In this paper, we characterize the tumor texture in pediatric brain magnetic resonance images (MRIs) and exploit
these features for automatic segmentation of posterior fossa (PF) tumors. We focus on PF tumor because of the
prevalence of such tumor in pediatric patients. Due to varying appearance in MRI, we propose to model the
tumor texture with a multi-fractal process, such as a multi-fractional Brownian motion (mBm). In mBm, the
time-varying Holder exponent provides flexibility in modeling irregular tumor texture. We develop a detailed
mathematical framework for mBm in two-dimension and propose a novel algorithm to estimate the multi-fractal
structure of tissue texture in brain MRI based on wavelet coefficients. This wavelet based multi-fractal feature along with MR image intensity and a regular fractal feature obtained using our existing piecewise-triangular-prism-surface-area (PTPSA) method, are fused in segmenting PF tumor and non-tumor regions in brain T1, T2, and FLAIR MR images respectively. We also demonstrate a non-patient-specific automated tumor prediction scheme based on these image features. We experimentally show the tumor discriminating power of our novel multi-fractal texture along with intensity and fractal features in automated tumor segmentation and statistical prediction. To evaluate the performance of our tumor prediction scheme, we obtain ROCs and demonstrate how sharply the curves reach the specificity of 1.0 sacrificing minimal sensitivity. Experimental results show the effectiveness of our proposed techniques in automatic detection of PF tumors in pediatric MRIs.
Identification of significantly differentially expressed genes (marker genes) among sample groups is a central issue in microarray analysis. This identification is important to understand the molecular pathway of diseases. Many statistical
methods have been proposed to locate marker genes. These methods depend on a cutoff value for selection. A tightfisted
cutoff may omit some of the important marker genes, whereas a generous threshold increases the number of false
positives. Although robust models for identifying marker genes more accurately is an area of intense research, effective
tools for the evaluation of results is often ignored in the literature. Despite the robustness of many of these methods,
there is always some probability of false positives. In this paper, we propose a novel approach that exploits parallel
coordinates to visualize the gene expression patterns so that one can compare the expression level changes of the marker
genes between sample groups and determine whether the selected marker genes are valid. Such visualization is useful to
measure the validity of the marker gene selection process as well as to fine tune the parameters of a particular method.
A prediction method based on the selected marker genes is used to measure the reliability of our process.