Multifractal modeling, segmentation, prediction and statistical validation of posterior fossa tumors

被引:9
作者
Islam, Atiq [1 ]
Iftekharuddin, Khan M. [1 ]
Ogg, Robert J. [2 ]
Laningham, Fred H. [2 ]
Sivakumar, Bhuvaneswari [1 ]
机构
[1] Univ Memphis, Dept Elect & Comp Engn, Intelligent Syst & Image Proc Lab, Memphis, TN 38152 USA
[2] St Jude Childrens Res Hosp, Dept Diagnost Imaging, Memphis, TN 38105 USA
来源
MEDICAL IMAGING 2008: COMPUTER-AIDED DIAGNOSIS, PTS 1 AND 2 | 2008年 / 6915卷
关键词
posterior fossa tumor; feature extraction; segmentation; prediction; magnetic resonance images; multifractal texture and shape; receiver operating curves;
D O I
10.1117/12.770902
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
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.
引用
收藏
页数:12
相关论文
共 36 条
[1]  
ALIREZAIE J, 1996, IEEE NUCL SCI S
[2]  
[Anonymous], 1983, New York
[3]   SINGULARITY SPECTRUM OF FRACTAL SIGNALS FROM WAVELET ANALYSIS - EXACT RESULTS [J].
BACRY, E ;
MUZY, JF ;
ARNEODO, A .
JOURNAL OF STATISTICAL PHYSICS, 1993, 70 (3-4) :635-674
[4]   CHARACTERIZATION OF MAMMOGRAPHIC PARENCHYMAL PATTERN BY FRACTAL DIMENSION [J].
CALDWELL, CB ;
STAPLETON, SJ ;
HOLDSWORTH, DW ;
JONG, RA ;
WEISER, WJ ;
COOKE, G ;
YAFFE, MJ .
PHYSICS IN MEDICINE AND BIOLOGY, 1990, 35 (02) :235-247
[5]   FRACTAL ANALYSIS OF TRABECULAR PATTERNS IN PROJECTION RADIOGRAPHS - AN ASSESSMENT [J].
CHEN, J ;
ZHENG, B ;
CHANG, YH ;
SHAW, CC ;
TOWERS, JD ;
GUR, D .
INVESTIGATIVE RADIOLOGY, 1994, 29 (06) :624-629
[6]  
GONCALVES P, 1992, IEEE INT C AC SPEECH, pV157
[7]  
GONCALVES P, 1997, ICASSP, V5, P3433
[8]  
Goncalves P., 1998, P 32 AS C SIGN SYST
[9]  
Goncalves P ., 2000, P INT C TEL AC MEX M
[10]  
IFTEKHARUDDIN K, 2006, P BIOM SIGN IM PROC