RESUMEN
Pattern recognition techniques (factor analysis and neural networks) were used to investigate and classify human brain tumors based on the 1H NMR spectra of chemically extracted biopsies (n = 118). After removing information from lactate (because of variable ischemia times), unsupervised learning suggested that the spectra separated naturally into two groups: meningiomas and other tumors. Principal component analysis reduced the dimensionality of the data. A back-propagation neural network using the first 30 principal components gave 85% correct classification of meningiomas and nonmeningiomas. Simplification by vector rotation gave vectors that could be assigned to various metabolites, making it possible to use or to reject their information for neural network classification. Using scores calculated from the four rotated vectors due to creatine and glutamine gave the best classification into meningiomas and nonmeningiomas (89% correct). Classification of gliomas (n = 47) gave 62% correct within one grade. Only inositol showed a significant correlation with glioma grade.
Asunto(s)
Biomarcadores de Tumor/análisis , Neoplasias Encefálicas/química , Espectroscopía de Resonancia Magnética , Neoplasias Meníngeas/química , Meningioma/química , Extractos de Tejidos/química , Biopsia , Encéfalo/patología , Neoplasias Encefálicas/clasificación , Neoplasias Encefálicas/patología , Diagnóstico Diferencial , Humanos , Espectroscopía de Resonancia Magnética/métodos , Neoplasias Meníngeas/clasificación , Neoplasias Meníngeas/patología , Meninges/patología , Meningioma/clasificación , Meningioma/patología , Redes Neurales de la Computación , Percloratos , Sensibilidad y EspecificidadRESUMEN
The ability to classify spectra of tumours according to their stage and type will be essential if magnetic resonance spectroscopy (MRS) is to be used as an aid in the diagnosis of cancer. MRS data are normally classified on the basis of selected peak measurements but these may be difficult to extract automatically. We present two alternative methods of feature extraction which we used to discriminate between spectra from tumours and normal tissues. Discrimination could be achieved either using features from the whole spectrum, or from a selected region containing the peaks from the phospholipid precursors in the phosphomonoester region.
Asunto(s)
Metabolismo de los Lípidos , Neoplasias Experimentales/metabolismo , Animales , Femenino , Espectroscopía de Resonancia Magnética , Reconocimiento de Normas Patrones Automatizadas , Ratas , Ratas Endogámicas BUF , Ratas Endogámicas WF , Ratas WistarRESUMEN
Pattern recognition has been applied to the analysis of in vivo 31P NMR spectra. Using four different classes of tumour and three types of normal tissue, cluster analysis and artificial neural networks were successful in separating and classifying the majority of samples analysed. Although the phosphomonoester and P(i) regions appeared to be the most important spectral features, data representing the entire 31P spectrum were required for best separation of the tumour and tissue classes.
Asunto(s)
Neoplasias Experimentales/diagnóstico , Reconocimiento de Normas Patrones Automatizadas , Animales , Encéfalo/metabolismo , Femenino , Fibrosarcoma/diagnóstico , Fibrosarcoma/metabolismo , Fibrosarcoma/patología , Hígado/metabolismo , Espectroscopía de Resonancia Magnética/métodos , Ratones , Ratones Endogámicos C3H , Músculos/metabolismo , Trasplante de Neoplasias , Neoplasias Experimentales/metabolismo , Neoplasias Experimentales/patología , Fósforo , Ratas , Ratas Endogámicas BUF , Ratas Wistar , Estudios RetrospectivosRESUMEN
1H nuclear magnetic resonance (NMR) spectra of tumors and normal tissue include signals from all hydrogen-containing metabolites and can therefore be considered multicomponent multivariate mixtures. We have obtained 1H spectra from perchloric acid extracts of three normal tissues (liver, kidney, and spleen) and five rat tumors (GH3 prolactinoma, Morris hepatomas 7777 and 9618a, LBDS1 fibrosarcoma, and Walker 256 carcinosarcoma). We have applied several different chemometric methods to analyze the data. First, we used principal component analysis, cluster analysis, and an optimized artificial neural network to develop a classification rule from a training set of samples of known origin or class. The classification rule was then assessed using a set of unknown samples. We were able to successfully determine the class of each unknown sample. Second, we used the chemometric techniques of factor analysis followed by target testing to investigate the underlying biochemical differences that are detected between the classes of samples.
Asunto(s)
Espectroscopía de Resonancia Magnética , Neoplasias Experimentales/química , Adenocarcinoma/química , Animales , Inteligencia Artificial , Carcinoma Hepatocelular/química , Carcinosarcoma/química , Clasificación , Análisis por Conglomerados , Análisis Factorial , Femenino , Fibrosarcoma/química , Hidrógeno , Riñón/química , Hígado/química , Neoplasias Hepáticas/química , Masculino , Modelos Químicos , Redes Neurales de la Computación , Prolactinoma/química , Ratas , Ratas Endogámicas , Ratas Endogámicas WF , Ratas Wistar , Procesamiento de Señales Asistido por Computador , Bazo/químicaRESUMEN
1H spectra of tumours or normal tissues, which include signals from all hydrogen-containing metabolites, are too complex for the human eye to interpret. We have studied 58 1H spectra from perchloric acid extracts of three normal tissues (liver, kidney and spleen) and five rat tumours (GH3 pituitary, fibrosarcoma, Morris Hepatomas 7777 and 9618a and Walker carcinosarcoma). Instead of editing them or quantifying individual metabolites, we have used statistical pattern recognition techniques to classify them into groups. This automatic, objective method differentiated spectra from normal and malignant rat tissue biopsies, and from different types of cancer. It seems likely that this technique can be applied to human tissues and thus used for cancer diagnosis.
