BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification
This work addresses the problem of computationally intensive and expertise-dependent data augmentation for medical imaging, offering a plug-and-play solution that improves model performance, though it appears incremental as it builds on semantic data augmentation concepts.
The authors tackled the challenge of designing effective data augmentation for medical image classification by proposing BSDA, a Bayesian random semantic data augmentation method that operates in feature space, which outperformed current methods on multiple 2D and 3D medical image datasets.
Data augmentation is a crucial regularization technique for deep neural networks, particularly in medical image classification. Mainstream data augmentation (DA) methods are usually applied at the image level. Due to the specificity and diversity of medical imaging, expertise is often required to design effective DA strategies, and improper augmentation operations can degrade model performance. Although automatic augmentation methods exist, they are computationally intensive. Semantic data augmentation can implemented by translating features in feature space. However, over-translation may violate the image label. To address these issues, we propose \emph{Bayesian Random Semantic Data Augmentation} (BSDA), a computationally efficient and handcraft-free feature-level DA method. BSDA uses variational Bayesian to estimate the distribution of the augmentable magnitudes, and then a sample from this distribution is added to the original features to perform semantic data augmentation. We performed experiments on nine 2D and five 3D medical image datasets. Experimental results show that BSDA outperforms current DA methods. Additionally, BSDA can be easily assembled into CNNs or Transformers as a plug-and-play module, improving the network's performance. The code is available online at \url{https://github.com/YaoyaoZhu19/BSDA}.