Classification of melanoma using wavelet transform-based optimal feature set

Ronn Walvick; Ketan Patel; Sachin V. Patwardhan; Atam P. Dhawan

doi:10.1117/12.536013

Classification of melanoma using wavelet transform-based optimal feature set

Ronn Walvick, Ketan Patel, Sachin V. Patwardhan, Atam P. Dhawan

Research output: Contribution to journal › Conference article › peer-review

17 Scopus citations

Abstract

The features used in the ABCD rule for characterization of skin lesions suggest that the spatial and frequency information in the nevi changes at various stages of melanoma development. To analyze these changes wavelet transform based features have been reported. The classification of melanoma using these features has produced varying results. In this work, all the reported wavelet transform based features are combined to form a single feature set. This feature set is then optimized by removing redundancies using principal component analysis. A feed forward neural network trained with the back propagation algorithm is then used in the classification process to obtain better classification results.

Original language	English (US)
Pages (from-to)	944-951
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5370 II
DOIs	https://doi.org/10.1117/12.536013
State	Published - 2004
Event	Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing - San Diego, CA, United States Duration: Feb 16 2004 → Feb 19 2004

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Keywords

Melanoma
Neural Networks
Principal Component Analysis
Wavelet Transform

Access to Document

10.1117/12.536013

Cite this

@article{a9fb072151f3407ca0d3d8fdaead8447,

title = "Classification of melanoma using wavelet transform-based optimal feature set",

abstract = "The features used in the ABCD rule for characterization of skin lesions suggest that the spatial and frequency information in the nevi changes at various stages of melanoma development. To analyze these changes wavelet transform based features have been reported. The classification of melanoma using these features has produced varying results. In this work, all the reported wavelet transform based features are combined to form a single feature set. This feature set is then optimized by removing redundancies using principal component analysis. A feed forward neural network trained with the back propagation algorithm is then used in the classification process to obtain better classification results.",

keywords = "Melanoma, Neural Networks, Principal Component Analysis, Wavelet Transform",

author = "Ronn Walvick and Ketan Patel and Patwardhan, {Sachin V.} and Dhawan, {Atam P.}",

year = "2004",

doi = "10.1117/12.536013",

language = "English (US)",

volume = "5370 II",

pages = "944--951",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing ; Conference date: 16-02-2004 Through 19-02-2004",

}

TY - JOUR

T1 - Classification of melanoma using wavelet transform-based optimal feature set

AU - Walvick, Ronn

AU - Patel, Ketan

AU - Patwardhan, Sachin V.

AU - Dhawan, Atam P.

PY - 2004

Y1 - 2004

N2 - The features used in the ABCD rule for characterization of skin lesions suggest that the spatial and frequency information in the nevi changes at various stages of melanoma development. To analyze these changes wavelet transform based features have been reported. The classification of melanoma using these features has produced varying results. In this work, all the reported wavelet transform based features are combined to form a single feature set. This feature set is then optimized by removing redundancies using principal component analysis. A feed forward neural network trained with the back propagation algorithm is then used in the classification process to obtain better classification results.

AB - The features used in the ABCD rule for characterization of skin lesions suggest that the spatial and frequency information in the nevi changes at various stages of melanoma development. To analyze these changes wavelet transform based features have been reported. The classification of melanoma using these features has produced varying results. In this work, all the reported wavelet transform based features are combined to form a single feature set. This feature set is then optimized by removing redundancies using principal component analysis. A feed forward neural network trained with the back propagation algorithm is then used in the classification process to obtain better classification results.

KW - Melanoma

KW - Neural Networks

KW - Principal Component Analysis

KW - Wavelet Transform

UR - http://www.scopus.com/inward/record.url?scp=5644288612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5644288612&partnerID=8YFLogxK

U2 - 10.1117/12.536013

DO - 10.1117/12.536013

M3 - Conference article

AN - SCOPUS:5644288612

SN - 0277-786X

VL - 5370 II

SP - 944

EP - 951

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing

Y2 - 16 February 2004 through 19 February 2004

ER -

Classification of melanoma using wavelet transform-based optimal feature set

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this