SLD-SAG: Enhanced Skin Lesion Diagnosis with SegNet based Segmentation and AlexNet based Prediction using Genetic Optimizer

Skin cancer is still life-threatening conditions in worldwide, emphasizing the need for accurate and timely diagnosis to improve patient outcomes. This research implies an innovative method for segmenting and detecting melonama by integrating advanced deep learning models with optimization algorithms. To address the challenges posed by low contrast and high similarity between cancerous and healthy skin regions, a SegNet architecture, augmented with residual connections and recurrent structures, is utilized for lesion segmentation, achieving a Jaccard coefficient of 90.48%. For classification, the AlexNet model demonstrates superior performance with an accuracy of 93.28%. The combination of cutting-edge deep learning methodologies and robust optimization techniques establishes a comprehensive framework for early-stage skin cancer detection and segmentation, contributing significantly to improve diagnostic precision and informed treatment strategies.