@article{Alwakid2026, 
author = {Ghadah Naif Alwakid and Samabia Tehsin and Mamoona Humayun and Asad Farooq and Ibrahim Alrashdi and Amjad Alsirhani},
title = {Graph Attention Networks for Skin Lesion Classification with CNN-Driven Node Features},
year = {2026},
journal = {Computers, Materials & Continua},
volume = {86},
number = {1},
pages = {1-21},
keywords = {Graph neural network, image classification, DermaMNIST dataset, graph representation},
url = {https://www.sciopen.com/article/10.32604/cmc.2025.069162},
doi = {10.32604/cmc.2025.069162},
abstract = {Skin diseases affect millions worldwide. Early detection is key to preventing disfigurement, lifelong disability, or death. Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance, and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks (CNNs). We frame skin lesion recognition as graph-based reasoning and, to ensure fair evaluation and avoid data leakage, adopt a strict lesion-level partitioning strategy. Each image is first over-segmented using SLIC (Simple Linear Iterative Clustering) to produce perceptually homogeneous superpixels. These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity. Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone, providing strong representational power at modest computational cost. The resulting graphs are processed by a five-layer Graph Attention Network (GAT) that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output. Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35% accuracy and 98.04% AUC, outperforming contemporary CNNs, AutoML approaches, and alternative graph neural networks. An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet, and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing. The method requires no data augmentation or external metadata, making it a drop-in upgrade for clinical computer-aided diagnosis systems.}
}