Display Settings:

Format

Send to:

Choose Destination
See comment in PubMed Commons below
J Biomed Opt. 2007 May-Jun;12(3):034002.

Sensitivity map of laser tweezers Raman spectroscopy for single-cell analysis of colorectal cancer.

Author information

  • 1Chinese Academy of Sciences, Shanghai Institute of Optics and Fine Mechanics, Key Laboratory for Quantum Optics, Shanghai 201800, China.

Erratum in

  • J Biomed Opt. 2007 May-Jun;12(3):039801.

Abstract

Raman spectroscopy on single, living epithelial cells captured in a laser trap is shown to have diagnostic power over colorectal cancer. This new single-cell technology comprises three major components: primary culture processing of human tissue samples to produce single-cell suspensions, Raman detection on singly trapped cells, and diagnoses of the cells by artificial neural network classifications. It is compared with DNA flow cytometry for similarities and differences. Its advantages over tissue Raman spectroscopy are also discussed. In the actual construction of a diagnostic model for colorectal cancer, real patient data were taken to generate a training set of 320 Raman spectra and a test set of 80. By incorporating outlier corrections to a conventional binary neural classifier, our network accomplished significantly better predictions than logistic regressions, with sensitivity improved from 77.5% to 86.3% and specificity improved from 81.3% to 86.3% for the training set and moderate improvements for the test set. Most important, the network approach enables a sensitivity map analysis to quantitate the relevance of each Raman band to the normal-to-cancer transform at the cell level. Our technique has direct clinic applications for diagnosing cancers and basic science potential in the study of cell dynamics of carcinogenesis.

PMID:
17614710
[PubMed - indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Silverchair Information Systems
    Loading ...
    Write to the Help Desk