Border detection in dermoscopy images using statistical region merging Journal Article
| Authors: | Celebi, M. E.; Kingravi, H. A.; Iyatomi, H.; Aslandogan, Y. A.; Stoecker, W. V.; Moss, R. H.; Malters, J. M.; Grichnik, J. M.; Marghoob, A. A.; Rabinovitz, H. S.; Menzies, S. W. |
| Article Title: | Border detection in dermoscopy images using statistical region merging |
| 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 testedon 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. © 2008 The Authors Journal compilation © 2008 Blackwell Munksgaard. |
| Keywords: | diagnostic accuracy; melanoma; dermoscopy; image analysis; image interpretation, computer-assisted; skin neoplasms; skin cancer; automation; epiluminescence microscopy; pigmentation; skin; statistical analysis; data interpretation, statistical; computer assisted diagnosis; image enhancement; medical imaging; artificial intelligence; pattern recognition, automated; diagnostic error; intermethod comparison; health; segmentation; image processing; computer graphics; image display; computer-aided diagnosis (cad); imaging techniques; dermoscopy images; pigmented skin lesions; imaging systems; border detection; clustering algorithms; computer-aided diagnosis; statistical region merging; arsenic compounds; boolean functions; computer aided diagnosis; error detection; fuzzy clustering; merging; optical data processing; statistical methods; automated methods; extraction algorithms; fuzzy c means (fcm); image processing techniques; mean shift clustering; melanoma (mm); region merging; skin imaging technology; benign skin tumor; fuzzy system |
| Journal Title: | Skin Research and Technology |
| Volume: | 14 |
| Issue: | 3 |
| ISSN: | 0909-752X |
| Publisher: | Wiley Blackwell |
| Date Published: | 2008-08-01 |
| Start Page: | 347 |
| End Page: | 353 |
| Language: | English |
| DOI: | 10.1111/j.1600-0846.2008.00301.x |
| PUBMED: | 19159382 |
| PROVIDER: | scopus |
| PMCID: | PMC3160669 |
| DOI/URL: | |
| Notes: | --- - "Cited By (since 1996): 29" - "Export Date: 17 November 2011" - "CODEN: SRTEF" - "Source: Scopus" |
