Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Med.

Sec. Precision Medicine

Volume 12 - 2025 | doi: 10.3389/fmed.2025.1681542

This article is part of the Research TopicImmune-Related Biomarkers in Skin and Breast Cancer: Innovations in Immunological Diagnostics and TherapiesView all articles

An explainable hybrid deep learning framework for precise skin lesion segmentation and multi-class classification

Provisionally accepted
  • 1green international university lahore, Lahore, Pakistan
  • 2University of Central Punjab, Lahore, Pakistan
  • 3Hainan Normal University, Haikou, China
  • 4University of Bisha, Bishah, Saudi Arabia
  • 5Center for Scientific Research and Entrepreneurship, Northern Border University, Arar 73213, Saudi Arabia, Arar, Saudi Arabia
  • 6Manchester Metropolitan University, Manchester, United Kingdom

The final, formatted version of the article will be published soon.

Skin diseases, ranging from benign conditions to malignant tumors such as melanoma, present substantial diagnostic challenges due to their visual complexity and the inherent subjectivity in manual examination. This paper introduces a hybrid deep learning framework specifically designed for skin lesion segmentation and multi-class classification using dermoscopic images. The proposed model integrates a dual-task architecture, which combines a U-Net-based segmentation network with a classification module based on the EfficientNet-B0 backbone. To improve model interpretability and foster clinical trust, Grad-CAM is incorporated, allowing clinicians to visualize heatmaps that highlight the regions influencing the model's decisions. The model was trained and evaluated on the HAM10000 dataset, demonstrating robust performance, with a Dice coefficient surpassing 0.85 for segmentation and classification accuracy nearing 85%. Despite challenges such as class imbalance and the variety of lesion types, the model provides reliable results across different skin conditions. 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 clinical environments.

Keywords: skin disease, Classification, segmentation, Explainable AI, Grad-CAM

Received: 07 Aug 2025; Accepted: 26 Sep 2025.

Copyright: © 2025 Fiaz, Shoaib, Bilal, Khan, Kaid, Darem and Sarwar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Raheem Sarwar, r.sarwar@mmu.ac.uk

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.