An Ensemble Deep Learning Framework for Automated Multi Class Skin Lesion Classification Using ConvNeXt-Tiny, EfficientNetV2-S, and MobileNetV3
DOI:
https://doi.org/10.21015/vtse.v14i1.2311Abstract
Skin cancer is one of the fastest rising malignancies in the world, where early and accurate diagnosis plays a decisive role in the survival of patients. Even though the performance of convolutional neural networks (CNNs) in dermoscopic image analysis has been impressive, three main issues that hinder their application in the clinical setting remain: severe imbalance in classes, inter-class visual similarity, overfitting, and lack of interpretability. In this paper, a three-stream ensemble deep learning model that combines ConvNeXt-Tiny, EfficientNetV2-S, and MobileNetV3-Large has been proposed to classify automated multiclass skin lesion on the HAM10000 dataset. Balanced stratified sampling strategy (BalancedDataGen) is used in order to take care of class imbalance without synthetic oversampling in order to have equal contribution of classes in the training. More successful feature diversity and generalization are further improved with the help of adversarial Albumentations-based data augmentation. Each backbone model is fine-tuned separately based on label smoothing, dropout regularization, early stopping, and adaptive learning rate scheduling. The probability-level ensemble averaging is done to give final predictions. The post-hoc explainability of the results is offered to improve clinical interpretability, and ensemble saliency maps created through SmoothGrad allow seeing lesion-specific discriminatory areas consistently. Experimental findings indicate that the proposed ensemble is more accurate, robust and minority-class recognizing than individual models, and it has a test accuracy of 89.72%. The framework provides a good, interpretable and computationally efficient solution to automated dermoscopic diagnosis to fit low-resource clinical settings.
References
A. H. Roky et al., “Overview of skin cancer types and prevalence rates across continents,” Cancer Pathogenesis and Therapy, vol. 3, no. 2, pp. 89–100, 2025.
B. Ahmed, M. I. Qadir, and S. Ghafoor, “Malignant melanoma: Skin cancer—diagnosis, prevention, and treatment,” Critical Reviews in Eukaryotic Gene Expression, vol. 30, no. 4, 2020.
S. Levit, J. Shoykhet, and E. Levit, “Comprehensive insights into basal cell carcinoma: Causes, presentation, prevention, and modern therapeutic approaches,” Cancer Medicine, vol. 14, no. 24, Art. no. e71448, 2025.
G. P. Pfeifer, “Mechanisms of UV-induced mutations and skin cancer,” Genome Instability & Disease, vol. 1, no. 3, pp. 99–113, 2020.
M. Abubakar, “Overview of skin cancer and risk factors,” International Journal of General Practice Nursing, vol. 2, no. 3, pp. 42–56, 2024.
L. Rey-Barroso, S. Peña-Gutiérrez, C. Yáñez, F. J. Burgos-Fernández, M. Vilaseca, and S. Royo, “Optical technologies for the improvement of skin cancer diagnosis: A review,” Sensors, vol. 21, no. 1, Art. no. 252, 2021.
N. Melarkode, K. Srinivasan, S. M. Qaisar, and P. Plawiak, “AI-powered diagnosis of skin cancer: A contemporary review, open challenges and future research directions,” Cancers, vol. 15, no. 4, Art. no. 1183, 2023.
N. Razmjooy et al., “Computer-aided diagnosis of skin cancer: A review,” Current Medical Imaging Reviews, vol. 16, no. 7, pp. 781–793, 2020.
S. Haque, F. Ahmad, V. Singh, D. M. Mathkor, and A. Babegi, “Skin cancer detection using deep learning approaches,” Cancer Biotherapy & Radiopharmaceuticals, vol. 40, no. 5, pp. 301–312, 2025.
M. Faris, R. Qayyum, C. Pepe, M. F. Ali, and S. M. Zanoli, “Multi-class skin disease detection using deep learning hybrid method,” in Proc. 26th Int. Carpathian Control Conf. (ICCC), 2025, pp. 1–5.
S. Adamu et al., “The future of skin cancer diagnosis: A comprehensive systematic literature review of machine learning and deep learning models,” Cogent Engineering, vol. 11, no. 1, Art. no. 2395425, 2024.
S. J. Kumar, G. P. Kanna, D. P. Raja, and Y. Kumar, “A comprehensive study on deep learning models for the detection of ovarian cancer and glomerular kidney disease using histopathological images,” Archives of Computational Methods in Engineering, vol. 32, no. 1, pp. 35–61, 2025.
C. N. Kanani and P. U. Jadeja, “Skin disease diagnosis: A comprehensive survey of models, datasets, and clinical applications,” Cureus, vol. 2, no. 1, 2025.
B. Kamaraj et al., “Explainable AI for skin cancer detection using convolutional neural networks with SE and Grad-CAM,” Journal of Investigative Dermatology, vol. 145, no. 8, p. S21, 2025.
H. L. Gururaj, N. Manju, A. Nagarjun, V. M. Aradhya, and F. Flammini, “DeepSkin: A deep learning approach for skin cancer classification,” IEEE Access, vol. 11, pp. 50205–50214, 2023.
M. Benaly, B. Kouach, I. Alihamidi, and L. Hlou, “Explainable AI for skin cancer classification: Unlocking insights with Grad-CAM and Grad-CAM++,” in Proc. Int. Conf. Circuit, Systems and Communication (ICCSC), 2025, pp. 1–4.
T. Öznacar and N. Varol Kayapunar, “Advanced skin cancer prediction with medical image data using MobileNetV2 deep learning and optimized techniques,” Scientific Reports, vol. 15, no. 1, Art. no. 28962, 2025.
E. Zhao, “Deep learning models-based skin cancer classification and early detection,” in ITM Web of Conferences, vol. 78, Art. no. 02007, 2025.
A. V. Dahat, U. T. Kute, T. R. Mahore, A. A. Joshi, S. Dhanraj, and U. D. Pande, “Detection of multi-class skin cancer using stochastic gradient descent augmentation model and activation mapping,” Journal of Innovative Image Processing, vol. 7, no. 4, pp. 1415–1435, 2025.
J. V. Tembhurne, N. Hebbar, H. Y. Patil, and T. Diwan, “Skin cancer detection using ensemble of machine learning and deep learning techniques,” Multimedia Tools and Applications, vol. 82, no. 18, pp. 27501–27524, 2023.
P. Tschandl, “The HAM10000 dataset: A large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Harvard Dataverse, 2018, doi: 10.7910/DVN/DBW86T.
A. H. Efat, S. M. Hasan, M. P. Uddin, and M. A. Mamun, “A multi-level ensemble approach for skin lesion classification using customized transfer learning with triple attention,” PLOS ONE, vol. 19, no. 10, Art. no. e0309430, 2024.
S. M. Thwin and H.-S. Park, “Skin lesion classification using a deep ensemble model,” Applied Sciences, vol. 14, no. 13, Art. no. 5599, 2024.
A. Halder, A. Dalal, S. Gharami, M. Woźniak, M. F. Ijaz, and P. K. Singh, “A fuzzy rank-based deep ensemble methodology for multi-class skin cancer classification,” Scientific Reports, vol. 15, no. 1, Art. no. 6268, 2025, doi: 10.1038/s41598-025-90423-3.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-By) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
