Detection of atypical texture features in early malignant melanoma

• Published in: Skin research and technology 2010-02, Vol.16 (1), p.60-65
• Main Authors: Shrestha, Bijaya, Bishop, Joseph, Kam, Keong, Chen, Xiaohe, Moss, Randy H., Stoecker, William V., Umbaugh, Scott, Stanley, R. Joe, Celebi, M. Emre, Marghoob, Ashfaq A., Argenziano, Giuseppe, Soyer, H. Peter
• Format: Article
• Language: English
• Subjects: Carcinoma in Situ - pathology; Databases, Factual; dermoscopy; Dermoscopy - methods; Dermoscopy - standards; Diagnosis, Differential; Dysplastic Nevus Syndrome - pathology; Early Diagnosis; Humans; Hutchinson's Melanotic Freckle - pathology; image analysis; Image Processing, Computer-Assisted - methods; Image Processing, Computer-Assisted - standards; melanoma; Melanoma - pathology; pigment network; Reproducibility of Results; Skin Neoplasms - pathology; texel; texture
• ISSN: 0909-752X; 1600-0846
• DOI: 10.1111/j.1600-0846.2009.00402.x

Background: The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods: For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results: Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4%. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4–5 texels per mm. Conclusion: Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.