Interpretable Skin Cancer Detection via Optimized CNN Models for Smart Healthcare Solutions


Year : 2025 | Volume : 12 | Issue : 01 | Page : 13-17
    By

    Gajendra Kumar Deshmukh,

  • Satyam Jadhav,

  • Aditya Kadam,

  • Sumit Aware,

  • Twinkle Shukla,

  1. Student, Department of Information Technology, P.G. Moze College of Engineering, Pune, Maharashtra, India
  2. Student, Department of Information Technology, P.G. Moze College of Engineering, Pune, Maharashtra, India
  3. Student, Department of Information Technology, P.G. Moze College of Engineering, Pune, Maharashtra, India
  4. Student, Department of Information Technology, P.G. Moze College of Engineering, Pune, Maharashtra, India
  5. Professor, Department of Information Technology, P.G. Moze College of Engineering, Pune, Maharashtra, India

Abstract

Skin cancer is a common and potentially life-threatening condition, highlighting the importance of reliable and efficient diagnostic techniques. Recently, convolutional neural networks (CNNs) have demonstrated significant potential in automating the classification of skin cancer using thermoscopic images. Despite these advancements, the lack of interpretability in these models poses a barrier to their widespread use in clinical settings. In this study, we propose an interpretable CNN architecture optimized for skin cancer classification within a smart healthcare system. Our proposed model leverages a combination of traditional CNN layers with attention mechanisms and feature visualization techniques to enhance interpretability. Through extensive experimentation and hyperparameter tuning, we optimize the architecture to achieve both high accuracy and interpretability. We train and evaluate the model on a large dataset of thermoscopic images, ensuring its robustness across different skin cancer types and variations. Furthermore, we integrate the optimized CNN model into a smart healthcare system, allowing for seamless integration into clinical workflows. The system offers real-time feedback to dermatologists, helping them make better decisions and enhancing the accuracy of their diagnoses. Moreover, the interpretable nature of our model enables clinicians to understand the underlying features driving classification decisions, fostering trust and acceptance. Our experimental results demonstrate superior performance compared to state-of-the-art methods, achieving high accuracy in skin cancer classification while providing meaningful insights into the decision-making process. Overall, our proposed approach represents a significant advancement toward the development of interpretable and effective tools for skin cancer diagnosis in smart healthcare systems

Keywords: Skin cancer, healthcare, artificial intelligence, deep learning, OpenCV, RNN

[This article belongs to Research & Reviews: A Journal of Bioinformatics (rrjobi)]

How to cite this article:
Gajendra Kumar Deshmukh, Satyam Jadhav, Aditya Kadam, Sumit Aware, Twinkle Shukla. Interpretable Skin Cancer Detection via Optimized CNN Models for Smart Healthcare Solutions. Research & Reviews: A Journal of Bioinformatics. 2025; 12(01):13-17.
How to cite this URL:
Gajendra Kumar Deshmukh, Satyam Jadhav, Aditya Kadam, Sumit Aware, Twinkle Shukla. Interpretable Skin Cancer Detection via Optimized CNN Models for Smart Healthcare Solutions. Research & Reviews: A Journal of Bioinformatics. 2025; 12(01):13-17. Available from: https://journals.stmjournals.com/rrjobi/article=2025/view=196911


References

  1. AlSalman ISA, Alkaff TM, Alzaid T, Binamer Y. Nonmelanoma skin cancer in Saudi Arabia: Single center experience. Ann Saudi Med. 2018;38(1):42–45. doi:10.5144/0256-4947.2018.42.
  2. Nehal KS, Bichakjian CK. Update on keratinocyte carcinomas. N Engl J Med. 2018;379(4):363–374. doi:10.1056/NEJMra1708709.
  3. American Cancer Society. (2022). Key statistics for melanoma skin cancer. Atlanta, GA: American Cancer Society [Online]. Available from: https://www.cancer.org/cancer/melanoma-skin-cancer/about/key-statistics.html.
  4. Albahar MA. Classification of skin lesions using convolutional neural networks with novel regularization capabilities. IEEE Access. 2019;7:38306–3813.doi:10.1109/ACCESS.2019.2906116.
  5. Hasan MR, Fatemi MI, Khan MM, Kaur M, Zaguia A. Comparative analysis of skin cancer (benign vs. malignant) detection using convolutional neural networks. J Healthc Eng. 2021;2021:5895156. doi:10.1155/2021/5895156.
  6. Siegel RL. Colorectal cancer statistics, 2020. CA Cancer J Clin. 2020;70(3):145–164. doi:10.3322/caac.21601.
  7. Ajagbe SA, Amuda KA, Oladipupo MA, Afe OF, Okesola KI. Multiclassification of Alzheimer disease on magnetic resonance images (MRI) using deep convolutional neural network (DCNN) approaches. Int J Adv Comput Res. 2021;11(53):51–60. doi:10.19101/IJACR.2021.115007.
  8. Barata C, Marques JS, Celebi ME. Deep attention model for the hierarchical diagnosis of skin lesions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2019. p. 1–9. IEEE. doi:10.1109/CVPRW.2019.00001.
  9. Soyer HP, Argenziano G, Ruocco V, Chimenti S. Dermoscopy of pigmented skin lesions (Part II). Eur J Dermatol. 2001;11(5):483–498.
  10. Ankad B, Sakhare P, Prabhu M. Dermoscopy of non-melanocytic and pink tumors in brown skin: A descriptive study. Indian J Dermatopathol Diagn Dermatol. 2017;4(2):41. doi:10.4103/IJDPDD.IJDPDD_10_17.

Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 14/12/2024
Accepted 09/01/2025
Published 04/02/2025


Loading citations…