Optimal Artificial Intelligence Based Automated Skin Lesion Detection and Classification Model

Skin lesions have become a critical illness worldwide, and the earlier identification of skin using dermoscopic images can raise survival rate. Classification lesion from those will be tedious task. The accuracy classification is improved by use deep learning models. Recently, convolutional neural networks (CNN) been established in this domain, their techniques are extremely for feature extraction, leading to enhanced classification. With motivation, study focuses on design artificial intelligence (AI) based solutions, particularly (DL) algorithms, distinguish malignant benign images. This presents an automated detection technique utilizing optimized stacked sparse autoencoder (OSSAE) extractor with backpropagation network (BPNN), named OSSAE-BPNN technique. proposed contains multi-level thresholding segmentation detecting affected region. In addition, OSSAE BPNN classifier employed diagnosis. Moreover, parameter tuning SSAE model carried out sea gull optimization (SGO) algorithm. To showcase outcomes model, comprehensive experimental analysis performed benchmark dataset. findings demonstrated that approach outperformed other current strategies terms several assessment metrics.