Content-based image retrieval in dermatology using intelligent technique

This study proposes a content-based image retrieval system for skin lesion images as a diagnostic aid. Effectiveness is measured by the rate of correct retrieval of images from skin lesions. The proposed architecture is used to retrieve digital images and the name of the disease category from an image data repository by the contents in the image, such as shape, texture and colour that is extracted from the image. The author's proposed algorithm used feature vector, classification and regression tree to retrieve comprehensive reference sources for diagnostic purpose. The results proved using a receiver operating characteristic curve that the proposed architecture has high contribute to computer-aided diagnosis of skin lesions. Experiments on a set of 1210 images yielded a specificity of 97.25% and a sensitivity of 91.24%. Their empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other works. The authors present explicit combinations of feature vectors corresponding to healthy and lesion skin.