Concentric decile segmentation of white and hypopigmented areas in dermoscopy images of skin lesions allows discrimination of malignant melanoma.

Ankur Dalal, Randy H Moss, R Joe Stanley, William V Stoecker, Kapil Gupta, David A Calcara, Jin Xu, Bijaya Shrestha, Rhett Drugge, Joseph M Malters, Lindall A Perry
Author Information
  1. Ankur Dalal: Department of Electrical and Computer Engineering, Missouri University of Science and Technology, 116 Emerson Electric Company Hall, 301 West 16th Street, Rolla, MO 65409-0040, USA. addgf3@mst.edu

Abstract

Dermoscopy, also known as dermatoscopy or epiluminescence microscopy (ELM), permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. White areas, prominent in early malignant melanoma and melanoma in situ, contribute to early detection of these lesions. An adaptive detection method has been investigated to identify white and hypopigmented areas based on lesion histogram statistics. Using the Euclidean distance transform, the lesion is segmented in concentric deciles. Overlays of the white areas on the lesion deciles are determined. Calculated features of automatically detected white areas include lesion decile ratios, normalized number of white areas, absolute and relative size of largest white area, relative size of all white areas, and white area eccentricity, dispersion, and irregularity. Using a back-propagation neural network, the white area statistics yield over 95% diagnostic accuracy of melanomas from benign nevi. White and hypopigmented areas in melanomas tend to be central or paracentral. The four most powerful features on multivariate analysis are lesion decile ratios. Automatic detection of white and hypopigmented areas in melanoma can be accomplished using lesion statistics. A neural network can achieve good discrimination of melanomas from benign nevi using these areas. Lesion decile ratios are useful white area features.

References

  1. Skin Res Technol. 2005 Feb;11(1):36-41 [PMID: 15691257]
  2. Dermatol Clin. 2001 Apr;19(2):337-45 [PMID: 11556242]
  3. J Am Acad Dermatol. 2003 May;48(5):679-93 [PMID: 12734496]
  4. Skin Res Technol. 2005 Aug;11(3):179-84 [PMID: 15998328]
  5. CA Cancer J Clin. 2009 Jul-Aug;59(4):225-49 [PMID: 19474385]
  6. Br J Dermatol. 2007 Nov;157(5):907-13 [PMID: 17725673]
  7. Comput Med Imaging Graph. 2009 Mar;33(2):148-53 [PMID: 19121917]
  8. Br J Dermatol. 2004 Jan;150(1):64-71 [PMID: 14746618]

Grants

  1. R44 CA060294-02A2/NCI NIH HHS
  2. R44 CA101639/NCI NIH HHS
  3. R44 CA-01639-02A2/NCI NIH HHS

MeSH Term

Algorithms
Dermoscopy
Humans
Image Enhancement
Image Interpretation, Computer-Assisted
Luminescent Measurements
Melanoma
Pattern Recognition, Automated
Reproducibility of Results
Sensitivity and Specificity
Skin Neoplasms

Word Cloud

Created with Highcharts 10.0.0whiteareaslesionfeaturesmelanomahypopigmenteddecileareadetectionstatisticsratiosmelanomasWhiteearlymalignantlesionsUsingdecilesrelativesizeneuralnetworkbenignnevicanusingdiscriminationDermoscopyalsoknowndermatoscopyepiluminescencemicroscopyELMpermitsvisualizationpigmentedmelanocyticneoplasmsdiscernableexaminationnakedeyeprominentsitucontributeadaptivemethodinvestigatedidentifybasedhistogramEuclideandistancetransformsegmentedconcentricOverlaysdeterminedCalculatedautomaticallydetectedincludenormalizednumberabsolutelargesteccentricitydispersionirregularityback-propagationyield95%diagnosticaccuracytendcentralparacentralfourpowerfulmultivariateanalysisAutomaticaccomplishedachievegoodLesionusefulConcentricsegmentationdermoscopyimagesskinallows

Similar Articles

Cited By