1998
DOI: 10.1002/mrm.1910390604
|View full text |Cite
|
Sign up to set email alerts
|

Pattern recognition analysis of 1H NMR spectra from perchloric acid extracts of human brain tumor biopsies

Abstract: 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 p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
44
0
1

Year Published

2000
2000
2013
2013

Publication Types

Select...
8
1

Relationship

1
8

Authors

Journals

citations
Cited by 68 publications
(45 citation statements)
references
References 25 publications
0
44
0
1
Order By: Relevance
“…Every other week, NMR scans were performed to follow the fate of tumors, using a General Electric Orizon 1-Tesla machine under conditions dedicated to skull analysis. 23 Mice were sacrificed at indicated time points and further examined by means of histological sections.…”
Section: Animal Studiesmentioning
confidence: 99%
“…Every other week, NMR scans were performed to follow the fate of tumors, using a General Electric Orizon 1-Tesla machine under conditions dedicated to skull analysis. 23 Mice were sacrificed at indicated time points and further examined by means of histological sections.…”
Section: Animal Studiesmentioning
confidence: 99%
“…In addition, HR-MAS NMR spectroscopy of intact tissues (ex vivo) provides further advantages over traditional high resolution liquid NMR of tissue extracts (in vitro) (27,34). High resolution NMR of extracts from excised tissues requires large amounts of sample (35). Likewise, the extraction process via protein precipitation methods disables the direct observation of small cellular proteins and membrane semi-mobile lipids.…”
Section: Introductionmentioning
confidence: 99%
“…Data on brain cancers also is extensive, with defined metabolomics biomarkers established from studies of brain tumor specimens exhibiting discrete 1 H-NMR spectra (34,35 ). Analysis of tCho by magnetic resonance spectroscopic imaging was able to detect breast, prostate, and brain tumors and correlated well with diagnosis via dynamic contrast-enhanced MRI (35 ).…”
Section: Opportunities From the Cancer Metabolomementioning
confidence: 99%