An efficient feature selection algorithm for computer-aided polyp detection

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

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

We present an efficient feature selection algorithm for computer aided detection (CAD) computed tomographic (CT) colonography. The algorithm (1) determines an appropriate piecewise linear network (PLN) model by cross validation, (2) applies the orthonormal least square (OLS) procedure to the PLN model utilizing a Modified Schmidt procedure, and (3) uses a floating search algorithm to select features that minimize the output variance. The undesirable "nesting effect" is prevented by the floating search approach, and the piecewise linear OLS procedure makes this algorithm very computationally efficient because the Modified Schmidt procedure only requires one data pass during the whole searching process. The selected features are compared to those obtained by other methods, through cross validation with support vector machines (SVMs).

Original languageEnglish (US)
Pages (from-to)893-915
Number of pages23
JournalInternational Journal on Artificial Intelligence Tools
Volume15
Issue number6
DOIs
StatePublished - Dec 2006

Fingerprint

Feature extraction
Linear networks
Support vector machines

Keywords

  • Branch and bound
  • CAD
  • Feature selection
  • Floating search
  • Orthonormal least squares
  • Piecewise linear network

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

An efficient feature selection algorithm for computer-aided polyp detection. / Jiang, Li; Jianhua, Yao; Summers, Ronald M.; Petrick, Nicholas; Manry, Michael T.; Hara, Amy K.

In: International Journal on Artificial Intelligence Tools, Vol. 15, No. 6, 12.2006, p. 893-915.

Research output: Contribution to journalArticle

Jiang, Li ; Jianhua, Yao ; Summers, Ronald M. ; Petrick, Nicholas ; Manry, Michael T. ; Hara, Amy K. / An efficient feature selection algorithm for computer-aided polyp detection. In: International Journal on Artificial Intelligence Tools. 2006 ; Vol. 15, No. 6. pp. 893-915.
@article{3d8a9a8ad9864c8c974608f64265ab4c,
title = "An efficient feature selection algorithm for computer-aided polyp detection",
abstract = "We present an efficient feature selection algorithm for computer aided detection (CAD) computed tomographic (CT) colonography. The algorithm (1) determines an appropriate piecewise linear network (PLN) model by cross validation, (2) applies the orthonormal least square (OLS) procedure to the PLN model utilizing a Modified Schmidt procedure, and (3) uses a floating search algorithm to select features that minimize the output variance. The undesirable {"}nesting effect{"} is prevented by the floating search approach, and the piecewise linear OLS procedure makes this algorithm very computationally efficient because the Modified Schmidt procedure only requires one data pass during the whole searching process. The selected features are compared to those obtained by other methods, through cross validation with support vector machines (SVMs).",
keywords = "Branch and bound, CAD, Feature selection, Floating search, Orthonormal least squares, Piecewise linear network",
author = "Li Jiang and Yao Jianhua and Summers, {Ronald M.} and Nicholas Petrick and Manry, {Michael T.} and Hara, {Amy K.}",
year = "2006",
month = "12",
doi = "10.1142/S021821300600303X",
language = "English (US)",
volume = "15",
pages = "893--915",
journal = "International Journal on Artificial Intelligence Tools",
issn = "0218-2130",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

TY - JOUR

T1 - An efficient feature selection algorithm for computer-aided polyp detection

AU - Jiang, Li

AU - Jianhua, Yao

AU - Summers, Ronald M.

AU - Petrick, Nicholas

AU - Manry, Michael T.

AU - Hara, Amy K.

PY - 2006/12

Y1 - 2006/12

N2 - We present an efficient feature selection algorithm for computer aided detection (CAD) computed tomographic (CT) colonography. The algorithm (1) determines an appropriate piecewise linear network (PLN) model by cross validation, (2) applies the orthonormal least square (OLS) procedure to the PLN model utilizing a Modified Schmidt procedure, and (3) uses a floating search algorithm to select features that minimize the output variance. The undesirable "nesting effect" is prevented by the floating search approach, and the piecewise linear OLS procedure makes this algorithm very computationally efficient because the Modified Schmidt procedure only requires one data pass during the whole searching process. The selected features are compared to those obtained by other methods, through cross validation with support vector machines (SVMs).

AB - We present an efficient feature selection algorithm for computer aided detection (CAD) computed tomographic (CT) colonography. The algorithm (1) determines an appropriate piecewise linear network (PLN) model by cross validation, (2) applies the orthonormal least square (OLS) procedure to the PLN model utilizing a Modified Schmidt procedure, and (3) uses a floating search algorithm to select features that minimize the output variance. The undesirable "nesting effect" is prevented by the floating search approach, and the piecewise linear OLS procedure makes this algorithm very computationally efficient because the Modified Schmidt procedure only requires one data pass during the whole searching process. The selected features are compared to those obtained by other methods, through cross validation with support vector machines (SVMs).

KW - Branch and bound

KW - CAD

KW - Feature selection

KW - Floating search

KW - Orthonormal least squares

KW - Piecewise linear network

UR - http://www.scopus.com/inward/record.url?scp=33845623846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845623846&partnerID=8YFLogxK

U2 - 10.1142/S021821300600303X

DO - 10.1142/S021821300600303X

M3 - Article

AN - SCOPUS:33845623846

VL - 15

SP - 893

EP - 915

JO - International Journal on Artificial Intelligence Tools

JF - International Journal on Artificial Intelligence Tools

SN - 0218-2130

IS - 6

ER -