Improving Lesion Detection by exploring bias on Skin Lesion dataset

TL;DR

This paper investigates biases in skin lesion datasets affecting deep learning models and proposes using GANs to mitigate these biases, aiming to improve lesion detection accuracy.

Contribution

It introduces shape-preserving masking experiments and applies GANs to reduce dataset bias in skin lesion analysis.

Findings

Shape-preserving masks do not improve model performance, indicating reliance on spurious correlations.

GANs can help mitigate dataset biases and improve model robustness.

Biases in datasets can significantly distort deep learning model outcomes.

Abstract

All datasets contain some biases, often unintentional, due to how they were acquired and annotated. These biases distort machine-learning models' performance, creating spurious correlations that the models can unfairly exploit, or, contrarily destroying clear correlations that the models could learn. With the popularity of deep learning models, automated skin lesion analysis is starting to play an essential role in the early detection of Melanoma. The ISIC Archive is one of the most used skin lesion sources to benchmark deep learning-based tools. Bissoto et al. experimented with different bounding-box based masks and showed that deep learning models could classify skin lesion images without clinically meaningful information in the input data. Their findings seem confounding since the ablated regions (random rectangular boxes) are not significant. The shape of the lesion is a crucial factor in the clinical characterization of a skin lesion. In that context, we performed a set of experiments that generate shape-preserving masks instead of rectangular bounding-box based masks. A deep learning model trained on these shape-preserving masked images does not outperform models trained on images without clinically meaningful information. That strongly suggests spurious correlations guiding the models. We propose use of general adversarial network (GAN) to mitigate the underlying bias.