Open Access

An Optimized Convolutional Neural Network Architecture for Accurate Skin Lesion Analysis and Intelligent Skin Cancer Prediction System

PDF

Dr. Lukas Weber ¹ , Dr. Anna Schmidt ¹ ,

⁴ Institute of Industrial Engineering Technical University of Munich, Germany

⁴ Faculty of Management University of Heidelberg, Germany

Abstract

Skin cancer is among the most rapidly increasing forms of malignancy worldwide, requiring early and accurate detection for effective treatment and survival improvement. Traditional diagnostic approaches rely heavily on dermatological expertise and visual examination, which are often subjective and time-consuming. Recent advancements in deep learning, particularly convolutional neural networks (CNNs), have demonstrated significant potential in automating skin lesion classification with high accuracy and consistency. This study proposes an optimized CNN-based architecture designed for enhanced feature extraction, improved generalization, and robust classification of dermoscopic skin lesion images.

The proposed system integrates advanced convolutional blocks inspired by modern lightweight architectures and deep feature fusion strategies to improve performance across heterogeneous datasets. The methodology emphasizes preprocessing, data augmentation, optimized feature learning, and classification refinement. The study also evaluates the system in the context of established dermatological research and machine learning models, highlighting its superiority in diagnostic accuracy and computational efficiency.

Existing literature confirms the effectiveness of deep learning-based models in skin cancer detection; however, challenges such as overfitting, class imbalance, and limited interpretability remain critical barriers. By addressing these issues, the proposed model contributes to improved clinical decision support systems. The findings suggest that optimized CNN architectures can significantly enhance early detection capabilities and reduce diagnostic uncertainty in dermatology.

Keywords

Skin cancer detection, convolutional neural network, deep learning, dermoscopic image analysis

References

A. Hawrot, M. Alam, and D. Ratner, “Squamous cell carcinoma,” Curr. Probl. Dermatol., vol. 15, no. 3, pp. 91–133, 2003.

A. Jemal, F. Bray, M. M. Center, J. Ferlay, E. Ward, and D. Forman, “Global cancer statistics,” CA. Cancer J. Clin., vol. 61, no. 2, pp. 69–90, 2011.

B. Pallavi, “A hybrid diagnosis system for malignant melanoma detection in dermoscopic images,” in 2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), IEEE, 2019, pp. 1471–1476.

E. Micu, “Solar radiation and melanoma epidemiology in Norway: Epidemiological data argue against a negative impact of sun exposure for certain types of melanoma,” 2014.

F. Chollet, “Xception:Deep learning with depthwise separable convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1251–1258.

F. Xie, H. Fan, Y. Li, Z. Jiang, R. Meng, and A. Bovik, “Melanoma classification on dermoscopy images using a neural network ensemble model,” IEEE Trans. Med. Imaging, vol. 36, no. 3, pp. 849–858, 2016.

H. M. Gloster Jr and D. G. Brodland, “The epidemiology of skin cancer,” Dermatologic Surg., vol. 22, no. 3, pp. 217–226, 1996.

I. ul haq, J. Amin, M. Sharif, and M. Almas Anjum, “Skin lesion detection using recent machine learning approaches,” in Prognostic Models in Healthcare: AI and Statistical Approaches, Springer, 2022, pp. 193–211.

J. G. Nutt, C. D. Marsden, and P. D. Thompson, “Human walking and higher‐level gait disorders, particularly in the elderly,” Neurology, vol. 43, no. 2, p. 268, 1993.

N. C. Lynn and N. War, “Segmentation of skin lesion towards melanoma skin cancer classification,” Int. J. Comput. Sci. Netw., vol. 8, no. 3, 2019.

R. Javed, M. S. M. Rahim, T. Saba, and A. Rehman, “A comparative study of features selection for skin lesion detection from dermoscopic images,” Netw. Model. Anal. Heal. Informatics Bioinforma., vol. 9, no. 1, p. 4, 2020.

R. M. MacKie, Skin cancer. CRC Press, 1996.

S. C. Taylor, “Skin of color: biology, structure, function, and implications for dermatologic disease,” J. Am. Acad. Dermatol., vol. 46, no. 2, pp. S41–S62, 2002.

W. He, N. Liao, W. Liu, J. Gong, C. Li, and B. Guo, “An Ultra-High Speed Gesture RecognitionAlgorithm Based on MobileNetV2,” in Neural Computing for Advanced Applications: Second International Conference, NCAA 2021, Guangzhou, China, August 27-30, 2021, Proceedings 2, Springer, 2021, pp. 590–602.

X. Zhang, X. Zhou, M. Lin, and J. Sun, “Shufflenet: An extremely efficient convolutional neural network for mobile devices,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 6848–6856.

Most read articles by the same author(s)

<< < 6 7 8 9 10 11 12 > >>

International Journal of Modern Computer Science and IT Innovations

An Optimized Convolutional Neural Network Architecture for Accurate Skin Lesion Analysis and Intelligent Skin Cancer Prediction System

Abstract

Keywords

References

Most read articles by the same author(s)

Similar Articles