Attention-enhanced hybrid deep learning for skin cancer diagnosis with hierarchical feature fusion
DOI:
https://doi.org/10.35335/mandiri.v15i1.552Keywords:
Deep Learning, Hierarchical Feature Fusion, Hybrid Attention Mechanism, Image Classification, Skin Cancer DiagnosisAbstract
Skin cancer is one of the most prevalent cancers worldwide, making early and accurate diagnosis essential for improving patient outcomes and reducing mortality. However, automated skin lesion classification remains challenging due to high inter-class similarity, class imbalance, and variations in lesion appearance. This study proposes an attention-enhanced hybrid deep learning for skin cancer diagnosis with hierarchical feature fusion. The proposed framework integrates channel and spatial attention with hierarchical feature fusion to enhance discriminative feature learning and improve classification robustness. Experiments were conducted on the PAD-UFES-20 dataset using image preprocessing and data augmentation. The proposed model achieved approximately 98% training accuracy, 95% validation accuracy, and a validation loss below 0.5, outperforming DRMv2Net, DenseNet201, ResNet101, and MobileNetV2 while demonstrating faster convergence and stronger generalization. These findings demonstrate the potential of hybrid attention and hierarchical feature fusion to improve the reliability and robustness of artificial intelligence-based diagnostic systems in dermatology, supporting more effective clinical decision-making and early skin cancer screening.
References
Alghamdi, H. M. (2026). Enhanced genetic algorithm-optimized deep learning features for lung cancer classification. Alexandria Engineering Journal, 134, 341–357. https://doi.org/10.1016/j.aej.2025.12.023
Aljohani, B. H. S., Yafooz, W. M. S., & Alsaeedi, A. (2026). AI-driven dermatological diagnostics: A systematic review of machine and deep learning methods for skin disease classification. Array, 30, 100797. https://doi.org/10.1016/j.array.2026.100797
Alshareef, I. Y., Rahman, A. A.-H. A., Shaameri, A. Z., Khan, N., Rusli, M. S., Hassan, M. K., Manzak, A., & Marsono, M. N. (2026). ReLU-DCT and LASP: Real-valued frequency-domain activations and adaptive pooling for DCT-Based CNNs. Knowledge-Based Systems, 343, 116018. https://doi.org/10.1016/j.knosys.2026.116018
Bhargavi, M., & Balakrishna, S. (2026). ENDNet: A lightweight attention-enhanced feature fusion framework for multi-class skin cancer classification. Alexandria Engineering Journal, 144, 92–116. https://doi.org/10.1016/j.aej.2026.04.020
Bindhu, A., & Thanammal, K. K. (2023). Segmentation of skin cancer using Fuzzy U-network via deep learning. Measurement: Sensors, 26, 100677. https://doi.org/10.1016/j.measen.2023.100677
Cataldo, A., Cino, L., Distante, C., Maietta, G., Masciullo, A., Mazzeo, P. L., & Schiavoni, R. (2024). Integrating microwave reflectometry and deep learning imaging for in-vivo skin cancer diagnostics. Measurement, 235, 114911. https://doi.org/10.1016/j.measurement.2024.114911
Chang, S., Yang, K., Wang, Y., Sun, Y., Qi, C., Fan, W., Zhang, Y., Liu, S., Gao, W., Meng, J., & Xue, L. (2025). A multi-stage deep learning network toward multi-classification of polyps in colorectal images. Alexandria Engineering Journal, 119, 189–200. https://doi.org/10.1016/j.aej.2025.01.110
Dash, A., Sethy, P. K., & Behera, S. K. (2023). Maize disease identification based on optimized support vector machine using deep feature of DenseNet201. Journal of Agriculture and Food Research, 14, 100824. https://doi.org/10.1016/j.jafr.2023.100824
Dube, D., & Kumar, A. (2026). MTA-HXCN: Modified Triplet Attention Fused Hybrid Learning Enabled Explainable Convolutional Neural Network for brain tumor detection. Neurocomputing, 694, 133886. https://doi.org/10.1016/j.neucom.2026.133886
Ghosh, S., Dhar, S., Yoddha, R., Kumar, S., Thakur, A. K., & Jana, N. D. (2024). Melanoma Skin Cancer Detection Using Ensemble of Machine Learning Models Considering Deep Feature Embeddings. Procedia Computer Science, 235, 3007–3015. https://doi.org/10.1016/j.procs.2024.04.284
