Feature subset selection using ICA for classifying emphysema in HRCT images

Mithun Nagendra Prasad; Arcot Sowmya; Inge Koch

doi:10.1109/ICPR.2004.1333824

Feature subset selection using ICA for classifying emphysema in HRCT images

Mithun Nagendra Prasad, Arcot Sowmya, Inge Koch

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

13 Citations (Scopus)

Abstract

Feature subset selection, applied as a pre-processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In recent years, data in some applications has increased in both the number of instances and features. It is in this context that we introduce a novel approach to reduce both instance and feature space through Independent Component Analysis (ICA) for the classification of Emphysema in High Resolution Computer Tomography (HRCT) images. The technique was tested successfully on 60 HRCT scans having Emphysema using three different classifiers (Naïve Bayes, C4.5 and Seeded K Means). The results were also compared against "density mask", a standard approach used for Emphysema detection in medical image analysis. In addition, the results were visually validated by radiologists.

Original language	English
Title of host publication	Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
Editors	J. Kittler, M. Petrou, M. Nixon
Pages	515-518
Number of pages	4
Volume	4
DOIs	https://doi.org/10.1109/ICPR.2004.1333824
Publication status	Published - 20 Dec 2004
Externally published	Yes
Event	17th International Conference on Pattern Recognition - Cambridge, United Kingdom Duration: 23 Aug 2004 → 26 Aug 2004

Conference

Conference	17th International Conference on Pattern Recognition
Abbreviated title	ICPR 2004
Country/Territory	United Kingdom
City	Cambridge
Period	23/08/04 → 26/08/04

Access to Document

10.1109/ICPR.2004.1333824

Cite this

@inproceedings{4375c9293090489ca2abf51ff20ce9fc,

title = "Feature subset selection using ICA for classifying emphysema in HRCT images",

abstract = "Feature subset selection, applied as a pre-processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In recent years, data in some applications has increased in both the number of instances and features. It is in this context that we introduce a novel approach to reduce both instance and feature space through Independent Component Analysis (ICA) for the classification of Emphysema in High Resolution Computer Tomography (HRCT) images. The technique was tested successfully on 60 HRCT scans having Emphysema using three different classifiers (Na{\"i}ve Bayes, C4.5 and Seeded K Means). The results were also compared against {"}density mask{"}, a standard approach used for Emphysema detection in medical image analysis. In addition, the results were visually validated by radiologists.",

author = "Prasad, {Mithun Nagendra} and Arcot Sowmya and Inge Koch",

year = "2004",

month = dec,

day = "20",

doi = "10.1109/ICPR.2004.1333824",

language = "English",

isbn = "0769521282",

volume = "4",

pages = "515--518",

editor = "J. Kittler and M. Petrou and M. Nixon",

booktitle = "Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004",

note = "17th International Conference on Pattern Recognition, ICPR 2004 ; Conference date: 23-08-2004 Through 26-08-2004",

}

Prasad, MN, Sowmya, A & Koch, I 2004, Feature subset selection using ICA for classifying emphysema in HRCT images. in J Kittler, M Petrou & M Nixon (eds), Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004. vol. 4, pp. 515-518, 17th International Conference on Pattern Recognition, Cambridge, United Kingdom, 23/08/04. https://doi.org/10.1109/ICPR.2004.1333824

TY - GEN

T1 - Feature subset selection using ICA for classifying emphysema in HRCT images

AU - Prasad, Mithun Nagendra

AU - Sowmya, Arcot

AU - Koch, Inge

PY - 2004/12/20

Y1 - 2004/12/20

N2 - Feature subset selection, applied as a pre-processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In recent years, data in some applications has increased in both the number of instances and features. It is in this context that we introduce a novel approach to reduce both instance and feature space through Independent Component Analysis (ICA) for the classification of Emphysema in High Resolution Computer Tomography (HRCT) images. The technique was tested successfully on 60 HRCT scans having Emphysema using three different classifiers (Naïve Bayes, C4.5 and Seeded K Means). The results were also compared against "density mask", a standard approach used for Emphysema detection in medical image analysis. In addition, the results were visually validated by radiologists.

AB - Feature subset selection, applied as a pre-processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In recent years, data in some applications has increased in both the number of instances and features. It is in this context that we introduce a novel approach to reduce both instance and feature space through Independent Component Analysis (ICA) for the classification of Emphysema in High Resolution Computer Tomography (HRCT) images. The technique was tested successfully on 60 HRCT scans having Emphysema using three different classifiers (Naïve Bayes, C4.5 and Seeded K Means). The results were also compared against "density mask", a standard approach used for Emphysema detection in medical image analysis. In addition, the results were visually validated by radiologists.

UR - http://www.scopus.com/inward/record.url?scp=10044266234&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2004.1333824

DO - 10.1109/ICPR.2004.1333824

M3 - Conference paper

AN - SCOPUS:10044266234

SN - 0769521282

VL - 4

SP - 515

EP - 518

BT - Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004

A2 - Kittler, J.

A2 - Petrou, M.

A2 - Nixon, M.

T2 - 17th International Conference on Pattern Recognition

Y2 - 23 August 2004 through 26 August 2004

ER -

Feature subset selection using ICA for classifying emphysema in HRCT images

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this