article · Diagnostics
Skin disease diagnosis across conditions like early skin cancer, benign neoplasms, and leukaemia can be challenging due to physical variations across patient groups. To address this, an ensemble deep learning framework combines three separate convolutional neural networks: EfficientNet-B0, EfficientNet-B2, and ResNet50. Each network processes images independently to extract distinctive visual features before passing them to a fusion mechanism. This mechanism incorporates dense and dropout layers to reduce dimensionality and improve generalisation. The model was trained and evaluated on a Kaggle dataset comprising 27,153 skin disease images spanning ten distinct disorder categories, split into training, validation, and testing sets. During testing, the unified architecture achieved an overall classification accuracy of 99.14 per cent, demonstrating strong diagnostic precision, recall, and F1-score performance across the evaluated classes.
Dermatological conditions vary widely in appearance, making reliable clinical identification difficult. Achieving high multi-class diagnostic accuracy through deep learning can help standardise evaluations and support early identification of severe conditions, including skin cancers. This offers healthcare practitioners clearer decision support when triaging diverse patient groups.
The architecture points towards automated clinical decision-support tools for dermatologists and general healthcare providers diagnosing skin disorders. The technology is at an applied research stage, having been validated on a retrospective dataset of 27,153 images rather than prospective clinical trials. Further real-world clinical evaluation and integration into diagnostic software would be required before deployment in active healthcare settings.
AI-generated from the published abstract. Always read the original work before citing.
<b>Background:</b> Medical diagnosis for skin diseases, including leukemia, early skin cancer, benign neoplasms, and alternative disorders, becomes difficult because of external variations among groups of patients. A research goal is to create a fusion-level deep learning model that improves stability and skin disease classification performance. <b>Methods:</b> The model design merges three convolutional neural networks (CNNs): EfficientNet-B0, EfficientNet-B2, and ResNet50, which operate independently under distinct branches. The neural network model uses its capability to extract detailed features from multiple strong architectures to reach accurate results along with tight classification precision. A fusion mechanism completes its operation by transmitting extracted features to dense and dropout layers for generalization and reduced dimensionality. Analyses for this research utilized the 27,153-image Kaggle Skin Diseases Image Dataset, which distributed testing materials into training (80%), validation (10%), and testing (10%) portions for ten skin disorder classes. <b>Results:</b> Evaluation of the proposed model revealed 99.14% accuracy together with excellent precision, recall, and F1-score metrics. <b>Conclusions:</b> The proposed deep learning approach demonstrates strong potential as a starting point for dermatological diagnosis automation since it shows promise for clinical use in skin disease classification.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/diagnostics15050551
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
