CNN-Based Diagnosis of Skin Cancer from Dermoscopic Images

Year : 2026 | Volume : 15 | Issue : 01 | Page : 37 42
    By

    Ankita Srivastava,

  • Abhishek Gupta,

  • Arohan Chaudhary,

  • Nida Khan,

  1. Assistant Professor, Department of Computer Science & Engineering, Integral University, Lucknow, Uttar Pradesh, India
  2. Student, Department of Computer Science & Engineering, Integral University, Lucknow, Uttar Pradesh, India
  3. Student, Department of Computer Science & Engineering, Integral University, Lucknow, Uttar Pradesh, India
  4. Student, Department of Computer Science & Engineering, Integral University, Lucknow, Uttar Pradesh, India

Abstract

Skin cancer has become one of the diseases widely spread over the globe, with melanoma becoming a severe threat to one’s health. Detection of such diseases at the initial stage saves an individual from drastic damage. Using a Convolutional Neural Network (CNN) for detecting skin cancer through image classification as benign or malignant provides significant support to dermatological practice and reduces dependence solely on subjective visual examination. Dermatologists often face diagnostic challenges because early-stage lesions may closely resemble harmless conditions, and visual interpretation can vary depending on clinical experience. To overcome these diagnostic variations and improve reliability, this research proposes a robust computer-aided detection (CAD) framework based on a multi-layered CNN architecture. The system automatically extracts relevant features, such as asymmetry, border irregularity, color variation, and texture patterns from dermoscopic images without the need for manual feature engineering. By learning hierarchical representations of lesion characteristics, the model enhances diagnostic accuracy and assists clinicians in early screening. This approach aims to function as a supportive decision-making tool, enabling faster evaluation, reducing human error, and facilitating timely identification of potentially malignant lesions, ultimately contributing to improved patient outcomes and more efficient dermatological care.

Keywords: Clinical, CNN, deep learning, melanoma, skin cancer

[This article belongs to Research and Reviews: Journal of Oncology and Hematology ]

How to cite this article:
Ankita Srivastava, Abhishek Gupta, Arohan Chaudhary, Nida Khan. CNN-Based Diagnosis of Skin Cancer from Dermoscopic Images. Research and Reviews: Journal of Oncology and Hematology. 2026; 15(01):37-42.
How to cite this URL:
Ankita Srivastava, Abhishek Gupta, Arohan Chaudhary, Nida Khan. CNN-Based Diagnosis of Skin Cancer from Dermoscopic Images. Research and Reviews: Journal of Oncology and Hematology. 2026; 15(01):37-42. Available from: https://journals.stmjournals.com/rrjooh/article=2026/view=240158


References

  1. Brinker TJ, Hekler A, Enk AH, Berking C, Haferkamp S, Hauschild A, et al. Skin cancer classification using convolutional neural networks: Systematic performance comparison. Eur J Cancer. 2019;119:30–37.
  2. Celebi ME, Wen Q, Iyatomi H, Shimizu K, Zhou H, Schaefer G. Lesion border detection in dermoscopy images. Comput Med Imaging Graph. 2008;33(2):148–153.
  3. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–118.
  4. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. p. 770–778.
  5. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. p. 4700–4708.
  6. Setiawan A, Wibowo A, Widiastuti W, et al. Skin lesion classification using convolutional neural network with color enhancement preprocessing. IEEE Access. 2020;8:129340–129349.
  7. Zhang Y, Li X, Yang H, et al. Attention-based convolutional neural network for skin lesion classification. IEEE Trans Med Imaging. 2021;40(9):2346–2356.
  8. Matsunaga K, Hamada A, Minagawa A, Koga H. Image classification of melanomas and nevi using a convolutional neural network. arXiv [Preprint]. 2017;arXiv:1710.05006.
  9. Xie F, Yang J, Liu J, Jiang Z, Zheng Y, Wang Y. Skin lesion segmentation using deep learning. Neurocomputing. 2020;380:259–269.
  10. Goyal M, Knackstedt T, Yan S, Hassanpour S. Mobile-based skin lesion diagnosis using lightweight deep learning models. Comput Biol Med. 2023;140:105113.
Regular Issue Subscription Review Article
Volume 15
Issue 01
Received 07/02/2026
Accepted 10/02/2026
Published 05/04/2026
Publication Time 57 Days
7

Login


My IP

PlumX Metrics