Abstract
Skin cancer diagnosis relies on the accurate analysis of medical images to identify malignant and benign lesions. The Shearlet transform, a powerful mathematical tool for multiresolution analysis, has shown promise in enhancing the detection and classification of skin cancer. This study investigates the application of Shearlet transform-based multiresolution analysis in skin cancer diagnosis. The Shearlet transform, known for its ability to capture anisotropic features and directional information, provides a comprehensive representation of skin lesion images at multiple scales and orientations. We integrate the Shearlet transform with advanced image processing techniques to extract discriminative features from dermoscopic images. These features are then utilized to train a machine learning classifier, specifically a support vector machine (SVM), to distinguish between malignant and benign skin lesions. The proposed methodology is evaluated on a publicly available dataset, and the results demonstrate significant improvements in diagnostic accuracy compared to traditional methods. Our approach enhances feature extraction capabilities, leading to more reliable and precise skin cancer diagnosis, ultimately contributing to better patient outcomes.