Nosologic imaging of the brain: segmentation and classification using MRI and MRSI

A new technique is presented to create nosologic images of the brain based on magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI). A nosologic image summarizes the presence of different tissues and lesions in a single image by color coding each voxel or pixel according to the histopathological class it is assigned to. The proposed technique applies advanced methods from image processing as well as pattern recognition to segment and classify brain tumors. First, a registered brain atlas and a subject‐specific abnormal tissue prior, obtained from MRSI data, are used for the segmentation. Next, the detected abnormal tissue is classified based on supervised pattern recognition methods. Class probabilities are also calculated for the segmented abnormal region. Compared to previous approaches, the new framework is more flexible and able to better exploit spatial information leading to improved nosologic images. The combined scheme offers a new way to produce high‐resolution nosologic images, representing tumor heterogeneity and class probabilities, which may help clinicians in decision making. Copyright © 2008 John Wiley & Sons, Ltd.

[1]  A. W. Simonetti,et al.  Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra , 2006, NMR in biomedicine.

[2]  Arend Heerschap,et al.  A chemometric approach for brain tumor classification using magnetic resonance imaging and spectroscopy. , 2003, Analytical chemistry.

[3]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[4]  B. Scheithauer,et al.  The 2007 WHO classification of tumours of the central nervous system , 2007, Acta Neuropathologica.

[5]  Johan A. K. Suykens,et al.  Bayesian Framework for Least-Squares Support Vector Machine Classifiers, Gaussian Processes, and Kernel Fisher Discriminant Analysis , 2002, Neural Computation.

[6]  A. W. Simonetti,et al.  The use of multivariate MR imaging intensities versus metabolic data from MR spectroscopic imaging for brain tumour classification. , 2005, Journal of magnetic resonance.

[7]  Lutgarde M. C. Buydens,et al.  Published online in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/cem.721 Mixture modelling of medical magnetic resonance data , 2002 .

[8]  Christopher Nimsky,et al.  Proton Magnetic Resonance Spectroscopic Imaging Integrated into Image-guided Surgery: Correlation to Standard Magnetic Resonance Imaging and Tumor Cell Density , 2005, Neurosurgery.

[9]  A W Simonetti,et al.  Automated correction of unwanted phase jumps in reference signals which corrupt MRSI spectra after eddy current correction. , 2002, Journal of magnetic resonance.

[10]  Franklyn A Howe,et al.  1H MR spectroscopy of brain tumours and masses , 2003, NMR in biomedicine.

[11]  R. Kikinis,et al.  Automated segmentation of MR images of brain tumors. , 2001, Radiology.

[12]  Sabine Van Huffel,et al.  Tissue segmentation and classification of MRSI data using canonical correlation analysis , 2005, Magnetic resonance in medicine.

[13]  Koenraad Van Leemput,et al.  Automated model-based bias field correction of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[14]  Mark W. Schmidt,et al.  Segmenting brain tumors using alignment-based features , 2005, Fourth International Conference on Machine Learning and Applications (ICMLA'05).

[15]  Susan M. Chang,et al.  Age and the risk of anaplasia in magnetic resonance‐nonenhancing supratentorial cerebral tumors , 1997, Cancer.

[16]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[17]  Koenraad Van Leemput,et al.  Automated model-based tissue classification of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[18]  Sabine Van Huffel,et al.  A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection , 2007, Artif. Intell. Medicine.

[19]  V. Govindaraju,et al.  Proton NMR chemical shifts and coupling constants for brain metabolites , 2000, NMR in biomedicine.

[20]  Lawrence O. Hall,et al.  Automatic tumor segmentation using knowledge-based techniques , 1998, IEEE Transactions on Medical Imaging.

[21]  D. van Ormondt,et al.  SVD-based quantification of magnetic resonance signals , 1992 .

[22]  Sabine Van Huffel,et al.  Fast nosological imaging using canonical correlation analysis of brain data obtained by two‐dimensional turbo spectroscopic imaging , 2008, NMR in biomedicine.

