Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 28;15(1):14913.
doi: 10.1038/s41598-025-98205-7.

SkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems

Umesh Kumar Lilhore  1   2 , Yogesh Kumar Sharma  3 , Sarita Simaiya  4   5 , Roobaea Alroobaea  6 , Abdullah M Baqasah  7 , Majed Alsafyani  6 , Afnan Alhazmi  7
Affiliations

SkinEHDLF a hybrid deep learning approach for accurate skin cancer classification in complex systems

Umesh Kumar Lilhore et al. Sci Rep. .

Abstract

Skin cancer represents a significant global public health issue, and prompt and precise detection is essential for effective treatment. This study introduces SkinEHDLF, an innovative deep-learning model that enhances skin cancer classification. SkinEHDLF utilizes the advantages of several advanced models, i.e., ConvNeXt, EfficientNetV2, and Swin Transformer, while integrating an adaptive attention-based feature fusion mechanism to enhance the synthesis of acquired features. This hybrid methodology combines ConvNeXt's proficient feature extraction capabilities, EfficientNetV2's scalability, and Swin Transformer's long-range attention mechanisms, resulting in a highly accurate and dependable model. The adaptive attention mechanism dynamically optimizes feature fusion, enabling the model to focus on the most relevant information, enhancing accuracy and reducing false positives. We trained and evaluated SkinEHDLF using the ISIC 2024 dataset, which comprises 401,059 skin lesion images extracted from 3D total-body photography. The dataset is divided into three categories: melanoma, benign lesions, and noncancerous skin anomalies. The findings indicate the superiority of SkinEHDLF compared to current models. In binary skin cancer classification, SkinEHDLF surpassed baseline models, achieving an AUROC of 99.8% and an accuracy of 98.76%. The model attained 98.6% accuracy, 97.9% precision, 97.3% recall, and 99.7% AUROC across all lesion categories in multi-class classification. SkinEHDLF demonstrates a 7.9% enhancement in accuracy and a 28% decrease in false positives, outperforming leading models including ResNet-50, EfficientNet-B3, ViT-B16, and hybrid methodologies such as ResNet-50 + EfficientNet and ViT + CNN, thereby positioning itself as a more precise and reliable solution for automated skin cancer detection. These findings underscore SkinEHDLF's capacity to transform dermatological diagnostics by providing a scalable and accurate method for classifying skin cancer.

Keywords: ConvNeXt; Deep learning; EfficientNetV2; Hybrid model; Skin Cancer detection; Swin transformer.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Consent for publication: All authors have reviewed and approved the final manuscript for publication.

Figures

Fig. 1
Fig. 1
Overview of image category in the ISIC-2024 dataset.
Fig. 2
Fig. 2
Architecture of the proposed SkinEHDLF hybrid model.
Fig. 3
Fig. 3
ConvNeXt Feature Extraction layer architecture in the proposed hybrid model.
Fig. 4
Fig. 4
Architecture of EfficientNetV2 Layer in Proposed Hybrid Model.
Fig. 5
Fig. 5
Architecture of Swin Transformer Layer.
Fig. 6
Fig. 6
Performance Comparison of Different Lesion Types Using Proposed Model.
Fig. 7
Fig. 7
Confusion Matrix for proposed and existing models for Binary Skin-cancer classification on Test Dataset.
Fig. 8
Fig. 8
Comparative analysis of Binary vs. multi-class Classification results for Proposed Vs. Existing Models.
Fig. 9
Fig. 9
Comparative analysis of Cross-Dataset Evaluation for Binary classification.
Fig. 10
Fig. 10
K-Fold Cross-Validation Results for SkinEHDLF (Proposed Model).
Fig. 11
Fig. 11
Data Pre-processing Impact in Skin Cancer Analysis.
Fig. 12
Fig. 12
Accuracy Vs. Loss Curve for (Training, Testing, and Validation for Proposed Hybrid SkinEHDLF Model.
Fig. 13
Fig. 13
AUC-ROC curve analysis for the Proposed Model.
Fig. 14
Fig. 14
Comparative Results of SkinEHDLF with Existing Models.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Ozdemir, B. & Pacal, I. A robust deep learning framework for multiclass skin cancer classification. Sci. Rep.15 (1), 4938 (2025). - PMC - PubMed
    1. Kumar Lilhore, Umesh, S. et al. Anchit Bijalwan, and Roobaea Alroobaea. A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization. Sci. Rep.14 (1), 4299 (2024). - PMC - PubMed
    1. Mavaddati, S. Skin cancer classification based on a hybrid deep model and long short-term memory. Biomed. Signal Process. Control. 100, 107109 (2025).
    1. Subhashini, G. & Chandrasekar, A. Hybrid deep learning technique for optimal segmentation and classification of multi-class skin cancer. Imaging Sci. J.72 (8), 1043–1064 (2024).
    1. Pacal, I., Ozdemir, B., Zeynalov, J., Gasimov, H. & Pacal, N. A novel CNN-ViT-based deep learning model for early skin cancer diagnosis. Biomed. Signal Process. Control. 104, 107627 (2025).

LinkOut - more resources