Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2011 Oct 18;12 Suppl 10(Suppl 10):S12.
doi: 10.1186/1471-2105-12-S10-S12.

An improved border detection in dermoscopy images for density based clustering

Sait Suer  1 , Sinan Kockara, Mutlu Mete
Affiliations

An improved border detection in dermoscopy images for density based clustering

Sait Suer et al. BMC Bioinformatics. .

Abstract

Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. In current practice, dermatologists determine lesion area by manually drawing lesion borders. Therefore, automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is automated detection of lesion borders. To our knowledge, in our 2010 study we achieved one of the highest accuracy rates in the automated lesion border detection field by using modified density based clustering algorithm. In the previous study, we proposed a novel method which removes redundant computations in well-known spatial density based clustering algorithm, DBSCAN; thus, in turn it speeds up clustering process considerably.

Findings: Our previous study was heavily dependent on the pre-processing step which creates a binary image from original image. In this study, we embed a new distance measure to the existing algorithm. This provides twofold benefits. First, since new approach removes pre-processing step, it directly works on color images instead of binary ones. Thus, very important color information is not lost. Second, accuracy of delineated lesion borders is improved on 75% of 100 dermoscopy image dataset.

Conclusion: Previous and improved methods are tested within the same dermoscopy dataset along with the same set of dermatologist drawn ground truth images. Results revealed that the improved method directly works on color images without any pre-processing and generates more accurate results than existing method.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Density-reachability and density-connectivity
Figure 2
Figure 2
Convex hull which represents a primitive cluster. MinPts = 5.
Figure 3
Figure 3
Expanding a cluster
Figure 4
Figure 4
Unionized convex hulls generate a polygon.
Figure 5
Figure 5
Leading points (blue region).
Figure 6
Figure 6
Algorithm FDBLD
Figure 7
Figure 7
Function expand for FDBLD
Figure 8
Figure 8
Results generated by FDBLD with different distance measures
Figure 9
Figure 9
Comparison between our method and FDBLD (Mete et al. [13]), x direction is image numbers, y direction is border error of corresponding image.
See this image and copyright information in PMC

References

    1. National Cancer Institute. Common Cancer Types. http://www.cancer.gov/cancertopics/commoncancers Accessed June 2011.
    1. Jemal A, Siegel R, Xu J, Ward E. 2010 Cancer Statistics. CA Cancer J Clin. 2010. pp. 277–300. DOI: 10.3322/caac.20073. - PubMed
    1. American Cancer Society. Cancer Facts&Figures. 2010. http://www.cancer.org/acs/groups/content/@nho/documents/document/acspc-0... Accessed June 2011.
    1. Rigel DS, Carucci JA. Malignant melanoma: prevention, early detection, and treatment in the 21st century. CA Cancer J Clin. 2000;5(no:4, 50):215–236. - PubMed
    1. Lorentzen H, Weismann K, Petersen CS, Larsen FG, Secher L, Skødt V. Clinical and dermatoscopic diagnosis of malignant melanoma. Assessed by expert and non-expert groups. Acta dermato venereologica. 1999;79(4):3014. doi:10.1080/000155599750010715. PMID 10429989. - PubMed

Publication types