Thresholding methods for lesion segmentation of basal cell carcinoma in dermoscopy images

• Published in: Skin research and technology 2017-08, Vol.23 (3), p.416-428
• Main Authors: Kaur, R., LeAnder, R., Mishra, N. K., Hagerty, J. R., Kasmi, R., Stanley, R. J., Celebi, M. E., Stoecker, W. V.
• Format: Article
• Language: English
• Subjects: Algorithms; Basal cell carcinoma; Borders; Carcinoma, Basal Cell - classification; Carcinoma, Basal Cell - diagnostic imaging; Carcinoma, Basal Cell - pathology; Classification; dermoscopy; Dermoscopy - instrumentation; Dermoscopy - methods; Error analysis; Errors; Huang method; Humans; image analysis; Image Interpretation, Computer-Assisted - methods; Image processing; Image segmentation; Isodata method; lesion segmentation; Li method; Melanoma - pathology; Otsu method; Pattern Recognition, Automated - methods; Shanbhag method; Skin cancer; Skin Neoplasms - diagnostic imaging; Skin Neoplasms - pathology; Test sets; thresholding; Vignetting
• ISSN: 0909-752X; 1600-0846
• DOI: 10.1111/srt.12352

Purpose Algorithms employed for pigmented lesion segmentation perform poorly on dermoscopy images of basal cell carcinoma (BCC), the most common skin cancer. The main objective was to develop better methods for BCC segmentation. Methods Fifteen thresholding methods were implemented for BCC lesion segmentation. We propose two error metrics that better measure the type II error: Relative XOR Error and Lesion Capture Ratio. Results On training/test sets of 305 and 34 BCC images, respectively, five new techniques outperform two state‐of‐the‐art methods used in segmentation of melanomas, based on the new error metrics. Conclusion The proposed algorithms, which include solutions for image vignetting correction and border expansion to achieve dermatologist‐like borders, provide more inclusive and feature‐preserving border detection, favoring better BCC classification accuracy, in future work.