International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Bias-Aware Explainable Foundation Model for Clinically Ready Real-Time Skin Cancer Diagnosis |
|---|---|
| ABSTRACT | Skin cancer is one of the most prevalent and rapidly rising malignancies worldwide, placing a significant burden on healthcare systems and clinical practitioners. Early diagnosis plays a critical role in improving survival outcomes, particularly for melanoma, which exhibits aggressive metastatic behavior when detected late. Although artificial intelligence (AI) has demonstrated promising performance in automated skin lesion classification, the majority of existing systems remain unsuitable for real-world clinical deployment due to demographic bias, limited interpretability, poor generalization, and lack of real-time feasibility. This paper proposes a clinically deployable, bias-aware, and explainable multimodal foundation model for real-time skin cancer diagnosis. The framework integrates dermoscopic images, clinical photographs, patient metadata, and clinically meaningful digital biomarkers into a unified architecture. Fairness-aware learning strategies are embedded directly into the optimization process to reduce demographic disparities, while explainability is achieved through biomarker-aligned attention mechanisms and interpretable feature attribution. Extensive experimental evaluation across multiple dermatological datasets demonstrates that the proposed approach achieves high diagnostic accuracy, robust generalization, equitable performance across demographic subgroups, and low-latency inference suitable for clinical workflows. The results indicate that the proposed framework represents a significant step toward trustworthy and ethically aligned AI-assisted dermatological diagnosis. |
| AUTHOR | AKHILESH SHUKLA, PRAMOD SINGH, AKHILESH A. WAOO Department of Computer Science, AKS University, Satna, India |
| VOLUME | 180 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1401064 |
| pdf/64_A Bias-Aware Explainable Foundation Model for Clinically Ready Real-Time Skin Cancer Diagnosis.pdf | |
| KEYWORDS | |
| References | 1. J.-W. Tjiu and C.-F. Lu,“Equity and generalizability of artificial intelligence for skin-lesion diagnosis using clinical, dermoscopic, and smartphone images: A systematic review and meta-analysis,” Medicina, vol. 61, no. 12, pp. 1–18, 2025. 2. Z. Wang , “Explainable multimodal AI for skin lesion risk prediction via 3D imaging and clinical data,” Scientific Reports, vol. 15, no. 1, pp. 1–14, 2025. 3. Singh, A. A. Waoo, and S. Subhadra “Alleviate cold-start problem in recommendation systems using machine learning algorithms,” Jan. 2024. [Online]. give these refernces in apa format 4. N. Kushwaha and A. A. Waoo, “Energy consumption prediction by using machine learning,” Mar. 2024. [Online]. 5. J. K. Jain and A. A. Waoo, “An artificial neural network technique for prediction of cyber-attack using intrusion detection system,” Feb. 2023. [Online]. 6. S. Sharma and A. A. Waoo, “Customer behavior analysis in e-commerce using machine learning approach: A survey,” Apr. 2023. [Online]. 7. A. Waoo and R. S. Thakur, “Machine learning-based intrusion detection system for network security,” International Journal of Computer Networks and Applications, vol. 10, no. 2, pp. 145–154, 2023. 8. A. Waoo, P. Tiwari, and M. Bhatele, “Secure medical data transmission using hybrid encryption and watermarking techniques,” Journal of Medical Systems, vol. 47, no. 6, pp. 1–12, 2023. 9. M. D. Ali “Explainable AI-based multi-class skin cancer detection,” Applied Sciences, vol. 15, no. 21, pp. 1–20, 2025. 10. S. Verma, M. Bhatele, and A. A. Waoo, “Enhancing medical image security using RGB and YUV color space-based advanced triple watermarking,” Multimedia Tools and Applications, vol. 83, pp. 1–24, 2024. 11. S. Górecki “Artificial intelligence and new technologies in melanoma: Developments, challenges, and translation,” Frontiers in Oncology, vol. 15, pp. 1–19, 2025. 12. O. Attallah, “Explainable deep learning classification of skin cancer: Ensemble CNN approaches,” Computers in Biology and Medicine, vol. 173, pp. 1–13, 2024. 13. S. Verma, M. Bhatele, and A. A. Waoo, “A comparative analysis of spatial and transform domain watermarking techniques for medical images,” International Journal of Computer Applications, vol. 185, no. 12, pp. 15–21, 2022. 14. T. Li “Application of multimodal deep learning in the auxiliary dermatological diagnosis,” Artificial Intelligence in Medicine, vol. 154, pp. 1–17, 2025. 15. S. Verma, M. Bhatele, and A. A. Waoo, “Advanced security framework for DICOM images using triple watermarking with DWT and SVD for role-based access control,” Next Research, vol. 2, no. 3, Art. no. 100524, Jun. 2025, doi: 10.1016/j.nexres.2025.100524. 16. A. Waoo, S. Sharma, and J. K. Jain, “A comprehensive survey on machine learning techniques for cybersecurity applications,” Journal of King Saud University – Computer and Information Sciences, vol. 36, no. 2, pp. 101–118, 2024. 17. S. A. H. Shah, “Explainable AI-based skin cancer detection using CNN,” Vision, vol. 10, no. 12, pp. 1–16, 2024. 18. Shoaib, “An explainable hybrid deep learning framework for precise skin lesion classification,” Frontiers in Medicine, vol. 12, pp. 1–15, 2025. 19. M. Zbrzezny “Artificial intelligence in dermatology: Methods, ethics, and verification,” Applied Sciences, vol. 15, no. 9, pp. 1–22, 2025. 20. N. S. Naz “Privacy-preserving skin cancer diagnosis through multimodal data fusion,” Scientific Reports, vol. 15, pp. 1–14, 2025. 21. Metta“Interpretable AI for enhanced skin lesion classification,” Diagnostics, vol. 14, no. 7, pp. 1–18, 2024. 22. M. Pavani “Hybrid explainable deep learning framework for skin disease detection,” Artificial Intelligence, vol. 9, pp. 1–16, 2025. 23. Das “Comparative analysis of multimodal architectures for skin lesion detection,” Frontiers in Artificial Intelligence, vol. 8, pp. 1–17, 2025. 24. T. Chanda “Dermatologist-like explainable artificial intelligence enhances trust and diagnostic accuracy,” Nature Communications, vol. 15, pp. 1–12, 2024. 25. M. A. A. Mahmud “Explainable deep learning approaches for high-precision skin cancer diagnostics,” Scientific Reports, vol. 15, pp. 1–15, 2025. 26. A. A. Waoo, S. Verma, and M. Bhatele, “Privacy-aware intelligent healthcare systems using secure AI frameworks,” Artificial Intelligence in Medicine, vol. 153, Art. no. 102570, 2025. |
