A thorough analysis of developments in machine learning (ML) and deep learning (DL) technologies for skin cancer diagnosis is provided in this research. It investigates how ML and DL could improve the precision and effectiveness of melanoma, basal cell carcinoma, and squamous cell carcinoma detection. By looking at current studies, the study emphasizes the use of neural networks, convolutional neural networks (CNNs), support vector machines (SVM), random forests, and k-nearest neighbors (KNN) in the diagnosis of skin cancer. Key findings show that DL models, including VGG, ResNet, and Inception benefit from huge datasets and sophisticated data augmentation strategies to attain high accuracy, sensitivity, and specificity. The paper also discusses the challenges and limitations associated with these technologies, such as the requirement for extensive annotated datasets. The study concludes with a call for collaboration to overcome current challenges and enhance the practical application of ML and DL in skin cancer detection.

It is essential to early detect skin cancer, especially melanoma since it significantly affects patients' survival. However, an experienced dermatologist still has difficulty distinguishing between a healthy lesion and a tumor; there are fine distinctions between benign and malignant tumors. In this research, we have developed a combined deep learning system, which uses Convolutional Neural Networks (CNNs) in combination with Vision Transformers (ViTs), to develop an automated diagnostic tool for detecting skin cancer based upon skin images. In developing this hybrid model, we utilized EfficientNet-B4 as a local feature extractor and a Vision Transformer as a global feature extractor. To combine these two feature extractors, we employed a special fusion module. This module used concatenation to merge the feature sets from each branch into a single layer and then processed them through a multi-layer perception. We were able to train and test the model using the ISIC 2020 data set, which contains 33,126 skin images, with successively improved training methodologies using a technique called 5-fold cross-validation. On the test set, the proposed hybrid model had an accuracy of 95.4%, a sensitivity of 90.7%, a specificity of 95.1%, and an AUC-ROC of 0.982. The above results show that the hybrid CNN-Transformer design performed better than the previous state-of-the-art EfficientNet-B4 + Attention model (accuracy of 92.1%) and had significant increases in both sensitivity (+1.8%) and specificity (+1.0%). These findings indicate that a hybrid CNN-Transformer design can provide a hopeful means of assisting physicians in diagnosing skin cancer, thus potentially improving physician decision making.

This bibliometric survey examines 200 highly cited publications spanning from 2018 to 2025, retrieved from the Scopus database using search terms targeting federated learning applications in healthcare, medical imaging, and clinical diagnostics. The analysis reveals a rapidly maturing interdisciplinary field at the convergence of distributed machine learning, privacy-preserving technologies, and biomedical informatics. Key findings indicate that federated learning has emerged as a transformative paradigm for collaborative AI model training across healthcare institutions without compromising patient data privacy. The United States, China, the United Kingdom, Germany, and India emerge as the most productive nations, with extensive international collaboration networks reflecting the global need for privacy-compliant healthcare AI. Thematic clustering identifies five major research domains: (1) federated learning architectures and algorithms for healthcare, (2) privacy-preserving techniques including differential privacy, homomorphic encryption, and blockchain integration, (3) medical imaging applications (radiology, pathology, dermatology, ophthalmology), (4) electronic health records and predictive analytics, and (5) wearable devices and remote patient monitoring. Emerging trends include the integration of federated learning with explainable AI for clinical interpretability, the convergence of federated learning with digital twins and the healthcare metaverse, and the development of personalized federated learning frameworks for handling non-IID medical data. This survey provides a comprehensive mapping of the intellectual landscape, identifies persistent challenges including data heterogeneity, communication efficiency, and security vulnerabilities, and proposes future directions for privacy-preserving healthcare AI.