Hybrid methods for automated diagnosis of breast tumors

Casey Diekman, Wei He, Nagabhushana Prabhu, Harvey Cramer

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

OBJECTIVE: To design and analyze a new family of hybrid methods for the diagnosis of breast tumors using fine needle aspirates. STUDY DESIGN: We present a radically new approach to the design of diagnosis systems. In the new approach, a nonlinear classifier with high sensitivity but low specificity is hybridized with a linear classifier having low sensitivity but high specificity. Data from the Wisconsin Breast Cancer Database are used to evaluate, computationally, the performance of the hybrid classifiers. RESULTS: The diagnosis scheme obtained by hybridizing the nonlinear classifier ellipsoidal multisurface method (EMSM) with the linear classifier proximal support vector machine (PSVM) was found to have a mean sensitivity of 97.36% and a mean specificity of 95.14% and was found to yield a 2.44% improvement in the reliability of positive diagnosis over that of EMSM at the expense of 0.4% degradation in the reliability of negative diagnosis, again compared to EMSM. At the 95% confidence level we can trust the hybrid method to be 96.19-98.53% correct in its malignant diagnosis of new tumors and 93.57-96.71% correct in its benign diagnosis. CONCLUSION: Hybrid diagnosis schemes represent a significant paradigm shift and provide a promising new technique to improve the specificity of nonlinear classifiers without seriously affecting the high sensitivity of nonlinear classifiers.

Original languageEnglish
Pages (from-to)183-190
Number of pages8
JournalAnalytical and Quantitative Cytology and Histology
Volume25
Issue number4
StatePublished - Aug 2003

Fingerprint

Breast Neoplasms
Sensitivity and Specificity
Needles
Databases
Neoplasms

Keywords

  • Aspiration biopsy
  • Breast cancer
  • Computer assisted
  • Diagnosis

ASJC Scopus subject areas

  • Anatomy
  • Histology
  • Cell Biology

Cite this

Hybrid methods for automated diagnosis of breast tumors. / Diekman, Casey; He, Wei; Prabhu, Nagabhushana; Cramer, Harvey.

In: Analytical and Quantitative Cytology and Histology, Vol. 25, No. 4, 08.2003, p. 183-190.

Research output: Contribution to journalArticle

Diekman, Casey ; He, Wei ; Prabhu, Nagabhushana ; Cramer, Harvey. / Hybrid methods for automated diagnosis of breast tumors. In: Analytical and Quantitative Cytology and Histology. 2003 ; Vol. 25, No. 4. pp. 183-190.
@article{f4e14b4bd5e444a196d7f9502da37d49,
title = "Hybrid methods for automated diagnosis of breast tumors",
abstract = "OBJECTIVE: To design and analyze a new family of hybrid methods for the diagnosis of breast tumors using fine needle aspirates. STUDY DESIGN: We present a radically new approach to the design of diagnosis systems. In the new approach, a nonlinear classifier with high sensitivity but low specificity is hybridized with a linear classifier having low sensitivity but high specificity. Data from the Wisconsin Breast Cancer Database are used to evaluate, computationally, the performance of the hybrid classifiers. RESULTS: The diagnosis scheme obtained by hybridizing the nonlinear classifier ellipsoidal multisurface method (EMSM) with the linear classifier proximal support vector machine (PSVM) was found to have a mean sensitivity of 97.36{\%} and a mean specificity of 95.14{\%} and was found to yield a 2.44{\%} improvement in the reliability of positive diagnosis over that of EMSM at the expense of 0.4{\%} degradation in the reliability of negative diagnosis, again compared to EMSM. At the 95{\%} confidence level we can trust the hybrid method to be 96.19-98.53{\%} correct in its malignant diagnosis of new tumors and 93.57-96.71{\%} correct in its benign diagnosis. CONCLUSION: Hybrid diagnosis schemes represent a significant paradigm shift and provide a promising new technique to improve the specificity of nonlinear classifiers without seriously affecting the high sensitivity of nonlinear classifiers.",
keywords = "Aspiration biopsy, Breast cancer, Computer assisted, Diagnosis",
author = "Casey Diekman and Wei He and Nagabhushana Prabhu and Harvey Cramer",
year = "2003",
month = "8",
language = "English",
volume = "25",
pages = "183--190",
journal = "Analytical and Quantitative Cytopathology and Histopathology",
issn = "0301-102X",
publisher = "John Rylands University Library",
number = "4",

}

TY - JOUR

T1 - Hybrid methods for automated diagnosis of breast tumors

AU - Diekman, Casey

AU - He, Wei

AU - Prabhu, Nagabhushana

AU - Cramer, Harvey

PY - 2003/8

Y1 - 2003/8

N2 - OBJECTIVE: To design and analyze a new family of hybrid methods for the diagnosis of breast tumors using fine needle aspirates. STUDY DESIGN: We present a radically new approach to the design of diagnosis systems. In the new approach, a nonlinear classifier with high sensitivity but low specificity is hybridized with a linear classifier having low sensitivity but high specificity. Data from the Wisconsin Breast Cancer Database are used to evaluate, computationally, the performance of the hybrid classifiers. RESULTS: The diagnosis scheme obtained by hybridizing the nonlinear classifier ellipsoidal multisurface method (EMSM) with the linear classifier proximal support vector machine (PSVM) was found to have a mean sensitivity of 97.36% and a mean specificity of 95.14% and was found to yield a 2.44% improvement in the reliability of positive diagnosis over that of EMSM at the expense of 0.4% degradation in the reliability of negative diagnosis, again compared to EMSM. At the 95% confidence level we can trust the hybrid method to be 96.19-98.53% correct in its malignant diagnosis of new tumors and 93.57-96.71% correct in its benign diagnosis. CONCLUSION: Hybrid diagnosis schemes represent a significant paradigm shift and provide a promising new technique to improve the specificity of nonlinear classifiers without seriously affecting the high sensitivity of nonlinear classifiers.

AB - OBJECTIVE: To design and analyze a new family of hybrid methods for the diagnosis of breast tumors using fine needle aspirates. STUDY DESIGN: We present a radically new approach to the design of diagnosis systems. In the new approach, a nonlinear classifier with high sensitivity but low specificity is hybridized with a linear classifier having low sensitivity but high specificity. Data from the Wisconsin Breast Cancer Database are used to evaluate, computationally, the performance of the hybrid classifiers. RESULTS: The diagnosis scheme obtained by hybridizing the nonlinear classifier ellipsoidal multisurface method (EMSM) with the linear classifier proximal support vector machine (PSVM) was found to have a mean sensitivity of 97.36% and a mean specificity of 95.14% and was found to yield a 2.44% improvement in the reliability of positive diagnosis over that of EMSM at the expense of 0.4% degradation in the reliability of negative diagnosis, again compared to EMSM. At the 95% confidence level we can trust the hybrid method to be 96.19-98.53% correct in its malignant diagnosis of new tumors and 93.57-96.71% correct in its benign diagnosis. CONCLUSION: Hybrid diagnosis schemes represent a significant paradigm shift and provide a promising new technique to improve the specificity of nonlinear classifiers without seriously affecting the high sensitivity of nonlinear classifiers.

KW - Aspiration biopsy

KW - Breast cancer

KW - Computer assisted

KW - Diagnosis

UR - http://www.scopus.com/inward/record.url?scp=0042021835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042021835&partnerID=8YFLogxK

M3 - Article

VL - 25

SP - 183

EP - 190

JO - Analytical and Quantitative Cytopathology and Histopathology

JF - Analytical and Quantitative Cytopathology and Histopathology

SN - 0301-102X

IS - 4

ER -