Application of decision trees for mass classification in mammography

Kuldeep Kumar, Ping Zhang, Brijesh Verma

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

This paper discusses the effectiveness of using decision trees for mass classification in mammography. The decision tree algorithms implemented by CART (Classification and Regression Trees) and See5 were used for the experiments. Different costs for type I and type II misclassification were applied for the experiments. The results obtained using algorithms based on decision trees were compared with that produced by neural network which was reported giving the higher classification rate than statistical models, with higher standard deviation. It is concluded that the decision trees are very promising for the classification of breast masses in digital mammograms.
Original languageEnglish
Pages366-376
Number of pages11
Publication statusPublished - 2006
EventThe 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery : ICNC 2006 and FSKD 2006 - Xi'an, China
Duration: 24 Sep 200628 Sep 2006

Conference

ConferenceThe 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery
CountryChina
CityXi'an
Period24/09/0628/09/06

Fingerprint

experiment
decision
cost
rate

Cite this

Kumar, K., Zhang, P., & Verma, B. (2006). Application of decision trees for mass classification in mammography. 366-376. Paper presented at The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery , Xi'an, China.
Kumar, Kuldeep ; Zhang, Ping ; Verma, Brijesh. / Application of decision trees for mass classification in mammography. Paper presented at The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery , Xi'an, China.11 p.
@conference{3d79617577374ca1bce6580d2d9865c7,
title = "Application of decision trees for mass classification in mammography",
abstract = "This paper discusses the effectiveness of using decision trees for mass classification in mammography. The decision tree algorithms implemented by CART (Classification and Regression Trees) and See5 were used for the experiments. Different costs for type I and type II misclassification were applied for the experiments. The results obtained using algorithms based on decision trees were compared with that produced by neural network which was reported giving the higher classification rate than statistical models, with higher standard deviation. It is concluded that the decision trees are very promising for the classification of breast masses in digital mammograms.",
author = "Kuldeep Kumar and Ping Zhang and Brijesh Verma",
year = "2006",
language = "English",
pages = "366--376",
note = "The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery : ICNC 2006 and FSKD 2006 ; Conference date: 24-09-2006 Through 28-09-2006",

}

Kumar, K, Zhang, P & Verma, B 2006, 'Application of decision trees for mass classification in mammography' Paper presented at The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery , Xi'an, China, 24/09/06 - 28/09/06, pp. 366-376.

Application of decision trees for mass classification in mammography. / Kumar, Kuldeep; Zhang, Ping; Verma, Brijesh.

2006. 366-376 Paper presented at The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery , Xi'an, China.

Research output: Contribution to conferencePaperResearchpeer-review

TY - CONF

T1 - Application of decision trees for mass classification in mammography

AU - Kumar, Kuldeep

AU - Zhang, Ping

AU - Verma, Brijesh

PY - 2006

Y1 - 2006

N2 - This paper discusses the effectiveness of using decision trees for mass classification in mammography. The decision tree algorithms implemented by CART (Classification and Regression Trees) and See5 were used for the experiments. Different costs for type I and type II misclassification were applied for the experiments. The results obtained using algorithms based on decision trees were compared with that produced by neural network which was reported giving the higher classification rate than statistical models, with higher standard deviation. It is concluded that the decision trees are very promising for the classification of breast masses in digital mammograms.

AB - This paper discusses the effectiveness of using decision trees for mass classification in mammography. The decision tree algorithms implemented by CART (Classification and Regression Trees) and See5 were used for the experiments. Different costs for type I and type II misclassification were applied for the experiments. The results obtained using algorithms based on decision trees were compared with that produced by neural network which was reported giving the higher classification rate than statistical models, with higher standard deviation. It is concluded that the decision trees are very promising for the classification of breast masses in digital mammograms.

M3 - Paper

SP - 366

EP - 376

ER -

Kumar K, Zhang P, Verma B. Application of decision trees for mass classification in mammography. 2006. Paper presented at The 2nd International Conference on Natural Computation and the 3rd International Conference on Fuzzy systems and Knowledge Discovery , Xi'an, China.