Hybrid committee classifier for a computerized colonic polyp detection system

Jiang Li, Jianhua Yao, Nicholas Petrick, Ronald M. Summers, Amy K. Hara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features (numbers varied from 10-20) were selected for 11 NN classifiers which were again combined to form a NN committee classifier. Finally, a hybrid committee classifier was defined by combining the outputs of both the SVM and NN committees. The method was tested on CTC scans (supine and prone views) of 29 patients, in terms of the partial area under a free response receiving operation characteristic (FROC) curve (AUC). Our results showed that the hybrid committee classifier performed the best for the prone scans and was comparable to other classifiers for the supine scans.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6144 III
DOIs
StatePublished - 2006
EventMedical Imaging 2006: Image Processing - San Diego, CA
Duration: Feb 13 2006Feb 16 2006

Other

OtherMedical Imaging 2006: Image Processing
CitySan Diego, CA
Period2/13/062/16/06

Fingerprint

Classifiers
Neural networks
Support vector machines
Computerized tomography

Keywords

  • Classifier Committee
  • Computer-Aided Detection
  • Neural Network
  • Pattern Recognition
  • Statistical Methods
  • Support Vector Machine

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, J., Yao, J., Petrick, N., Summers, R. M., & Hara, A. K. (2006). Hybrid committee classifier for a computerized colonic polyp detection system. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 6144 III). [61445A] https://doi.org/10.1117/12.652724

Hybrid committee classifier for a computerized colonic polyp detection system. / Li, Jiang; Yao, Jianhua; Petrick, Nicholas; Summers, Ronald M.; Hara, Amy K.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 III 2006. 61445A.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, J, Yao, J, Petrick, N, Summers, RM & Hara, AK 2006, Hybrid committee classifier for a computerized colonic polyp detection system. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 6144 III, 61445A, Medical Imaging 2006: Image Processing, San Diego, CA, 2/13/06. https://doi.org/10.1117/12.652724
Li J, Yao J, Petrick N, Summers RM, Hara AK. Hybrid committee classifier for a computerized colonic polyp detection system. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 III. 2006. 61445A https://doi.org/10.1117/12.652724
Li, Jiang ; Yao, Jianhua ; Petrick, Nicholas ; Summers, Ronald M. ; Hara, Amy K. / Hybrid committee classifier for a computerized colonic polyp detection system. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6144 III 2006.
@inproceedings{99ea58de666349b0bb426159672ecf8d,
title = "Hybrid committee classifier for a computerized colonic polyp detection system",
abstract = "We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features (numbers varied from 10-20) were selected for 11 NN classifiers which were again combined to form a NN committee classifier. Finally, a hybrid committee classifier was defined by combining the outputs of both the SVM and NN committees. The method was tested on CTC scans (supine and prone views) of 29 patients, in terms of the partial area under a free response receiving operation characteristic (FROC) curve (AUC). Our results showed that the hybrid committee classifier performed the best for the prone scans and was comparable to other classifiers for the supine scans.",
keywords = "Classifier Committee, Computer-Aided Detection, Neural Network, Pattern Recognition, Statistical Methods, Support Vector Machine",
author = "Jiang Li and Jianhua Yao and Nicholas Petrick and Summers, {Ronald M.} and Hara, {Amy K.}",
year = "2006",
doi = "10.1117/12.652724",
language = "English (US)",
isbn = "0819464236",
volume = "6144 III",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Hybrid committee classifier for a computerized colonic polyp detection system

AU - Li, Jiang

AU - Yao, Jianhua

AU - Petrick, Nicholas

AU - Summers, Ronald M.

AU - Hara, Amy K.

PY - 2006

Y1 - 2006

N2 - We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features (numbers varied from 10-20) were selected for 11 NN classifiers which were again combined to form a NN committee classifier. Finally, a hybrid committee classifier was defined by combining the outputs of both the SVM and NN committees. The method was tested on CTC scans (supine and prone views) of 29 patients, in terms of the partial area under a free response receiving operation characteristic (FROC) curve (AUC). Our results showed that the hybrid committee classifier performed the best for the prone scans and was comparable to other classifiers for the supine scans.

AB - We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features (numbers varied from 10-20) were selected for 11 NN classifiers which were again combined to form a NN committee classifier. Finally, a hybrid committee classifier was defined by combining the outputs of both the SVM and NN committees. The method was tested on CTC scans (supine and prone views) of 29 patients, in terms of the partial area under a free response receiving operation characteristic (FROC) curve (AUC). Our results showed that the hybrid committee classifier performed the best for the prone scans and was comparable to other classifiers for the supine scans.

KW - Classifier Committee

KW - Computer-Aided Detection

KW - Neural Network

KW - Pattern Recognition

KW - Statistical Methods

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=33745152343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745152343&partnerID=8YFLogxK

U2 - 10.1117/12.652724

DO - 10.1117/12.652724

M3 - Conference contribution

SN - 0819464236

SN - 9780819464231

VL - 6144 III

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -