Skin Lesion Classification from Dermoscopy Image using Structural Features and Random Forest
In this paper, an automatic algorithm for dermoscopy image classification in malignant and benign classes is presented. In this algorithm, a preprocessing step is applied to remove noises and artificial effects and also enhance image quality. Then, Otsu thresholding method is used to separate the lesion from the healthy areas. After that, some conventional shape and color features are extracted from the segmented image. Moreover, to strength our features, we define seven innovative structural features based on structure and border of the segmented lesion. These features try to capture valuable information from non-uniformity of lesion for detecting the malignant lesion. The results show that when these features are added to conventional shape and color features, the performance of classification is improved. Finally, the classification procedure is performed by different classifiers and different combinations of features. The results show that Random Forest (RF) classifier obtains the best performance with accuracy rate of 93.5%, sensitivity of 95% and specificity of 92.1%.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.