Blue-gray ovoids (B-GOs) are critical dermoscopic structures in basal cell carcinomas (BCCs) that pose a challenge for automatic detection. Due to variation in size and color, B-GOs can be easily mistaken for similar structures in benign lesions. Analysis of these structures could help further accomplish the goal of automatic BCC detection. This study introduces an efficient sector-based method for segmenting B-GOs. Four modifications of conventional region-growing techniques are presented: (i) employing a seed area rather than a seed point, (ii) utilizing fixed control limits determined from the seed area to eliminate re-calculations of previously-added regions, (iii) determining region growing criteria using logistic regression, and (iv) area analysis and expansion by sectors. Contact dermoscopy images of 68 confirmed BCCs having B-GOs were obtained. A total of 24 color features were analyzed for all B-GO seed areas. Logistic regression analysis determined blue chromaticity, followed by red variance, were the best features for discriminating B-GO edges from surrounding areas. Segmentation of malignant structures obtained an average Pratt's figure of merit of 0.397. The techniques presented here provide a non-recursive, sector-based, region-growing method applicable to any colored structure appearing in digital images. Further research using these techniques could lead to automatic detection of B-GOs in BCCs.
Keywords: Blue gray ovoids; basal cell carcinoma; cancer detection; dermoscopy; feature extraction; image analysis; region growing.
© 2013 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.