International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Skintel: A DenseNet121-Based Deep Learning Framework for Skin Lesion Classification using HAM10000 |
|---|---|
| ABSTRACT | Skin lesion classification is the first and necessary step toward early detection of dermatological conditions, especially melanoma, responsible for the vast majority of skin cancer-related deaths in the world. Traditional manual diagnosis is often subjective, time-consuming, and relies on expert dermatologists. This work proposes a deep learning-based approach to automatically classify skin lesions using the DenseNet121 architecture trained and fine-tuned on the HAM10000 dataset. The model exploits dense connectivity between layers to promote feature reuse and also facilitate gradient propagation, which leads to better learning. Besides, the image preprocessing techniques of resizing, normalization, and augmentation were performed in order to enhance robustness. The proposed model recorded a classification accuracy of 85.49%. The comparative performance analysis against state-of-the-art models, including hybrid fusion models using metaheuristics, autoencoder-based quantum feature extraction frameworks and clinical decision support systems, proves the superiority of DenseNet121 for multi-class skin lesion recognition on the HAM10000 dataset.This paper emphasizes the effectiveness and potential that deep transfer learning architectures could offer in the development process of dermatological diagnostic support systems and telemedicine solutions. |
| AUTHOR | PROF. NEETHA DAS, N LAASYA, KEERTHANA A, KHUSHI JANGIR, MODONA MARIA KROME Department of Computer Science and Engineering, Bangalore Institute of Technology, Bangalore, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312116 |
| pdf/116_Skintel A DenseNet121-Based Deep Learning Framework for Skin Lesion Classification using HAM10000.pdf | |
| KEYWORDS | |
| References | [1] M. Obayya, R. Nawaz, R. Ullah, and J. Xu, “Hybrid Metaheuristics with Deep Learning-Based Fusion Model for Biomedical Image Analysis,” IEEE Access, vol. 11, pp. 117149–117162, 2023. [2] F. Farhatullah, M. N. Khan, and A. Alam, “Classification of Skin Lesion with Feature Extraction Using QChPs-AE-LSTM Model,” IEEE Access, vol. 12, pp. 193924–193933, 2024. [3] S. M. Dash, P. Kumar, and A. Dandapat, “Deep Convolutional Networks for Skin Lesion Classification on Dermoscopic Images,” Biomedical Signal Processing and Control, vol. 73, p. 103435, 2022. [4] A. Khan, M. Alam, and Y. Lee, “Automated Diagnosis of Skin Diseases Using Convolutional Neural Networks,” International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), vol. 3, no. 3, pp. 768–772, Dec. 2023. [5] M. Obayya, I. Domingues, and R. Ullah, “Hybrid Salp Swarm Algorithm-Optimized Deep Learning for Biomedical Image Classification,” IEEE Access, vol. 11, pp. 117149–117169, 2023. [6] R. Mittal, M. Gupta, and R. Goel, “A Comparative Study of CNN Architectures for Skin Lesion Classification,” International Journal of Engineering and Advanced Technology (IJEAT), vol. 12, no. 3, pp. 56–63, 2023. [7] H. Zhang, S. Niu, X. Wang, and C. Li, “Quantum Autoencoder-Based Dermatological Image Analysis Using Chebyshev Polynomial Approximation,” IEEE Access, vol. 12, pp. 178221–178235, 2024. [8] A. Yadav, P. Singh, and R. Mehta, “Efficient Deep Spiking Neural Network for Multi-Class Skin Lesion Detection,” IEEE Access, vol. 11, pp. 176020–176032, 2023. [9] S. Sharma, P. Kumar, and T. Das, “Transfer Learning-Based Multiclass Classification for Dermatoscopic Image Analysis,” IEEE Access, vol. 11, pp. 179255–179268, 2023. [10] Z. Ji, X. Wang, C. Liu, Z. Wang, N. Yuan, and I. Ganchev, “EFAM-Net: A Multi-Class Skin Lesion Classification Model Utilizing Enhanced Feature Fusion and Attention Mechanisms,” IEEE Access, vol. 12, pp. 193924–193936, 2024. [11] V. S. S. B. T. Sathvika, N. Anmisha, V. Thanmayi, M. Suchetha, D. E. Dhas, S. Sehastrajit, and S. N. Aakur, “Classification of Skin Lesions Based on AlexNet CNN and SVM Model With Bi-Sectional Texture Features,” IEEE Access, vol. 12, pp. 190142–190155, 2024. [12] G. C. Garcia, M. N. Khan, A. Alam, J. Obregon, T. Abuhmed, and E.-N. Huh, “FiSC: A Novel Approach for Fitzpatrick Scale-Based Skin Analyzer’s Image Classification,” IEEE Access, vol. 12, pp. 192451–192463, 2024. |
