Detection of atypical texture features in early malignant melanoma

Bijaya Shrestha, Joseph Bishop, Keong Kam, Xiaohe Chen, Randy H. Moss, William V. Stoecker, Scott Umbaugh, R. Joe Stanley, M. Emre Celebi, Ashfaq A. Marghoob, Giuseppe Argenziano, H. Peter Soyer

Research output: Contribution to journalArticle

Abstract

Background: The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods:: For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results: Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4%. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4-5 texels per mm. Conclusion: Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.

Original languageEnglish
Pages (from-to)60-65
Number of pages6
JournalSkin Research and Technology
Volume16
Issue number1
DOIs
Publication statusPublished - Feb 2010

Fingerprint

Melanoma
Dysplastic Nevus Syndrome
Dermoscopy

Keywords

  • Dermoscopy
  • Image analysis
  • Melanoma
  • Pigment network
  • Texel
  • Texture

ASJC Scopus subject areas

  • Dermatology

Cite this

Shrestha, B., Bishop, J., Kam, K., Chen, X., Moss, R. H., Stoecker, W. V., ... Soyer, H. P. (2010). Detection of atypical texture features in early malignant melanoma. Skin Research and Technology, 16(1), 60-65. https://doi.org/10.1111/j.1600-0846.2009.00402.x

Detection of atypical texture features in early malignant melanoma. / Shrestha, Bijaya; Bishop, Joseph; Kam, Keong; Chen, Xiaohe; Moss, Randy H.; Stoecker, William V.; Umbaugh, Scott; Stanley, R. Joe; Celebi, M. Emre; Marghoob, Ashfaq A.; Argenziano, Giuseppe; Soyer, H. Peter.

In: Skin Research and Technology, Vol. 16, No. 1, 02.2010, p. 60-65.

Research output: Contribution to journalArticle

Shrestha, B, Bishop, J, Kam, K, Chen, X, Moss, RH, Stoecker, WV, Umbaugh, S, Stanley, RJ, Celebi, ME, Marghoob, AA, Argenziano, G & Soyer, HP 2010, 'Detection of atypical texture features in early malignant melanoma', Skin Research and Technology, vol. 16, no. 1, pp. 60-65. https://doi.org/10.1111/j.1600-0846.2009.00402.x
Shrestha, Bijaya ; Bishop, Joseph ; Kam, Keong ; Chen, Xiaohe ; Moss, Randy H. ; Stoecker, William V. ; Umbaugh, Scott ; Stanley, R. Joe ; Celebi, M. Emre ; Marghoob, Ashfaq A. ; Argenziano, Giuseppe ; Soyer, H. Peter. / Detection of atypical texture features in early malignant melanoma. In: Skin Research and Technology. 2010 ; Vol. 16, No. 1. pp. 60-65.
@article{c89afe52f8314df6a6edcee9d7e211bb,
title = "Detection of atypical texture features in early malignant melanoma",
abstract = "Background: The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods:: For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results: Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4{\%}. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4-5 texels per mm. Conclusion: Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.",
keywords = "Dermoscopy, Image analysis, Melanoma, Pigment network, Texel, Texture",
author = "Bijaya Shrestha and Joseph Bishop and Keong Kam and Xiaohe Chen and Moss, {Randy H.} and Stoecker, {William V.} and Scott Umbaugh and Stanley, {R. Joe} and Celebi, {M. Emre} and Marghoob, {Ashfaq A.} and Giuseppe Argenziano and Soyer, {H. Peter}",
year = "2010",
month = "2",
doi = "10.1111/j.1600-0846.2009.00402.x",
language = "English",
volume = "16",
pages = "60--65",
journal = "Skin Research and Technology",
issn = "0909-752X",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Detection of atypical texture features in early malignant melanoma

AU - Shrestha, Bijaya

AU - Bishop, Joseph

AU - Kam, Keong

AU - Chen, Xiaohe

AU - Moss, Randy H.

AU - Stoecker, William V.

AU - Umbaugh, Scott

AU - Stanley, R. Joe

AU - Celebi, M. Emre

AU - Marghoob, Ashfaq A.

AU - Argenziano, Giuseppe

AU - Soyer, H. Peter

PY - 2010/2

Y1 - 2010/2

N2 - Background: The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods:: For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results: Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4%. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4-5 texels per mm. Conclusion: Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.

AB - Background: The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods:: For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results: Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4%. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4-5 texels per mm. Conclusion: Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.

KW - Dermoscopy

KW - Image analysis

KW - Melanoma

KW - Pigment network

KW - Texel

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=73549091692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73549091692&partnerID=8YFLogxK

U2 - 10.1111/j.1600-0846.2009.00402.x

DO - 10.1111/j.1600-0846.2009.00402.x

M3 - Article

C2 - 20384884

AN - SCOPUS:73549091692

VL - 16

SP - 60

EP - 65

JO - Skin Research and Technology

JF - Skin Research and Technology

SN - 0909-752X

IS - 1

ER -