Domain-guided data augmentation for deep learning on medical imaging

TL;DR

This paper demonstrates that domain-guided data augmentation, specifically context-preserving cut-paste, can effectively enhance deep learning models for fetal ultrasound view classification, matching traditional augmentation performance.

Contribution

It introduces a novel context-preserving cut-paste augmentation strategy for medical imaging and evaluates its effectiveness on benchmark datasets, providing open-source tools for implementation.

Findings

Augmentation with cut-paste improves model performance.

Models trained with this augmentation perform similarly to traditional methods.

Open-source code enables easy adoption of the technique.

Abstract

While domain-specific data augmentation can be useful in training neural networks for medical imaging tasks, such techniques have not been widely used to date. Here, we test whether domain-specific data augmentation is useful for medical imaging using a well-benchmarked task: view classification on fetal ultrasound FETAL-125 and OB-125 datasets. We found that using a context-preserving cut-paste strategy, we could create valid training data as measured by performance of the resulting trained model on the benchmark test dataset. When used in an online fashion, models trained on this data performed similarly to those trained using traditional data augmentation (FETAL-125 F-score 85.33+/-0.24 vs 86.89+/-0.60, p-value 0.0139; OB-125 F-score 74.60+/-0.11 vs 72.43+/-0.62, p-value 0.0039). Furthermore, the ability to perform augmentations during training time, as well as the ability to apply chosen augmentations equally across data classes, are important considerations in designing a bespoke data augmentation. Finally, we provide open-source code to facilitate running bespoke data augmentations in an online fashion. Taken together, this work expands the ability to design and apply domain-guided data augmentations for medical imaging tasks.