Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform

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

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

13 Citations (Scopus)

Abstract

The development of computerised systems which differentiate between suspicious tumours and clinically benign pigmented skin lesions can assist in improved early diagnosis of malignant melanoma, subsequently reducing mortality rates associated with this disease. One lesion feature indicative of malignancy is border irregularity. In this paper the theoretical fundamentals of a harmonic-wavelet based methodology for skin lesion border evaluation are described. Our methodology is applied to the boundaries of 30 cutaneous lesions and classification algorithms are consequently utilised to evaluate the effectiveness of descriptors for differentiating between regular / irregular borders and between benign/malignant tumours. Results indicate that generated parameters have high discriminative value when differentiating between benign and malignant lesions: maximum classification accuracy achieved was 93.3%, with 80% sensitivity.
Original languageEnglish
Title of host publicationUnknown Host Publication
Pages18-23
Number of pages6
DOIs
Publication statusPublished - Sep 2009
EventInternational Machine Vision and Image Processing Conference (IMVIP 2009) - Dublin, Ireland
Duration: 1 Sep 2009 → …

Conference

ConferenceInternational Machine Vision and Image Processing Conference (IMVIP 2009)
Period1/09/09 → …

Fingerprint

Wavelet Analysis
Skin
Neoplasms
Early Diagnosis
Melanoma
Mortality

Cite this

Clawson, KM ; Morrow, PJ ; Scotney, BW ; McKenna, DJ ; Dolan, OM. / Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform. Unknown Host Publication. 2009. pp. 18-23
@inproceedings{64403cab74f54740878d9d50877f82d7,
title = "Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform",
abstract = "The development of computerised systems which differentiate between suspicious tumours and clinically benign pigmented skin lesions can assist in improved early diagnosis of malignant melanoma, subsequently reducing mortality rates associated with this disease. One lesion feature indicative of malignancy is border irregularity. In this paper the theoretical fundamentals of a harmonic-wavelet based methodology for skin lesion border evaluation are described. Our methodology is applied to the boundaries of 30 cutaneous lesions and classification algorithms are consequently utilised to evaluate the effectiveness of descriptors for differentiating between regular / irregular borders and between benign/malignant tumours. Results indicate that generated parameters have high discriminative value when differentiating between benign and malignant lesions: maximum classification accuracy achieved was 93.3{\%}, with 80{\%} sensitivity.",
author = "KM Clawson and PJ Morrow and BW Scotney and DJ McKenna and OM Dolan",
year = "2009",
month = "9",
doi = "10.1109/IMVIP.2009.11",
language = "English",
pages = "18--23",
booktitle = "Unknown Host Publication",

}

Clawson, KM, Morrow, PJ, Scotney, BW, McKenna, DJ & Dolan, OM 2009, Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform. in Unknown Host Publication. pp. 18-23, International Machine Vision and Image Processing Conference (IMVIP 2009), 1/09/09. https://doi.org/10.1109/IMVIP.2009.11

Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform. / Clawson, KM; Morrow, PJ; Scotney, BW; McKenna, DJ; Dolan, OM.

Unknown Host Publication. 2009. p. 18-23.

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

TY - GEN

T1 - Analysis of Pigmented Skin Lesion Border Irregularity Using the Harmonic Wavelet Transform

AU - Clawson, KM

AU - Morrow, PJ

AU - Scotney, BW

AU - McKenna, DJ

AU - Dolan, OM

PY - 2009/9

Y1 - 2009/9

N2 - The development of computerised systems which differentiate between suspicious tumours and clinically benign pigmented skin lesions can assist in improved early diagnosis of malignant melanoma, subsequently reducing mortality rates associated with this disease. One lesion feature indicative of malignancy is border irregularity. In this paper the theoretical fundamentals of a harmonic-wavelet based methodology for skin lesion border evaluation are described. Our methodology is applied to the boundaries of 30 cutaneous lesions and classification algorithms are consequently utilised to evaluate the effectiveness of descriptors for differentiating between regular / irregular borders and between benign/malignant tumours. Results indicate that generated parameters have high discriminative value when differentiating between benign and malignant lesions: maximum classification accuracy achieved was 93.3%, with 80% sensitivity.

AB - The development of computerised systems which differentiate between suspicious tumours and clinically benign pigmented skin lesions can assist in improved early diagnosis of malignant melanoma, subsequently reducing mortality rates associated with this disease. One lesion feature indicative of malignancy is border irregularity. In this paper the theoretical fundamentals of a harmonic-wavelet based methodology for skin lesion border evaluation are described. Our methodology is applied to the boundaries of 30 cutaneous lesions and classification algorithms are consequently utilised to evaluate the effectiveness of descriptors for differentiating between regular / irregular borders and between benign/malignant tumours. Results indicate that generated parameters have high discriminative value when differentiating between benign and malignant lesions: maximum classification accuracy achieved was 93.3%, with 80% sensitivity.

UR - http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=5319272

UR - http://ieeexplore.ieee.org/xpl/RecentCon.jsp?punumber=5319272

U2 - 10.1109/IMVIP.2009.11

DO - 10.1109/IMVIP.2009.11

M3 - Conference contribution

SP - 18

EP - 23

BT - Unknown Host Publication

ER -