Computer aided diagnosis of melanocytic tumors

The aim of this study was to check the applicability of tissue counter analysis (TCA) to the discrimination of benign common nevi and malignant melanoma lesions. TCA is based on the partition of the image into square elements of equal size where the features, are calculated out of each square element. The features, based on grey level histogram and co-occurrence matrix, allow the differentiation of homogeneous and high contrast tissue areas. 80 cases from microscopic views of benign common nevi and malignant melanoma were sampled. This study set was divided into a learning and test set. The classification was done by CART (Classification and Regression Trees) analysis. The features show for the benign common nevi a lower variance of the grey levels and the mean value lies in the range of higher grey levels than in the case of malignant melanoma. The distribution of the co-occurrence matrix elements is concentrated in the range of higher values with a lower variance than for the malignant melanoma. The results from classification show a clear-cut difference between common nevi and malignant melanoma. The classification correctly classified 92.7% of nevi elements and 92.1% of melanoma elements in the learning set. In the test set, discriminant analysis based on the percentage of “malignant elements” showed a correct classification of all cases. In conclusion, tissue counter analysis may be a useful method for the interpretation of melanocytic skin tumors.