MedAugment: Universal Automatic Data Augmentation Plug-in for Medical Image Analysis

TL;DR

MedAugment is a universal automatic data augmentation plugin designed specifically for medical image analysis, improving performance while avoiding distortions and reducing computational costs.

Contribution

The paper introduces MedAugment, a general automatic data augmentation method tailored for medical images, with a novel sampling strategy and hyperparameter control for safe and efficient augmentation.

Findings

Outperforms existing augmentation methods on multiple datasets

Prevents color distortions and structural alterations in medical images

Operates with negligible computational overhead

Abstract

Data augmentation (DA) has been widely leveraged in computer vision to alleviate data shortage, while its application in medical imaging faces multiple challenges. The prevalent DA approaches in medical image analysis encompass conventional DA, synthetic DA, and automatic DA. However, these approaches may result in experience-driven design and intensive computation costs. Here, we propose a suitable yet general automatic DA method for medical images termed MedAugment. We propose pixel and spatial augmentation spaces and exclude the operations that can break medical details and features. Besides, we propose a sampling strategy by sampling a limited number of operations from the two spaces. Moreover, we present a hyperparameter mapping relationship to produce a rational augmentation level and make the MedAugment fully controllable using a single hyperparameter. These configurations settle the differences between natural and medical images. Extensive experimental results on four classification and four segmentation datasets demonstrate the superiority of MedAugment. Compared with existing approaches, the proposed MedAugment prevents producing color distortions or structural alterations while involving negligible computational overhead. Our method can serve as a plugin without an extra training stage, offering significant benefits to the community and medical experts lacking a deep learning foundation. The code is available at https://github.com/NUS-Tim/MedAugment.