Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images

TL;DR

This study evaluates various data augmentation techniques for breast ultrasound image classification, revealing that specific augmentations significantly enhance model performance and generalizability across multiple datasets.

Contribution

It provides a comprehensive analysis of augmentation effectiveness in breast ultrasound imaging, filling a gap in understanding their impact across medical imaging tasks.

Findings

Certain augmentations outperform others in improving accuracy.

Augmentation techniques lead to significant performance gains.

Findings are consistent across multiple datasets.

Abstract

Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability in medical image analysis, it is frequently underutilized. This appears to be due to a gap in our collective understanding of the efficacy of different augmentation techniques across medical imaging tasks and modalities. One domain where this is especially true is breast ultrasound images. This work addresses this issue by analyzing the effectiveness of different augmentation techniques for the classification of breast lesions in ultrasound images. We assess the generalizability of our findings across several datasets, demonstrate that certain augmentations are far more effective than others, and show that their usage leads to significant performance gains.