The Impact of Lesion Focus on the Performance of AI-Based Melanoma Classification

TL;DR

This paper investigates how the focus of AI models on lesion areas affects melanoma classification accuracy, emphasizing the importance of interpretability for reliable medical diagnosis.

Contribution

It analyzes the relationship between lesion attention and diagnostic performance, introducing methods to improve model focus and interpretability in melanoma detection.

Findings

Higher lesion focus correlates with better accuracy

Explainability methods reveal model attention patterns

Enhanced focus improves precision, recall, and F1-score

Abstract

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.