A Chemometric Approach for Brain Tumor Classification Using Magnetic Resonance Imaging and Spectroscopy

• Published in: Analytical chemistry (Washington) 2003-10, Vol.75 (20), p.5352-5361
• Main Authors: Simonetti, Arjan W, Melssen, Willem J, van der Graaf, Marinette, Postma, Geert J, Heerschap, Arend, Buydens, Lutgarde M. C
• Format: Article
• Language: English
• Subjects: Analytical chemistry; Animal tumors. Experimental tumors; Aspartic Acid - analogs & derivatives; Aspartic Acid - analysis; Biochemistry; Biological and medical sciences; Brain; Brain - pathology; Brain Chemistry; Brain Neoplasms - classification; Brain Neoplasms - diagnosis; Cerebrospinal Fluid - chemistry; Chemistry; Choline - analysis; Creatine - analysis; Discriminant Analysis; Exact sciences and technology; Experimental head and neck tumors. Experimental orbital tumors; Fatty Acids - analysis; Glioma - classification; Glioma - diagnosis; Glutamic Acid - analysis; Humans; Image Processing, Computer-Assisted - methods; Inositol - analysis; Investigative techniques, diagnostic techniques (general aspects); Lactic Acid - analysis; Magnetic Resonance Imaging - methods; Magnetic Resonance Spectroscopy; Medical sciences; Nervous system; NMR; Nuclear magnetic resonance; Patient Selection; Principal Component Analysis; Probability; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Sensitivity and Specificity; Spectrometric and optical methods; Statistical Distributions; Tumors
• ISSN: 0003-2700; 1520-6882
• DOI: 10.1021/ac034541t

A new classification approach was developed to improve the noninvasive diagnosis of brain tumors. Within this approach, information is extracted from magnetic resonance imaging and spectroscopy data, from which the relative location and distribution of selected tumor classes in feature space can be calculated. This relative location and distribution is used to select the best information extraction procedure, to identify overlapping tumor classes, and to calculate probabilities of class membership. These probabilities are very important, since they provide information about the reliability of classification and might provide information about the heterogeneity of the tissue. Classification boundaries were calculated by setting thresholds for each investigated tumor class, which enabled the classification of new objects. Results on histopathologically determined tumors are excellent, demonstrated by spatial maps showing a high probability for the correctly identified tumor class and, moreover, low probabilities for other tumor classes.