https://doi.org/10.65770/XAMD8420
ABSTRACT
Skin cancer is a common and potentially fatal disease caused by the unnatural growth of skin cells. It can spread to other parts of the body, and early diagnosis significantly affects survival. However, the ability to detect skin cancer early is very difficult. Therefore, in this project, a medical image binary classification system based on deep learning is designed and implemented for distinguishing benign and malignant lesions. An innovative Residual Inception Attention Model is adopted, which uses a multi-branch residual structure and combines depthwise separable convolution, spatially separable convolution, and custom attention mechanism. Interpretability analysis was performed through Grad-CAM heatmap visualization. The training results show that the model has good training results on the test set, which proves that the model has high reliability in medical image diagnosis, can effectively distinguish benign and malignant lesions, and provides strong support for clinical diagnosis.
References
- [1] Mahbod, G. Schaefer, C. Wang, G. Dorffner, R. Ecker, and I. Ellinger, ‘Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification’, Comput. Methods Programs Biomed., vol. 193, p. 105475, Sept. 2020, doi: 10.1016/j.cmpb.2020.105475.
- [2] K. Koh, ‘Melanoma Screening: Focusing the Public Health Journey’, Arch. Dermatol., vol. 143, no. 1, pp. 101–103, Jan. 2007, doi: 10.1001/archderm.143.1.101.
- [3] McKnight, J. Shah, and R. Hargest, ‘Physiology of the skin’, Surg. Oxf., vol. 40, no. 1, pp. 8–12, Jan. 2022, doi: 10.1016/j.mpsur.2021.11.005.
- [4] Maqbool, S. Pumrin, and N. Panitantum, ‘Diagnosis of Skin Cancer via Transfer Learning with Combined Channel attention and Spatial Attention’, in 2024 28th International Computer Science and Engineering Conference (ICSEC), Nov. 2024, pp. 1–5. doi: 10.1109/ICSEC62781.2024.10770743.
- [5] Majumder and M. A. Ullah, ‘Feature extraction from dermoscopy images for melanoma diagnosis’, SN Appl. Sci., vol. 1, no. 7, p. 753, June 2019, doi: 10.1007/s42452-019-0786-8.
- [6] M. Thwin and H.-S. Park, ‘Advancing Skin Cancer Detection: Integrating Attention-Driven Transfer Learning and Autoencoder-Decoder Fusion’, in 2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Feb. 2025, pp. 0638–0643. doi: 10.1109/ICAIIC64266.2025.10920870.
- [7] Islam, J. T. Raya, M. T. Maisha, and D. Md. Farid, ‘Feature Fusion with Attention Mechanism for Skin Cancer Classification’, in 2023 6th International Conference on Electrical Information and Communication Technology (EICT), Dec. 2023, pp. 1–6. doi: 10.1109/EICT61409.2023.10427842.
- [8] K. Mallick, A. Sharma, N. Padhy, B. Sahoo, and J. Gochhayat, ‘Integrating Attention Mechanism for Accurate Skin Cancer Diagnosis’, in 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC), Feb. 2024, pp. 785–790. doi: 10.1109/ESIC60604.2024.10481565.
- [9] Arora, A. K. Dubey, Z. A. Jaffery, and A. Rocha, ‘Bag of feature and support vector machine based early diagnosis of skin cancer’, Neural Comput. Appl., vol. 34, no. 11, pp. 8385–8392, June 2022, doi: 10.1007/s00521-020-05212-y.
- S. R. Kiran, Y. S. Madhuri, P. Venkata Bala Annapurna, A. Lakshmanarao, and B. S. N. Murthy, ‘A Novel Approach to Skin Cancer Detection using CNN, ResNet, and Hybrid Feature Extraction’, in 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Oct. 2024, pp. 217–222. doi: 10.1109/ICSSAS64001.2024.10760465.
- Xu, L. Jin, T. Shen, and F. Huang, ‘Skin Cancer Diagnosis based on Improved Multiattention Convolutional Neural Network’, in 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Mar. 2021, pp. 761–765. doi:10.1109/IAEAC50856.2021.939072
Download all article in PDF
