BACKGROUND AND PURPOSE: MR Spectroscopy (MRS) has the unique ability to analyze tissue at the molecular level noninvasively. The purpose of this study was to determine if peak heights revealed by proton MRS ((1)H-MRS) signals showed that neural networks (NN) provided better accuracy than linear discriminant analysis (LDA) in differentiating head and neck squamous cell carcinoma (SCCA) from muscle METHODS: In vitro 11-T (1)H-MR spectra were obtained on SCCA tissue samples (n = 16) and muscle (n = 12). The peak heights at seven metabolite resonances were measured: olefinic acids at 5.3 ppm, inositol at 3.5 ppm, taurine at 3.4 ppm, choline (Cho) at 3.2 ppm, creatine (Cr) at 3.0 ppm, sialic acid at 2.2 ppm, and methyl at 0.9 ppm. Using leave-one-out experimental design and receiver operating characteristic curve analysis, the ability of NN and LDA classifiers to distinguish SCCA from muscle were compared (given equal weighting of false-negative and false-positive errors). These classifiers were also compared with an existing method that forms a diagnosis by using LDA of the Cho/Cr peak area ratio. RESULTS: NN classifiers, which were identified using height data, achieved better sensitivity and specificity rates in distinguishing SCAA from muscle than did LDA using height or area data. Sensitivity/specificity for the NN analysis of the seven metabolite peak heights were 87.5 % and 83.3%, respectively, for a one-hidden-node network and 81.2% and 91.7%, respectively, for a two-hidden-node network. Additional nodes did not improve accuracy. The sensitivity and specificity were 81.2% and 50%, respectively, for LDA of the seven peak heights, and 68% and 83%, respectively, for LDA of the Cho/Cr peak area ratio. CONCLUSION: NN classifiers with peak height data were superior to LDA of the peak heights and LDA of the Cho/Cr peak area ratio for differentiating SCCA from normal muscle. These results show neural network analysis can improve the diagnostic accuracy of (1)H-MRS in differentiating muscle from malignant tissue. Further studies are necessary to confirm our initial findings.
BACKGROUND AND PURPOSE: MR Spectroscopy (MRS) has the unique ability to analyze tissue at the molecular level noninvasively. The purpose of this study was to determine if peak heights revealed by proton MRS ((1)H-MRS) signals showed that neural networks (NN) provided better accuracy than linear discriminant analysis (LDA) in differentiating head and neck squamous cell carcinoma (SCCA) from muscle METHODS: In vitro 11-T (1)H-MR spectra were obtained on SCCA tissue samples (n = 16) and muscle (n = 12). The peak heights at seven metabolite resonances were measured: olefinic acids at 5.3 ppm, inositol at 3.5 ppm, taurine at 3.4 ppm, choline (Cho) at 3.2 ppm, creatine (Cr) at 3.0 ppm, sialic acid at 2.2 ppm, and methyl at 0.9 ppm. Using leave-one-out experimental design and receiver operating characteristic curve analysis, the ability of NN and LDA classifiers to distinguish SCCA from muscle were compared (given equal weighting of false-negative and false-positive errors). These classifiers were also compared with an existing method that forms a diagnosis by using LDA of the Cho/Cr peak area ratio. RESULTS: NN classifiers, which were identified using height data, achieved better sensitivity and specificity rates in distinguishing SCAA from muscle than did LDA using height or area data. Sensitivity/specificity for the NN analysis of the seven metabolite peak heights were 87.5 % and 83.3%, respectively, for a one-hidden-node network and 81.2% and 91.7%, respectively, for a two-hidden-node network. Additional nodes did not improve accuracy. The sensitivity and specificity were 81.2% and 50%, respectively, for LDA of the seven peak heights, and 68% and 83%, respectively, for LDA of the Cho/Cr peak area ratio. CONCLUSION: NN classifiers with peak height data were superior to LDA of the peak heights and LDA of the Cho/Cr peak area ratio for differentiating SCCA from normal muscle. These results show neural network analysis can improve the diagnostic accuracy of (1)H-MRS in differentiating muscle from malignant tissue. Further studies are necessary to confirm our initial findings.
Authors: L Bottaci; P J Drew; J E Hartley; M B Hadfield; R Farouk; P W Lee; I M Macintyre; G S Duthie; J R Monson Journal: Lancet Date: 1997-08-16 Impact factor: 79.321
Authors: S K Mukherji; S Schiro; M Castillo; L Kwock; R Soper; W Blackstock; W Shockley; M Weissler Journal: AJNR Am J Neuroradiol Date: 1996-09 Impact factor: 3.825
Authors: R L Somorjai; A E Nikulin; N Pizzi; D Jackson; G Scarth; B Dolenko; H Gordon; P Russell; C L Lean; L Delbridge Journal: Magn Reson Med Date: 1995-02 Impact factor: 4.668
Authors: M C Preul; Z Caramanos; D L Collins; J G Villemure; R Leblanc; A Olivier; R Pokrupa; D L Arnold Journal: Nat Med Date: 1996-03 Impact factor: 53.440
Authors: Tedros Bezabeh; Olva Odlum; Richard Nason; Paul Kerr; Donna Sutherland; Rakesh Patel; Ian C P Smith Journal: AJNR Am J Neuroradiol Date: 2005-09 Impact factor: 3.825