An explainable digital twin framework for skin cancer analysis using early activation meta-learner

Skin cancer is among the most common cancers globally, which calls for timely and precise diagnosis for successful therapy. Conventional methods of diagnosis, including dermoscopy and histopathology, are significantly dependent on expert judgment and therefore are time-consuming and susceptible to inconsistencies. Deep learning algorithms have shown potential in skin cancer classification but tend to consume a substantial amount of computational resources and large training sets. To overcome these issues, we introduce a new hybrid computer-aided diagnosis (CAD) system that integrates Stem Block for feature extraction and machine learning for classification. The International Skin Imaging Collaboration (ISIC) skin cancer dermoscopic images were collected from Kaggle, and essential features were collected from the Stem Block of a deep learning (DL) algorithm. The selected features, which were standardized using StandardScaler to achieve zero mean and unit variance, were then classified using a meta-learning classifier to enhance precision and efficiency. In addition, a digital twin framework was introduced to simulate and analyze the diagnostic process virtually, enabling real-time feedback and performance monitoring. This virtual replication aids in continuous improvement and supports the deployment of the CAD system in clinical environments. To improve transparency and clinical reliability, explainable artificial intelligence (XAI) methods were incorporated to visualize and interpret model predictions. Compared to state-of-the-art approaches, our system reduced training complexities without compromising high classification precision. Our proposed model attained an accuracy level of 96.25%, demonstrating its consistency and computationally efficient status as a screening tool for detecting skin cancer.