Skin lesion classification is a significant challenge in the medical field, particularly in the early detection of malignant skin lesions. Traditional methods require large amounts of data and often struggle to handle heterogeneous datasets, especially in medical datasets where there is an uneven distribution of disease types. A novel approach has been proposed that integrates Energy-Based Models (EBM) with an Energy Distance (ED) approach. This method aims to incorporate ED into the training process of the EBM model. The experimental results on the ISIC_2019 dataset achieved classification accuracy of 74.19%, a sensitivity of 60.29%, and a specificity of 95.46%. This shows that the proposed model is capable of classifying skin lesions with expected results, particularly showing better handling of imbalanced datasets. With the achieved results, along with the desire to contribute a new approach to skin lesion classification in particular and medical image classification in general, this method also provides an effective diagnostic support tool.