Explainable Melanoma Diagnosis with Contrastive Learning and LLM-based Report Generation
This addresses the lack of interpretability in deep learning models for clinical dermatology, which is a critical barrier to adoption by clinicians.
The paper tackles the problem of model opacity in melanoma diagnosis by introducing a cross-modal explainable framework that aligns clinical criteria with visual features and generates textual explanations, achieving 92.79% accuracy and an AUC of 0.961.
Deep learning has demonstrated expert-level performance in melanoma classification, positioning it as a powerful tool in clinical dermatology. However, model opacity and the lack of interpretability remain critical barriers to clinical adoption, as clinicians often struggle to trust the decision-making processes of black-box models. To address this gap, we present a Cross-modal Explainable Framework for Melanoma (CEFM) that leverages contrastive learning as the core mechanism for achieving interpretability. Specifically, CEFM maps clinical criteria for melanoma diagnosis-namely Asymmetry, Border, and Color (ABC)-into the Vision Transformer embedding space using dual projection heads, thereby aligning clinical semantics with visual features. The aligned representations are subsequently translated into structured textual explanations via natural language generation, creating a transparent link between raw image data and clinical interpretation. Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961, along with significant improvements across multiple interpretability metrics. Qualitative analyses further show that the spatial arrangement of the learned embeddings aligns with clinicians' application of the ABC rule, effectively bridging the gap between high-performance classification and clinical trust.