, compared to the usually deployed featured encoding techniques.

Brain Tumor Segmentation from Multi-Spectral MRI Data Using Cascaded Ensemble Learning

“…Previously, we introduced a brain tumor segmentation procedure that used ensemble learning by the means of binary decision trees (BDT), and employed a morphological criterion to enhance the accuracy of lesion segmentation [25], [26]. Later we performed several experiments to improve the overall segmentation quality and the runtime efficiency, like finding an optimal subset of features [27], comparing several types of ensembles [28], searching for the histogram uniformization technique that is most suitable to detect focal lesions [29], including multi-atlases in the segmentation process [30], and determining the effect of feature vector's spectral resolution upon segmentation accuracy [31]. In this paper we propose a new method that involves a second learning ensemble to provide a better performing segmentation criterion at post-processing.…”