Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification

KM Clawson, PJ Morrow, BW Scotney, DJ McKenna, OM Dolan

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

1 Citation (Scopus)

Abstract

Malignant melanoma is the deadliest form of skin cancer and must be diagnosed and excised during its earliest stages. The development of computerised systems which accurately quantify features representative of this cancer aims to assist diagnosis and improve preoperative diagnostic accuracy. One clinical feature suggestive of malignancy is asymmetry, which considers lesion shape, colour distribution and texture. In this paper techniques for the detection of colour asymmetry are evaluated and a new method for visually displaying and quantifying colour asymmetry is proposed. Automatic induction methods and a neural network model are utilised to evaluate the diagnostic capability of our features and identify those of greatest relative importance. Results indicate that those features quantifying possible areas of regression are most indicative of colour asymmetry.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages75-82
Number of pages8
DOIs
Publication statusPublished - Sep 2007
EventInternational Machine Vision and Image Processing Conference, 2007 (IMVIP 2007) -
Duration: 1 Sep 2007 → …

Conference

ConferenceInternational Machine Vision and Image Processing Conference, 2007 (IMVIP 2007)
Period1/09/07 → …

Fingerprint

Surface analysis
Pigments
Skin
Color
Textures
Neural networks

Cite this

Clawson, KM ; Morrow, PJ ; Scotney, BW ; McKenna, DJ ; Dolan, OM. / Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification. Unknown Host Publication. 2007. pp. 75-82
@inproceedings{e210def22f154ce3935248f50ccb8043,
title = "Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification",
abstract = "Malignant melanoma is the deadliest form of skin cancer and must be diagnosed and excised during its earliest stages. The development of computerised systems which accurately quantify features representative of this cancer aims to assist diagnosis and improve preoperative diagnostic accuracy. One clinical feature suggestive of malignancy is asymmetry, which considers lesion shape, colour distribution and texture. In this paper techniques for the detection of colour asymmetry are evaluated and a new method for visually displaying and quantifying colour asymmetry is proposed. Automatic induction methods and a neural network model are utilised to evaluate the diagnostic capability of our features and identify those of greatest relative importance. Results indicate that those features quantifying possible areas of regression are most indicative of colour asymmetry.",
author = "KM Clawson and PJ Morrow and BW Scotney and DJ McKenna and OM Dolan",
year = "2007",
month = "9",
doi = "10.1109/IMVIP.2007.34",
language = "English",
pages = "75--82",
booktitle = "Unknown Host Publication",

}

Clawson, KM, Morrow, PJ, Scotney, BW, McKenna, DJ & Dolan, OM 2007, Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification. in Unknown Host Publication. pp. 75-82, International Machine Vision and Image Processing Conference, 2007 (IMVIP 2007), 1/09/07. https://doi.org/10.1109/IMVIP.2007.34

Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification. / Clawson, KM; Morrow, PJ; Scotney, BW; McKenna, DJ; Dolan, OM.

Unknown Host Publication. 2007. p. 75-82.

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

TY - GEN

T1 - Computerised Skin Lesion Surface Analysis for Pigment Asymmetry Quantification

AU - Clawson, KM

AU - Morrow, PJ

AU - Scotney, BW

AU - McKenna, DJ

AU - Dolan, OM

PY - 2007/9

Y1 - 2007/9

N2 - Malignant melanoma is the deadliest form of skin cancer and must be diagnosed and excised during its earliest stages. The development of computerised systems which accurately quantify features representative of this cancer aims to assist diagnosis and improve preoperative diagnostic accuracy. One clinical feature suggestive of malignancy is asymmetry, which considers lesion shape, colour distribution and texture. In this paper techniques for the detection of colour asymmetry are evaluated and a new method for visually displaying and quantifying colour asymmetry is proposed. Automatic induction methods and a neural network model are utilised to evaluate the diagnostic capability of our features and identify those of greatest relative importance. Results indicate that those features quantifying possible areas of regression are most indicative of colour asymmetry.

AB - Malignant melanoma is the deadliest form of skin cancer and must be diagnosed and excised during its earliest stages. The development of computerised systems which accurately quantify features representative of this cancer aims to assist diagnosis and improve preoperative diagnostic accuracy. One clinical feature suggestive of malignancy is asymmetry, which considers lesion shape, colour distribution and texture. In this paper techniques for the detection of colour asymmetry are evaluated and a new method for visually displaying and quantifying colour asymmetry is proposed. Automatic induction methods and a neural network model are utilised to evaluate the diagnostic capability of our features and identify those of greatest relative importance. Results indicate that those features quantifying possible areas of regression are most indicative of colour asymmetry.

U2 - 10.1109/IMVIP.2007.34

DO - 10.1109/IMVIP.2007.34

M3 - Conference contribution

SP - 75

EP - 82

BT - Unknown Host Publication

ER -