Pattern recognition of 31P magnetic resonance spectroscopy tumour spectra obtained in vivo

S L Howells; R J Maxwell; F A Howe; A C Peet; M Stubbs; L M Rodrigues; S P Robinson; S Baluch; J R Griffiths

Pattern recognition of 31P magnetic resonance spectroscopy tumour spectra obtained in vivo

S L Howells, R J Maxwell, F A Howe, A C Peet, M Stubbs, L M Rodrigues, S P Robinson, S Baluch, J R Griffiths

Cancer and Genomic Sciences

Research output: Contribution to journal › Article › peer-review

30 Citations (Scopus)

Abstract

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.

Original language	English
Pages (from-to)	237-41
Number of pages	5
Journal	NMR in biomedicine
Volume	6
Issue number	4
Publication status	Published - 1 Jul 1993

Keywords

Animals
Brain
Female
Fibrosarcoma
Liver
Magnetic Resonance Spectroscopy
Mice
Mice, Inbred C3H
Muscles
Neoplasm Transplantation
Neoplasms, Experimental
Pattern Recognition, Automated
Phosphorus
Rats
Rats, Inbred BUF
Rats, Wistar
Retrospective Studies
Comparative Study
Journal Article
Research Support, Non-U.S. Gov't

Cite this

@article{633c9dada3024a2194e9d49b61324a8d,

title = "Pattern recognition of 31P magnetic resonance spectroscopy tumour spectra obtained in vivo",

abstract = "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.",

keywords = "Animals, Brain, Female, Fibrosarcoma, Liver, Magnetic Resonance Spectroscopy, Mice, Mice, Inbred C3H, Muscles, Neoplasm Transplantation, Neoplasms, Experimental, Pattern Recognition, Automated, Phosphorus, Rats, Rats, Inbred BUF, Rats, Wistar, Retrospective Studies, Comparative Study, Journal Article, Research Support, Non-U.S. Gov't",

author = "Howells, {S L} and Maxwell, {R J} and Howe, {F A} and Peet, {A C} and M Stubbs and Rodrigues, {L M} and Robinson, {S P} and S Baluch and Griffiths, {J R}",

year = "1993",

month = jul,

day = "1",

language = "English",

volume = "6",

pages = "237--41",

journal = "NMR in biomedicine",

issn = "0952-3480",

publisher = "Wiley",

number = "4",

}

TY - JOUR

T1 - Pattern recognition of 31P magnetic resonance spectroscopy tumour spectra obtained in vivo

AU - Howells, S L

AU - Maxwell, R J

AU - Howe, F A

AU - Peet, A C

AU - Stubbs, M

AU - Rodrigues, L M

AU - Robinson, S P

AU - Baluch, S

AU - Griffiths, J R

PY - 1993/7/1

Y1 - 1993/7/1

N2 - 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.

AB - 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.

KW - Animals

KW - Brain

KW - Female

KW - Fibrosarcoma

KW - Liver

KW - Magnetic Resonance Spectroscopy

KW - Mice

KW - Mice, Inbred C3H

KW - Muscles

KW - Neoplasm Transplantation

KW - Neoplasms, Experimental

KW - Pattern Recognition, Automated

KW - Phosphorus

KW - Rats

KW - Rats, Inbred BUF

KW - Rats, Wistar

KW - Retrospective Studies

KW - Comparative Study

KW - Journal Article

KW - Research Support, Non-U.S. Gov't

M3 - Article

C2 - 8217524

SN - 0952-3480

VL - 6

SP - 237

EP - 241

JO - NMR in biomedicine

JF - NMR in biomedicine

IS - 4

ER -

Pattern recognition of 31P magnetic resonance spectroscopy tumour spectra obtained in vivo

Abstract

Keywords

Fingerprint

Cite this