Latent Space Analysis for Melanoma Prevention

TL;DR

This paper presents a novel interpretable deep learning approach using a structured latent space for melanoma risk assessment, enabling nuanced diagnosis and improved clinical trust.

Contribution

It introduces a Conditional Variational Autoencoder that captures semantic relationships among skin lesions, providing interpretable, continuous risk modeling beyond binary classification.

Findings

Latent space effectively differentiates benign and malignant lesions.

Spatial proximity in latent space correlates with melanoma risk.

Model enhances interpretability and clinical trust in AI diagnosis.

Abstract

Melanoma represents a critical health risk due to its aggressive progression and high mortality, underscoring the need for early, interpretable diagnostic tools. While deep learning has advanced in skin lesion classification, most existing models provide only binary outputs, offering limited clinical insight. This work introduces a novel approach that extends beyond classification, enabling interpretable risk modelling through a Conditional Variational Autoencoder. The proposed method learns a structured latent space that captures semantic relationships among lesions, allowing for a nuanced, continuous assessment of morphological differences. An SVM is also trained on this representation effectively differentiating between benign nevi and melanomas, demonstrating strong and consistent performance. More importantly, the learned latent space supports visual and geometric interpretation of malignancy, with the spatial proximity of a lesion to known melanomas serving as a meaningful indicator of risk. This approach bridges predictive performance with clinical applicability, fostering early detection, highlighting ambiguous cases, and enhancing trust in AI-assisted diagnosis through transparent and interpretable decision-making.