Leveraging Contextual Data Augmentation for Generalizable Melanoma Detection

TL;DR

This paper introduces a data augmentation approach to improve the generalizability of melanoma detection models by simulating real-world variability and addressing the unreliability of size-based features.

Contribution

It proposes a custom model with various data augmentation techniques to enhance melanoma classifier robustness against real-world testing conditions.

Findings

Data augmentation improves model generalization.

Size alone is unreliable for melanoma classification.

Augmentation highlights key features for better detection.

Abstract

While skin cancer detection has been a valuable deep learning application for years, its evaluation has often neglected the context in which testing images are assessed. Traditional melanoma classifiers assume that their testing environments are comparable to the structured images they are trained on. This paper challenges this notion and argues that mole size, a critical attribute in professional dermatology, can be misleading in automated melanoma detection. While malignant melanomas tend to be larger than benign melanomas, relying solely on size can be unreliable and even harmful when contextual scaling of images is not possible. To address this issue, this implementation proposes a custom model that performs various data augmentation procedures to prevent overfitting to incorrect parameters and simulate real-world usage of melanoma detection applications. Multiple custom models employing different forms of data augmentation are implemented to highlight the most significant features of mole classifiers. These implementations emphasize the importance of considering user unpredictability when deploying such applications. The caution required when manually modifying data is acknowledged, as it can result in data loss and biased conclusions. Additionally, the significance of data augmentation in both the dermatology and deep learning communities is considered.