Scopus Indexed Publications

Paper Details


Title
A Comparative Evaluation of Lightweight and Explainable Models for Automated Skin Lesion Segmentation

Author
Abu Kausar, Abu Shahed Shah Md Nazmul Arefin, Kazi Jahid Hasan, Kishon Kumar Pashi, Maysha Mahjabin Mimi, Md. Salah Uddin,

Email

Abstract

Precise skin lesion localization of dermoscopic images is vital in the early detection of melanoma and digital dermatology processes. This paper is a full assessment of three light and interpretable deep learning architectures, namely U-Net, a modified convolutional neural network (CNN), and a transformer-based SegFormer, on the HAM10000-ISIC2018 dataset. The preprocessing, enhancement, and augmentation conditions were the same in all the models to succeed the fairness and repeatability. It included Grad-CAM and attention-rollout explainability methods to visualize areas of focus in models and choose to make them more clinical interpretable. Dice score, precision, and validation accuracy quantitatively show that both U-Net and SegFormer attained the highest Dice score 93.05%, and the custom CNN, next in terms of architectural complexity, has attained a competitive Dice score of 88.22%. SegFormer was the most precise 95.51% and effective, which means that it is very suitable in resource-limited or mobile diagnostic settings. [NEW] We validated model robustness against common dermatological artifacts (hair, ruler marks, gel bubbles) and compared performance with recent state-of-the-art architectures including TransUNet and Swin-UNet. The experimental results show that light and understandable segmentation models can be used to reach clinically significant performance and can be used as a reliable element in future computer-aided dermatology systems and diagnostic piping.


Keywords

Journal or Conference Name
2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence and Networking, QPAIN 2026

Publication Year
2026

Indexing
scopus