An Efficient Hybrid Optimization for Skin Cancer Detection Using PNN Classifier

The necessity of on-time cancer detection is extremely high in the recent days as it becomes a threat to human life. skin considered one dangerous diseases among other types since causes severe health impacts on beings and hence highly mandatory detect early stage for providing adequate treatment. Therefore, an effective image processing approach employed this present study accurate cancer. Initially, dermoscopy images lesions are retrieved processed by eliminating noises with assistance Gabor filter. Then, pre-processed segmented into multiple regions implementing cascaded Fuzzy C-Means (FCM) algorithm, which involves improving reliability detection. A Response Co-occurrence Matrix (GRCM) used extract melanoma parameters efficient manner. hybrid Particle Swarm Optimization (PSO)-Whale then utilized efficiently optimizing extracted features. Finally, features significantly classified Probabilistic Neural Network (PNN) classifier classifying stages lesion optimal whole work stimulated MATLAB attained outcomes have proved that introduced delivers results maximal accuracy 97.83%.