Reducing Labelled Data Requirement for Pneumonia Segmentation using Image Augmentations

TL;DR

This study demonstrates that specific image augmentations, particularly rotate and mixup, can significantly reduce the amount of labeled data needed for effective pneumonia segmentation in chest X-rays, achieving similar performance to models trained on full datasets.

Contribution

The paper introduces the use of targeted image augmentations to lower labeled data requirements in pneumonia segmentation, showing a 70% reduction while maintaining accuracy.

Findings

Rotate and mixup augmentations reduce data needs by 70%.

Augmented models perform comparably to full-data models in AUC and IoU.

Targeted augmentations can alleviate data annotation bottlenecks.

Abstract

Deep learning semantic segmentation algorithms can localise abnormalities or opacities from chest radiographs. However, the task of collecting and annotating training data is expensive and requires expertise which remains a bottleneck for algorithm performance. We investigate the effect of image augmentations on reducing the requirement of labelled data in the semantic segmentation of chest X-rays for pneumonia detection. We train fully convolutional network models on subsets of different sizes from the total training data. We apply a different image augmentation while training each model and compare it to the baseline trained on the entire dataset without augmentations. We find that rotate and mixup are the best augmentations amongst rotate, mixup, translate, gamma and horizontal flip, wherein they reduce the labelled data requirement by 70% while performing comparably to the baseline in terms of AUC and mean IoU in our experiments.