Automatic dirt trail analysis in dermoscopy images

• Published in: Skin research and technology Vol. 19; no. 1; pp. e20 - e26
• Main Authors: Cheng, Beibei, Joe Stanley, R., Stoecker, William V., Osterwise, Christopher T. P., Stricklin, Sherea M., Hinton, Kristen A., Moss, Randy H., Oliviero, Margaret, Rabinovitz, Harold S.
• Format: Journal Article
• Language: English
• Published: England Blackwell Publishing Ltd 01.02.2013; John Wiley & Sons, Inc
• Subjects: Algorithms; basal cell carcinoma; Carcinoma, Basal Cell - pathology; dermoscopy; Dermoscopy - instrumentation; Dermoscopy - methods; Diagnosis, Differential; dirt trails; Feasibility Studies; Humans; image analysis; Image Processing, Computer-Assisted - instrumentation; Image Processing, Computer-Assisted - methods; Logistic Models; Medical diagnosis; Models, Theoretical; neural network; Neural Networks, Computer; ROC Curve; Skin - pathology; Skin cancer; Skin Neoplasms - pathology; Studies
• ISSN: 0909-752X; 1600-0846
• DOI: 10.1111/j.1600-0846.2011.00602.x

Background Basal cell carcinoma (BCC) is the most common cancer in the US. Dermatoscopes are devices used by physicians to facilitate the early detection of these cancers based on the identification of skin lesion structures often specific to BCCs. One new lesion structure, referred to as dirt trails, has the appearance of dark gray, brown or black dots and clods of varying sizes distributed in elongated clusters with indistinct borders, often appearing as curvilinear trails. Methods In this research, we explore a dirt trail detection and analysis algorithm for extracting, measuring, and characterizing dirt trails based on size, distribution, and color in dermoscopic skin lesion images. These dirt trails are then used to automatically discriminate BCC from benign skin lesions. Results For an experimental data set of 35 BCC images with dirt trails and 79 benign lesion images, a neural network‐based classifier achieved a 0.902 are under a receiver operating characteristic curve using a leave‐one‐out approach. Conclusion Results obtained from this study show that automatic detection of dirt trails in dermoscopic images of BCC is feasible. This is important because of the large number of these skin cancers seen every year and the challenge of discovering these earlier with instrumentation.