DermAI: A Triple-CNN Ensemble Learning Approach for Early Detection of Skin Tone Abnormalities in Clinical Settings

Early detection of skin tone abnormalities is crucial for managing conditions like melanoma and other dermatological disorders. DermAI, a Triple-CNN ensemble, combines the strengths of ResNet for capturing complex visual patterns, DenseNet for extracting fine-grained features, and EfficientNet for ensuring computational efficiency without compromising accuracy. This ensemble model uses a novel weighted voting mechanism that dynamically adjusts each model's contribution based on input characteristics and confidence levels, enhancing the system”s adaptability to diverse skin types. In comparison with traditional methods such as Bagging, Boosting, and Stacking, DermAI demonstrates superior performance, achieving an accuracy of 93.5%, precision of 94.2%, recall of 92.8%, and an F1-score of 93.5%. These results confirm its potential as an effective and reliable tool for early diagnosis in clinical dermatology, offering improved diagnostic accuracy and faster decision-making in real-world healthcare settings.