Web-Based Skin Cancer and Skin Disease Detection Using Image Analysis and Machine Learning
DOI:
https://doi.org/10.15662/IJEETR.2026.0802164Keywords:
This work focuses on skin disease classification using deep learning techniques with an emphasis on explainable artificial intelligence (XAI). A lightweight MobileNetV2-based feature extractor is employed along with Grad-CAM to provide visual explanations for predictions. To enhance clinical trust, a novel Grad-CAM Reliability Score (GRS) is introduced for assessing prediction reliability and handling uncertain cases effectively.Abstract
Skin diseases are among the most common health conditions worldwide, and early diagnosis plays a crucial role in effective treatment and prevention of severe complications. Recent advances in artificial intelligence, particularly deep learning, have shown promising results in automated skin disease classification using medical images. However, many existing systems focus primarily on prediction accuracy while neglecting reliability assessment and explainability, which are critical for real-world clinical adoption. To address these limitations, this paper presents an Intelligent Skin Disease Diagnosis System with Reliability-Aware Explainable AI.
The proposed system utilizes a hybrid architecture that combines deep learning and machine learning techniques. A pre-trained MobileNetV2 convolutional neural network is employed as a feature extractor to capture discriminative visual characteristics from dermoscopic or skin lesion images. The extracted deep features are then fed into a machine learning classifier to predict the skin disease category along with a confidence score. This hybrid approach reduces computational complexity while maintaining high classification performance, making the system suitable for real-time web-based deployment.
To enhance transparency and trustworthiness, the system integrates Gradient-weighted Class Activation Mapping (Grad-CAM) to generate visual explanations highlighting the regions of the image that most influence the model’s predictions. Beyond simple visualization, a novel Grad-CAM Reliability Score (GRS) is introduced to quantitatively evaluate the reliability of each prediction based on activation intensity and spatial distribution. This reliability score, combined with prediction confidence and probability margin analysis, enables robust decision validation.
When the system detects low confidence or unreliable predictions, it automatically classifies the outcome as “Uncertain” and recommends medical consultation instead of providing a potentially misleading diagnosis. This reliability-aware decision mechanism significantly reduces the risk of false predictions and improves clinical safety. Additionally, the system provides severity estimation, precautionary guidance, and a user-friendly web interface to enhance accessibility.
Experimental evaluation using benchmark skin disease datasets demonstrates that the proposed system achieves competitive classification accuracy while offering superior explainability and reliability assessment compared to traditional deep learning approaches. The integration of explainable AI with quantitative reliability validation represents a key contribution of this work. The proposed framework can serve as an effective decision-support tool for preliminary skin disease screening and future clinical AI systems.
References
1. K. Shahzad (2024) – Multi-classification of skin lesions using deep learning and explainable AI.
– Discusses deep learning for multi-class dermoscopic skin lesion classification.
2. O. Attallah (2024) – Explainable deep learning classification of skin cancer.
– Presents “Skin-CAD”, an explainable deep learning system for precise skin cancer classification.
3. L. Cino et al. (2025) – Skin lesion classification through test-time augmentation with visual explanations.
– Focuses on skin lesion classification with explainable AI support.
4. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
5. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
6. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
7. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
8. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
9. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
10. Mathew, A., & Alex, H. (2025). Federated Learning for Secure Genomic Research: Privacy-Preserving AI Solutions for Precision Medicine. Science and Technology: Developments and Applications Vol. 9, 36-43.
11. Soundappan, S. J. (2020). Big Data Analytics in Healthcare: Applications for Pandemic Forecastin. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 3(1), 2248-2253.
12. Padmapriya, V. M., Thenmozhi, K., Hemalatha, M., Thanikaiselvan, V., Lakshmi, C., Chidambaram, N., & Rengarajan, A. (2025). Secured IIoT against trust deficit-A flexi cryptic approach. Multimedia Tools and Applications, 84(9), 5625-5652.
13. Mathew, A., & Alex, H. (2022). Detect & protect-medical device cybersecurity. Curr. Overview Sci. Technol. Res, 1, 60-68.
B. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
14. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
15. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
16. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
17. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
18. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
19. SAH Shah (2024) – Explainable AI-Based Skin Cancer Detection using CNN and Grad-CAM.
– Highlights AI interpretability and Grad-CAM in dermatology.
20. A Al Mahmud (2024) – SkinNet-14: Deep learning for accurate skin cancer classification using dermoscopy images.
– Introduces an efficient deep learning model with competitive results.
21. Concept-Attention Whitening for Interpretable Skin Lesion Diagnosis (Apr 2024)
– Proposes a concept alignment method to improve interpretability of skin lesion CNNs.
22. Jayanth Mohan et al. (2024) – Enhancing skin disease classification with Transformer architectures and XAI.
– Uses Vision Transformers, Grad-CAM, and SHAP for better dermatologist-aligned diagnosis.
