An explainable hybrid deep learning framework for precise skin lesion segmentation and multi-class classification
The use of explainable AI (XAI) enhances transparency, a crucial factor in the clinical acceptance of AI-based diagnostic tools. This approach shows promise in improving diagnostic accuracy and supporting dermatologists, especially in resource-constrained settings, by providing both accurate lesion delineation and reliable class predictions. Future research will focus on improving the model's generalizability, addressing underrepresented classes, and validating its effectiveness in real-world scenarios.
Authors
- Muhammad Bilal Khan (ORCID: https://orcid.org/0009-0001-5074-9672)
- Abdul Hannan Khan
- Anas Bilal (ORCID: https://orcid.org/0000-0002-7760-3374)
- Monir Abdullah (ORCID: https://orcid.org/0000-0002-9713-4296)
- Abdulbasit A. Darem (ORCID: https://orcid.org/0000-0002-5650-1838)
- Muhammad Fiaz (ORCID: https://orcid.org/0000-0001-7666-9147)
- Raheem Sarwar (ORCID: https://orcid.org/0000-0002-0640-807X)
Institutions
- Northern Border University (SA)
- Manchester Metropolitan University (GB)
- Hainan Normal University (CN)
- University of Central Punjab (PK)
- University of Bisha (SA)
- Nur International University (PK)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-10-13
- DOI
- https://doi.org/10.3389/fmed.2025.1681542
- Citations
- 4
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 4.18
Funders
- University of Bisha
- Northern Border University