Govindu, S., Devi, O. R., Sitharam, M., Koreddi, V., Kumar, M. K., & Sunitha, M. (2026). Cutting-edge CNN-based skin cancer detection with batch normalization and advanced imbalance learning for superior medical image classification. Biomedical Signal Processing and Control, 113, 108929. https://doi.org/10.1016/j.bspc.2025.108929
Hosseini, A., Guay, M., & Li, X. (2025). On ReLU neural networks as piecewise linear surrogate models. Computers & Chemical Engineering, 201, 109208. https://doi.org/10.1016/j.compchemeng.2025.109208
Liu, R., Chen, Z., Yao, G., & Zhang, P. (2026). Exploring the challenge and value of deep learning in automated skin disease diagnosis. Biomedical Signal Processing and Control, 117, 109589. https://doi.org/10.1016/j.bspc.2026.109589
Mahmud, T., Uddin, M. S., Hossain, M. A., Kabir, M. R., Bonik, E. M., & Shimul, M. M. H. (2026). HALI-net: An explainable hybrid deep learning model with attention and texture fusion for lung cancer detection in CT images. Intelligence-Based Medicine, 15, 100419. https://doi.org/10.1016/j.ibmed.2026.100419
Nagdiya, A., Kapoor, V., & Tokekar, V. (2025). Hybrid Deep Learning Architecture Combining Attention Mechanisms and Recurrent Neural Networks for Enhanced Time Series Analysis. Procedia Computer Science, 258, 3315–3323. https://doi.org/10.1016/j.procs.2025.04.589
Nguyen, M. N. (2025). A scoping review of deep learning approaches for lung cancer detection using chest radiographs and computed tomography scans. Biomedical Engineering Advances, 9, 100138. https://doi.org/10.1016/j.bea.2024.100138
Pacheco, A. G. C., Lima, G. R., Salomão, A. S., Krohling, B., Biral, I. P., De Angelo, G. G., Alves Jr, F. C. R., Esgario, J. G. M., Simora, A. C., Castro, P. B. C., Rodrigues, F. B., Frasson, P. H. L., Krohling, R. A., Knidel, H., Santos, M. C. S., Do Espírito Santo, R. B., Macedo, T. L. S. G., Canuto, T. R. P., & De Barros, L. F. S. (2020). PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data in Brief, 32, 106221. https://doi.org/10.1016/j.dib.2020.106221
Rajesh, M., Senapati, B., Das, R., & Martha, S. (2023). Identifying Colorectal Tumor For Single Cell RNA Sequence Using Rectified Linear Unit With Stochastic Gradient Descent. Procedia Computer Science, 218, 189–198. https://doi.org/10.1016/j.procs.2023.01.001
Revathi, M. (2026). Hybrid deep learning with cross-attention fusion for autism spectrum disorder classification from facial images.
Rezaei, S., Hamedani, Z., Ahmadi, K., Ghannadikhosh, P., Motamedi, A., Athari, M., Yousefi, H., Rajabi, A. H., Abbasi, A., & Arabi, H. (2025). Role of machine learning in molecular pathology for breast cancer: A review on gene expression profiling and RNA sequencing application. Critical Reviews in Oncology/Hematology, 213, 104780. https://doi.org/10.1016/j.critrevonc.2025.104780
Rocha, M. B., Pratavieira, S., Vieira, R. S., Geller, J. D., Stein, A. L. M., De Oliveira, F. S. S., Canuto, T. R. P., De Paula Vieira, L., Rossoni, R., Santos, M. C. S., Frasson, P. H. L., & Krohling, R. A. (2025). Fluorescence images of skin lesions and automated diagnosis using convolutional neural networks. Photodiagnosis and Photodynamic Therapy, 52, 104462. https://doi.org/10.1016/j.pdpdt.2024.104462
Thanga Purni, J. S., & Vedhapriyavadhana, R. (2024). EOSA-Net: A deep learning framework for enhanced multi-class skin cancer classification using optimized convolutional neural networks. Journal of King Saud University - Computer and Information Sciences, 36(3), 102007. https://doi.org/10.1016/j.jksuci.2024.102007
Wen, D., Khan, S. M., Ji Xu, A., Ibrahim, H., Smith, L., Caballero, J., Zepeda, L., De Blas Perez, C., Denniston, A. K., Liu, X., & Matin, R. N. (2022). Characteristics of publicly available skin cancer image datasets: A systematic review. The Lancet Digital Health, 4(1), e64–e74. https://doi.org/10.1016/S2589-7500(21)00252-1
Zhou, Z., Xie, X., Qiu, Y., Lin, R., Zheng, W.-S., & Wang, R. (2026). Class incremental learning with task-specific batch normalization and out-of-distribution detection. Neurocomputing, 680, 133321. https://doi.org/10.1016/j.neucom.2026.133321
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ahmad Sanmorino, Rendra Gustriansyah, Shinta Puspasari
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
