Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification
This work addresses the challenge of integrating spatial structure and patient metadata for automated skin cancer diagnosis, offering a new graph-centric perspective that improves classification robustness.
The paper proposes a graph-based framework for skin lesion classification that models dermoscopic images as superpixel graphs with geometric edge attributes and integrates patient metadata via a dedicated context node. It achieves consistent improvements over state-of-the-art methods across four public benchmarks.
Automated skin cancer classification from dermoscopic images remains challenging due to heterogeneous lesion structure, strong intra-class variability, and subtle visual differences between benign and malignant cases. Existing CNN/ViT pipelines typically rely on global or patch-level features and often combine patient metadata via late fusion, which limits spatially grounded multimodal reasoning. We present a novel region-based graph learning framework that explicitly models lesions as graphs of spatially coherent superpixel regions represented as frozen CNN features. To capture fine-grained lesion arrangements, we encode inter-regional geometry as edge attributes and introduce a dedicated metadata context node connected to all regions, providing structured integration of demographic/clinical variables within the same relational space. Node representations are updated using our edge-aware graph transformer followed by attention-driven propagation, and a final graph-level embedding for benign-malignant classification. Experiments on four public benchmarks demonstrate that explicit region-level relational modeling and graph-native multimodal fusion yield consistent gains over the state-of-the-art. Consequently, we establish a new graph-centric perspective in which CNN features are modeled as relational nodes and improved through contextual integration, yielding more expressive and robust classifications.