Automated segmentation and classification of multispectral magnetic resonance images of brain using artificial neural networks

被引:217
作者
Reddick, WE
Glass, JO
Cook, EN
Elkin, TD
Deaton, RJ
机构
[1] St Jude Childrens Res Hosp, Dept Diagnost Imaging, Memphis, TN 38105 USA
[2] Univ Memphis, Dept Elect Engn, Memphis, TN 38152 USA
[3] Univ Memphis, Dept Biomed Engn, Memphis, TN 38152 USA
[4] St Jude Childrens Res Hosp, Dept Behav Med, Memphis, TN 38105 USA
[5] Memphis State Univ, Dept Psychol, Memphis, TN 38152 USA
[6] Memphis State Univ, Dept Elect Engn, Memphis, TN 38152 USA
关键词
image processing; image segmentation and classification; MRI; neural networks;
D O I
10.1109/42.650887
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
We present a fully automated process for segmentation and classification of multispectral magnetic resonance (MR) images, This hybrid neural network method uses a Kohonen self-organizing neural network for segmentation and a multilayer backpropagation neural network for classification, To separate different tissue types, this process uses the standard T1-, T2-, and PD-weighted MR images acquired in clinical examinations, Volumetric measurements of brain structures, relative to intracranial volume, were calculated for an index transverse section in 14 normal subjects (median age 25 years; seven male, seven female), This index slice was at the level of the basal ganglia, included both genu and splenium of the corpus callosum, and generally, showed the putamen and lateral ventricle, An intraclass correlation of this automated segmentation and classification of tissues with the accepted standard of radiologist identification for the index slice in the 14 volunteers demonstrated coefficients (r(i)) of 0.91, 0.95, and 0.98 for white matter, gray matter, and ventricular cerebrospinal fluid (CSF), respectively, An analysis of variance for estimates of brain parenchyma volumes in five volunteers imaged five times each demonstrated high intrasubject reproducibility with a significance of at least p <0.05 for white matter, gray matter, and white/gray partial volumes, The population variation, across 14 volunteers, demonstrated little deviation from the averages for gray and white matter, while partial volume classes exhibited a slightly higher degree of variability, This fully automated technique produces reliable and reproducible MR image segmentation and classification while eliminating intra- and interobserver variability.
引用
收藏
页码:911 / 918
页数:8
相关论文
共 42 条
[1]   OPTIMIZATION NEURAL NETWORKS FOR THE SEGMENTATION OF MAGNETIC-RESONANCE IMAGES [J].
AMARTUR, SC ;
PIRAINO, D ;
TAKEFUJI, Y .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1992, 11 (02) :215-220
[2]  
AYLWARD EH, 1995, AM J PSYCHIAT, V152, P987
[3]  
BACHUS R, 1985, COMPUT ASSIST RADIOL, P496
[4]   REVIEW OF MR IMAGE SEGMENTATION TECHNIQUES USING PATTERN-RECOGNITION [J].
BEZDEK, JC ;
HALL, LO ;
CLARKE, LP .
MEDICAL PHYSICS, 1993, 20 (04) :1033-1048
[5]  
BLATTER DD, 1995, AM J NEURORADIOL, V16, P241
[6]   BEHAVIORAL RESILIENCY AMONG CHILDREN SURVIVING BRAIN-TUMORS - A LONGITUDINAL-STUDY [J].
CARPENTIERI, SC ;
MULHERN, RK ;
DOUGLAS, S ;
HANNA, S ;
FAIRCLOUGH, DL .
JOURNAL OF CLINICAL CHILD PSYCHOLOGY, 1993, 22 (02) :236-246
[7]  
Cheng KS, 1996, IEEE T MED IMAGING, V15, P560, DOI 10.1109/42.511759
[8]   MRI SEGMENTATION USING FUZZY CLUSTERING-TECHNIQUES [J].
CLARK, MC ;
HALL, LO ;
GOLDGOF, DB ;
CLARKE, LP ;
VELTHUIZEN, RP ;
SILBIGER, MS .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 1994, 13 (05) :730-742
[9]   MRI SEGMENTATION - METHODS AND APPLICATIONS [J].
CLARKE, LP ;
VELTHUIZEN, RP ;
CAMACHO, MA ;
HEINE, JJ ;
VAIDYANATHAN, M ;
HALL, LO ;
THATCHER, RW ;
SILBIGER, ML .
MAGNETIC RESONANCE IMAGING, 1995, 13 (03) :343-368
[10]   3D SURFACE RENDERED MR IMAGES OF THE BRAIN AND ITS VASCULATURE [J].
CLINE, HE ;
LORENSEN, WE ;
SOUZA, SP ;
JOLESZ, FA ;
KIKINIS, R ;
GERIG, G ;
KENNEDY, TE .
JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1991, 15 (02) :344-351