Near‐optimal region selection for feature space reduction: novel preprocessing methods for classifying MR spectra

We introduce a global feature extraction method specifically designed to preprocess magnetic resonance spectra of biomedical origin. Such preprocessing is essential for the accurate and reliable classification of diseases or disease stages manifest in the spectra. The new method is genetic algorithm‐guided. It is compared with our enhanced version of the standard forward selection algorithm. Both seek and select optimal spectral subregions. These subregions necessarily retain spectral information, thus aiding the eventual identification of the biochemistry of disease presence and progression. The power of the methods is demonstrated on two biomedical examples: the discrimination between meningioma and astrocytoma in brain tissue biopsies, and the classification of colorectal biopsies into normal and tumour classes. Both preprocessing methods lead to classification accuracies over 97% for the two examples. © 1998 John Wiley & Sons, Ltd.

[1]  Jack Sklansky,et al.  A note on genetic algorithms for large-scale feature selection , 1989, Pattern Recognit. Lett..

[2]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[3]  J. Friedman.  Regularized Discriminant Analysis , 1989 .

[4]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[5]  D Fewer,et al.  Classification of 1H MR spectra of human brain neoplasms: The influence of preprocessing and computerized consensus diagnosis on classification accuracy , 1996, Journal of magnetic resonance imaging : JMRI.

[6]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[7]  R L Somorjai,et al.  The classification of benign and malignant human prostate tissue by multivariate analysis of 1H magnetic resonance spectra. , 1997, Cancer research.

[8]  J. Saunders,et al.  A simple procedure for obtaining high‐quality nmr spectra of semiquantitative value from small tissue specimens: cervical biopsies. , 1992, Magnetic resonance in medicine.

[9]  B. Chandrasekaran,et al.  Quantization Complexity and Independent Measurements , 1974, IEEE Transactions on Computers.

[10]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[11]  Anthony N. Mucciardi,et al.  A Comparison of Seven Techniques for Choosing Subsets of Pattern Recognition Properties , 1971, IEEE Transactions on Computers.

[12]  R. Somorjai,et al.  Classification of 1H MR spectra of biopsies from untreated and recurrent ovarian cancer using linear discriminant analysis , 1997, Magnetic resonance in medicine.

[13]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Feature Subset Selection , 1977, IEEE Transactions on Computers.

[14]  Peter Russell,et al.  Computerized Consensus Diagnosis: A Classification Strategy for the Robust Analysis of MR Spectra. I. Application to 1H Spectra of Thyroid Neoplasms , 1995, Magnetic resonance in medicine.

[15]  J R Griffiths,et al.  An Investigation of Tumor 1H Nuclear Magnetic Resonance Spectra by the Application of Chemometric Techniques , 1992, Magnetic resonance in medicine.

[16]  John G. Proakis,et al.  Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .

[17]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .