The Impact of Lesion Focus on the Performance of AI-Based Melanoma Classification
This work addresses the diagnostic reliability issue in melanoma detection for medical applications, but it is incremental as it builds on existing methods to analyze attention-performance relationships.
The study tackled the problem of inconsistent lesion focus in AI-based melanoma classification, finding that models with higher attention on lesion areas achieved better diagnostic performance, as measured by precision, recall, and F1-score.
Melanoma is the most lethal subtype of skin cancer, and early and accurate detection of this disease can greatly improve patients' outcomes. Although machine learning models, especially convolutional neural networks (CNNs), have shown great potential in automating melanoma classification, their diagnostic reliability still suffers due to inconsistent focus on lesion areas. In this study, we analyze the relationship between lesion attention and diagnostic performance, involving masked images, bounding box detection, and transfer learning. We used multiple explainability and sensitivity analysis approaches to investigate how well models aligned their attention with lesion areas and how this alignment correlated with precision, recall, and F1-score. Results showed that models with a higher focus on lesion areas achieved better diagnostic performance, suggesting the potential of interpretable AI in medical diagnostics. This study provides a foundation for developing more accurate and trustworthy melanoma classification models in the future.