Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
It addresses the underutilization of data augmentation in medical image analysis, specifically for breast ultrasound classification, but is incremental as it focuses on evaluating existing techniques.
This work analyzed the effectiveness of different data augmentation techniques for classifying breast lesions in ultrasound images, showing that certain augmentations lead to significant performance gains.
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.