Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation
This work addresses the need for robust computer-assisted diagnosis methods during the COVID-19 pandemic, but it is incremental as it focuses on optimizing existing techniques rather than introducing new paradigms.
The paper tackled the problem of improving semantic segmentation of COVID-19 CT scans by evaluating 20 data augmentation techniques across five datasets, finding that spatial-level transformations are most effective for enhancing neural network training.
With the COVID-19 global pandemic, computer-assisted diagnoses of medical images have gained much attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) became highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of COVID-19 and has been widely explored since the COVID-19 outbreak. In this work, we propose an extensive analysis of how different data augmentation techniques improve the training of encoder-decoder neural networks on this problem. Twenty different data augmentation techniques were evaluated on five different datasets. Each dataset was validated through a five-fold cross-validation strategy, thus resulting in over 3,000 experiments. Our findings show that spatial level transformations are the most promising to improve the learning of neural networks on this problem.