Border detection in dermoscopy images using statistical region merging.

M Emre Celebi, Hassan A Kingravi, Hitoshi Iyatomi, Y Alp Aslandogan, William V Stoecker, Randy H Moss, Joseph M Malters, James M Grichnik, Ashfaq A Marghoob, Harold S Rabinovitz, Scott W Menzies
Author Information
  1. M Emre Celebi: Department of Computer Science, Louisiana State University in Shreveport, Shreveport, LA 71115, USA. ecelebi@lsus.edu

Abstract

BACKGROUND: As a result of advances in skin imaging technology and the development of suitable image processing techniques, during the last decade, there has been a significant increase of interest in the computer-aided diagnosis of melanoma. Automated border detection is one of the most important steps in this procedure, because the accuracy of the subsequent steps crucially depends on it.
METHODS: In this article, we present a fast and unsupervised approach to border detection in dermoscopy images of pigmented skin lesions based on the statistical region merging algorithm.
RESULTS: The method is tested on a set of 90 dermoscopy images. The border detection error is quantified by a metric in which three sets of dermatologist-determined borders are used as the ground-truth. The proposed method is compared with four state-of-the-art automated methods (orientation-sensitive fuzzy c-means, dermatologist-like tumor extraction algorithm, meanshift clustering, and the modified JSEG method).
CONCLUSION: The results demonstrate that the method presented here achieves both fast and accurate border detection in dermoscopy images.

References

  1. Comput Med Imaging Graph. 1998 Sep-Oct;22(5):375-89 [PMID: 9890182]
  2. IEEE Trans Pattern Anal Mach Intell. 2004 Nov;26(11):1452-8 [PMID: 15521493]
  3. Skin Res Technol. 2007 Nov;13(4):454-62 [PMID: 17908199]
  4. J Am Acad Dermatol. 1993 Oct;29(4):581-8 [PMID: 8408794]
  5. Melanoma Res. 2006 Apr;16(2):183-90 [PMID: 16567974]
  6. IEEE Trans Med Imaging. 1999 Feb;18(2):164-71 [PMID: 10232673]
  7. CA Cancer J Clin. 2007 Jan-Feb;57(1):43-66 [PMID: 17237035]
  8. Arch Dermatol. 1995 Mar;131(3):286-91 [PMID: 7887657]
  9. Skin Res Technol. 2005 Feb;11(1):17-26 [PMID: 15691255]

Grants

  1. R44 CA060294-02A2/NCI NIH HHS
  2. R44 CA101639/NCI NIH HHS
  3. 2R44 CA-101639-02A2/NCI NIH HHS

MeSH Term

Artificial Intelligence
Data Interpretation, Statistical
Dermoscopy
Humans
Image Enhancement
Image Interpretation, Computer-Assisted
Melanoma
Pattern Recognition, Automated
Skin Neoplasms

Word Cloud

Created with Highcharts 10.0.0detectionborderdermoscopyimagesmethodskinstepsfaststatisticalregionmergingalgorithmBACKGROUND:resultadvancesimagingtechnologydevelopmentsuitableimageprocessingtechniqueslastdecadesignificantincreaseinterestcomputer-aideddiagnosismelanomaAutomatedoneimportantprocedureaccuracysubsequentcruciallydependsitMETHODS:articlepresentunsupervisedapproachpigmentedlesionsbasedRESULTS:testedset90errorquantifiedmetricthreesetsdermatologist-determinedbordersusedground-truthproposedcomparedfourstate-of-the-artautomatedmethodsorientation-sensitivefuzzyc-meansdermatologist-liketumorextractionmeanshiftclusteringmodifiedJSEGCONCLUSION:resultsdemonstratepresentedachievesaccurateBorderusing

Similar Articles

Cited By