From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods
Open Access
- 1 June 1998
- journal article
- review article
- Published by Wiley in NMR in Biomedicine
- Vol. 11 (4-5) , 148-156
- https://doi.org/10.1002/(sici)1099-1492(199806/08)11:4/5<148::aid-nbm511>3.0.co;2-4
Abstract
This article reviews the wealth of different pattern recognition methods that have been used for magnetic resonance spectroscopy (MRS) based tumor classification. The methods have in common that the entire MR spectra is used to develop linear and non‐linear classifiers. The following issues are adressed: (i) pre‐processing, such as normalization and digitization, (ii) extraction of relevant spectral features by multivariate methods, such as principal component analysis, linear discriminant analysis (LDA), and optimal discriminant vector, and (iii) classification by LDA, cluster analysis and artificial neural networks. Different approaches are compared and discussed in view of practical and theoretical considerations. © 1998 John Wiley & Sons, Ltd.Keywords
This publication has 38 references indexed in Scilit:
- Automated feature extraction for the classification of human in vivo13C NMR spectra using statistical pattern recognition and waveletsMagnetic Resonance in Medicine, 1996
- Proton nuclear magnetic resonance spectroscopy of serum from patients with colorectal neoplasiaEuropean Journal of Surgical Oncology, 1996
- Characterization of malignant colon tumors with31p nuclear magnetic resonance phospholipid and phosphatic metabolite profilesCancer, 1995
- Classification of toxin-induced changes in 1H NMR spectra of urine using an artificial neural networkJournal of Pharmaceutical and Biomedical Analysis, 1995
- Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to 1H Spectra of Thyroid NeoplasmsMagnetic Resonance in Medicine, 1995
- Automatic reduction of NMR spectroscopic data for statistical and pattern recognition classification of samplesJournal of Pharmaceutical and Biomedical Analysis, 1994
- On a theoretical comparison between the orthonormal discriminant vector method and discriminant analysisPattern Recognition, 1993
- In vitro characterization of lung cancers by the use of 1H nuclear magnetic resonance spectroscopy of tissue extracts and discriminant factor analysisMagnetic Resonance in Medicine, 1993
- A pattern recognition approach to the comparison of PMR and clinical chemical data for classification of nephrotoxicityJournal of Pharmaceutical and Biomedical Analysis, 1990
- Detection of Malignant TumorsNew England Journal of Medicine, 1986