[23]  R. Kikinis,et al.  Recognizing Deviations from Normalcy for Brain Tumor Segmentation , 2002, MICCAI.

[24]  T. Mikkelsen,et al.  Correlation between Magnetic Resonance Spectroscopy Imaging and Image-guided Biopsies: Semiquantitative and Qualitative Histopathological Analyses of Patients with Untreated Glioma , 2001, Neurosurgery.

[25]  Johan A. K. Suykens,et al.  Multi-class kernel logistic regression: a fixed-size implementation , 2007, IJCNN.

[26]  Ron Kikinis,et al.  Segmentation of Meningiomas and Low Grade Gliomas in MRI , 1999, MICCAI.

[27]  T. Carpenter,et al.  Improved delineation of glioma margins and regions of infiltration with the use of diffusion tensor imaging: an image-guided biopsy study. , 2006, AJNR. American journal of neuroradiology.

[28]  Gene H. Golub,et al.  Matrix computations , 1983 .

[29]  Damien Galanaud,et al.  Noninvasive diagnostic assessment of brain tumors using combined in vivo MR imaging and spectroscopy , 2006, Magnetic resonance in medicine.

[30]  Ji Zhu,et al.  Kernel Logistic Regression and the Import Vector Machine , 2001, NIPS.

[31]  J. Suykens,et al.  Classification of brain tumours using short echo time 1H MR spectra. , 2004, Journal of magnetic resonance.

[32]  M Leonardi,et al.  Metabolic Findings on 3T 1H-MR Spectroscopy in Peritumoral Brain Edema , 2007, American Journal of Neuroradiology.

[33]  Lawrence O. Hall,et al.  Automatic segmentation of non-enhancing brain tumors in magnetic resonance images , 2001, Artif. Intell. Medicine.

[34]  Z L Gokaslan,et al.  Limitations of stereotactic biopsy in the initial management of gliomas. , 2001, Neuro-oncology.

[35]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[36]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[37]  Arend Heerschap,et al.  Combination of feature‐reduced MR spectroscopic and MR imaging data for improved brain tumor classification , 2005, NMR in biomedicine.

[38]  Guido Gerig,et al.  Level-set evolution with region competition: automatic 3-D segmentation of brain tumors , 2002, Object recognition supported by user interaction for service robots.

[39]  Glyn Johnson,et al.  Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging. , 2003, AJNR. American journal of neuroradiology.

[40]  V. L. Doyle,et al.  Metabolic profiles of human brain tumors using quantitative in vivo 1H magnetic resonance spectroscopy , 2003, Magnetic resonance in medicine.

[41]  Tommaso Scarabino,et al.  Multiparametric 3T MR approach to the assessment of cerebral gliomas: tumor extent and malignancy , 2006, Neuroradiology.

[42]  Christopher Nimsky,et al.  Preoperative grading of gliomas by using metabolite quantification with high-spatial-resolution proton MR spectroscopic imaging. , 2006, Radiology.

[43]  Ron Kikinis,et al.  Adaptive Template Moderated Spatially Varying Statistical Classification , 1998, MICCAI.

[44]  Ron Kikinis,et al.  Automated Segmentation of MRI of Brain Tumors , 2001 .

[45]  Sylvie Grand,et al.  A new approach for analyzing proton magnetic resonance spectroscopic images of brain tumors: nosologic images , 2000, Nature Medicine.

[46]  Ying Lu,et al.  Analysis of the spatial characteristics of metabolic abnormalities in newly diagnosed glioma patients , 2002, Journal of magnetic resonance imaging : JMRI.

[47]  U. Klose.  In vivo proton spectroscopy in presence of eddy currents , 1990, Magnetic resonance in medicine.

[48]  Guido Gerig,et al.  Automatic brain tumor segmentation by subject specific modification of atlas priors. , 2003, Academic radiology.

[49]  Mitchel S Berger,et al.  Correlation of magnetic resonance spectroscopic and growth characteristics within Grades II and III gliomas. , 2007, Journal of neurosurgery.

[50]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[51]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .