A probability-based spectroscopic diagnostic algorithm for simultaneous discrimination of brain tumor and tumor margins from normal brain tissue

Shovan K. Majumder, Steven Gebhart, Mahlon Johnson, Reid Thompson, Wei Chiang Lin, Anita Mahadevan-Jansen

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

This paper reports the development of a probability-based spectroscopic diagnostic algorithm capable of simultaneously discriminating tumor core and tumor margins from normal human brain tissues. The algorithm uses a nonlinear method for feature extraction based on maximum representation and discrimination feature (MRDF) and a Bayesian method for classification based on sparse multinomial logistic regression (SMLR). Both the autofluorescence and the diffuse-reflectance spectra acquired in vivo from patients undergoing craniotomy or temporal lobectomy at the Vanderbilt University Medical Center were used to train and validate the algorithm. The classification accuracy was observed to be approximately 96%, 80%, and 97% for the tumor, tumor margin, and normal brain tissues, respectively, for the training data set and approximately 96%, 94%, and 100%, respectively, for the corresponding tissue types in an independent validation data set. The inherently multi-class nature of the algorithm facilitates a rapid and simultaneous classification of tissue spectra into various tissue categories without the need for a hierarchical multi-step binary classification scheme. Further, the probabilistic nature of the algorithm makes it possible to quantitatively assess the certainty of the classification and recheck the samples that are classified with higher relative uncertainty.

Original languageEnglish (US)
Pages (from-to)548-557
Number of pages10
JournalApplied Spectroscopy
Volume61
Issue number5
DOIs
StatePublished - May 1 2007
Externally publishedYes

Fingerprint

brain
discrimination
Tumors
margins
Brain
tumors
Tissue
logistics
pattern recognition
Logistics
Feature extraction
regression analysis
education
reflectance

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Spectroscopy

Cite this

A probability-based spectroscopic diagnostic algorithm for simultaneous discrimination of brain tumor and tumor margins from normal brain tissue. / Majumder, Shovan K.; Gebhart, Steven; Johnson, Mahlon; Thompson, Reid; Lin, Wei Chiang; Mahadevan-Jansen, Anita.

In: Applied Spectroscopy, Vol. 61, No. 5, 01.05.2007, p. 548-557.

Research output: Contribution to journalArticle

Majumder, Shovan K. ; Gebhart, Steven ; Johnson, Mahlon ; Thompson, Reid ; Lin, Wei Chiang ; Mahadevan-Jansen, Anita. / A probability-based spectroscopic diagnostic algorithm for simultaneous discrimination of brain tumor and tumor margins from normal brain tissue. In: Applied Spectroscopy. 2007 ; Vol. 61, No. 5. pp. 548-557.
@article{d1e0cca649eb4456b72a7fc880a87410,
title = "A probability-based spectroscopic diagnostic algorithm for simultaneous discrimination of brain tumor and tumor margins from normal brain tissue",
abstract = "This paper reports the development of a probability-based spectroscopic diagnostic algorithm capable of simultaneously discriminating tumor core and tumor margins from normal human brain tissues. The algorithm uses a nonlinear method for feature extraction based on maximum representation and discrimination feature (MRDF) and a Bayesian method for classification based on sparse multinomial logistic regression (SMLR). Both the autofluorescence and the diffuse-reflectance spectra acquired in vivo from patients undergoing craniotomy or temporal lobectomy at the Vanderbilt University Medical Center were used to train and validate the algorithm. The classification accuracy was observed to be approximately 96{\%}, 80{\%}, and 97{\%} for the tumor, tumor margin, and normal brain tissues, respectively, for the training data set and approximately 96{\%}, 94{\%}, and 100{\%}, respectively, for the corresponding tissue types in an independent validation data set. The inherently multi-class nature of the algorithm facilitates a rapid and simultaneous classification of tissue spectra into various tissue categories without the need for a hierarchical multi-step binary classification scheme. Further, the probabilistic nature of the algorithm makes it possible to quantitatively assess the certainty of the classification and recheck the samples that are classified with higher relative uncertainty.",
author = "Majumder, {Shovan K.} and Steven Gebhart and Mahlon Johnson and Reid Thompson and Lin, {Wei Chiang} and Anita Mahadevan-Jansen",
year = "2007",
month = "5",
day = "1",
doi = "10.1366/000370207780807704",
language = "English (US)",
volume = "61",
pages = "548--557",
journal = "Applied Spectroscopy",
issn = "0003-7028",
publisher = "Society for Applied Spectroscopy",
number = "5",

}

TY - JOUR

T1 - A probability-based spectroscopic diagnostic algorithm for simultaneous discrimination of brain tumor and tumor margins from normal brain tissue

AU - Majumder, Shovan K.

AU - Gebhart, Steven

AU - Johnson, Mahlon

AU - Thompson, Reid

AU - Lin, Wei Chiang

AU - Mahadevan-Jansen, Anita

PY - 2007/5/1

Y1 - 2007/5/1

N2 - This paper reports the development of a probability-based spectroscopic diagnostic algorithm capable of simultaneously discriminating tumor core and tumor margins from normal human brain tissues. The algorithm uses a nonlinear method for feature extraction based on maximum representation and discrimination feature (MRDF) and a Bayesian method for classification based on sparse multinomial logistic regression (SMLR). Both the autofluorescence and the diffuse-reflectance spectra acquired in vivo from patients undergoing craniotomy or temporal lobectomy at the Vanderbilt University Medical Center were used to train and validate the algorithm. The classification accuracy was observed to be approximately 96%, 80%, and 97% for the tumor, tumor margin, and normal brain tissues, respectively, for the training data set and approximately 96%, 94%, and 100%, respectively, for the corresponding tissue types in an independent validation data set. The inherently multi-class nature of the algorithm facilitates a rapid and simultaneous classification of tissue spectra into various tissue categories without the need for a hierarchical multi-step binary classification scheme. Further, the probabilistic nature of the algorithm makes it possible to quantitatively assess the certainty of the classification and recheck the samples that are classified with higher relative uncertainty.

AB - This paper reports the development of a probability-based spectroscopic diagnostic algorithm capable of simultaneously discriminating tumor core and tumor margins from normal human brain tissues. The algorithm uses a nonlinear method for feature extraction based on maximum representation and discrimination feature (MRDF) and a Bayesian method for classification based on sparse multinomial logistic regression (SMLR). Both the autofluorescence and the diffuse-reflectance spectra acquired in vivo from patients undergoing craniotomy or temporal lobectomy at the Vanderbilt University Medical Center were used to train and validate the algorithm. The classification accuracy was observed to be approximately 96%, 80%, and 97% for the tumor, tumor margin, and normal brain tissues, respectively, for the training data set and approximately 96%, 94%, and 100%, respectively, for the corresponding tissue types in an independent validation data set. The inherently multi-class nature of the algorithm facilitates a rapid and simultaneous classification of tissue spectra into various tissue categories without the need for a hierarchical multi-step binary classification scheme. Further, the probabilistic nature of the algorithm makes it possible to quantitatively assess the certainty of the classification and recheck the samples that are classified with higher relative uncertainty.

UR - http://www.scopus.com/inward/record.url?scp=34248675227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34248675227&partnerID=8YFLogxK

U2 - 10.1366/000370207780807704

DO - 10.1366/000370207780807704

M3 - Article

VL - 61

SP - 548

EP - 557

JO - Applied Spectroscopy

JF - Applied Spectroscopy

SN - 0003-7028

IS - 5

ER -