Spectral Data Augmentation Techniques to quantify Lung Pathology from CT-images
This work addresses data scarcity in medical imaging for cystic fibrosis diagnosis, but it is incremental as it builds on existing augmentation methods.
The paper tackled the problem of limited labeled data in biomedical image processing by proposing spectral data augmentation techniques using discrete cosine and wavelet transforms for CT texture analysis to detect abnormal lung tissue in cystic fibrosis patients, resulting in a 44.1% increase in relative minor class segmentation performance over a baseline.
Data augmentation is of paramount importance in biomedical image processing tasks, characterized by inadequate amounts of labelled data, to best use all of the data that is present. In-use techniques range from intensity transformations and elastic deformations, to linearly combining existing data points to make new ones. In this work, we propose the use of spectral techniques for data augmentation, using the discrete cosine and wavelet transforms. We empirically evaluate our approaches on a CT texture analysis task to detect abnormal lung-tissue in patients with cystic fibrosis. Empirical experiments show that the proposed spectral methods perform favourably as compared to the existing methods. When used in combination with existing methods, our proposed approach can increase the relative minor class segmentation performance by 44.1% over a simple replication baseline.