Skin Lesion Decode A CNN-SVM Convergence for Enhanced Diagnostic Accuracy

This research study investigates the development and evaluation of a merged CNN and SVM model for detecting and classifying skin lesions. The research systematically divides skin lesions into five categories that allow a thorough analysis of the model's diagnostic skills. The CNN-SVM model is developed and tested using a high-quality dataset, and its accuracy, recall, and F1 scores provide insights into specific performance aspects of the model. The results show a high level of precision for all the classes that vary from 92.95% for Class 1 to 95.95% for Class 5, which suggests that the model is good at making optimistic predictions. The recall measure, a sensitivity measure of the model, varies from 91.44% for Class 3 to 98.47% for Class 1, indicating the model's capability to recognize true positives correctly. The F1-score, which balances precision and recall, is always high, fluctuating from 93.00% for Class 3 to 96.28% for Class 5, reflecting the model's well-balanced categorization. Several types of averages are computed to assess the model's performance thoroughly. The macro average indicates accuracy of 94.70%, recall of 94.81%, and F1-score of 94.73%, with equal weight given to each class. With class distribution, the weighted average is as follows: accuracy - 94.74%, recall - 94.72%, F1-score - 94.71%. The micro average indicating the sum of contributions from all classes is 94.72% for all three parameters across the board. The model is entirely accurate, with an overall accuracy of 94.72397, showing the model's strong ability to generalize across different skin lesion types. The statistical measures confirm the CNN-SVM model as a practical approach to accurate and reliable classification of skin lesions, revealing high clinical potential. The paper's impressive experimental and statistical analyses demonstrate the power of the model and its ability to improve dermatological diagnostic procedures.