Abstract - Cancer, characterized by uncontrolled cell growth, poses a significant threat to health, with skin cancer being particularly hazardous due to its prevalence across the body’s tissues. Typically originating in the outer layers of the skin, skin cancer presents initially as abnormal growths or lesions. To address this issue, various computer-aided techniques have been employed. In this study, we propose a novel approach combining a Fuzzy Neural Network with Jaya Optimization classification (FNN-JO) for skin cancer image analysis. Initially, a hybrid strategy integrating Particle Swarm Optimization (PSO) and Anisotropic Diffusion Filter (ADF), known as ADF-PSO, is utilized to enhance the quality of input medical images while preserving edge details. Subsequently, the Modified Marker Controlled Watershed Algorithm is employed for image segmentation, followed by morphological post-processing for refinement. To enhance prediction accuracy, specific features such as area, perimeter, GLCM, Major and Minor axes, concavity, eccentricity, and filled area are extracted. The FNN-JO classifier is then employed for skin cancer classification, leveraging JO to classify features effectively. Simulation results demonstrate that the proposed FNN-JO outperforms existing classification schemes, including the Adaptive Neuro Fuzzy Inference System (ANFIS) and conventional FNN approaches, in terms of accuracy and performance.