# Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation

arXiv: https://arxiv.org/abs/2205.09722 · HTML: https://mlsanity.com/paper/2205.09722/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 26 of 26)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [GridMask Data Augmentation](https://mlsanity.com/paper/2001.04086/) (2020)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://mlsanity.com/paper/1908.07801/) (2019)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19](https://mlsanity.com/paper/2004.02731/) (2020)
- [SuperMix: Supervising the Mixing Data Augmentation](https://mlsanity.com/paper/2003.05034/) (2020)
- [RegNet: Self-Regulated Network for Image Classification](https://mlsanity.com/paper/2101.00590/) (2021)
- [Improved Mixed-Example Data Augmentation](https://mlsanity.com/paper/1805.11272/) (2018)
- [Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images](https://mlsanity.com/paper/2004.05645/) (2020)
- [On the Cross-dataset Generalization in License Plate Recognition](https://mlsanity.com/paper/2201.00267/) (2022)
- [Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach](https://mlsanity.com/paper/2009.10181/) (2020)
- [Detection and severity classification of COVID-19 in CT images using deep learning](https://mlsanity.com/paper/2102.07726/) (2021)
- [Automated Chest CT Image Segmentation of COVID-19 Lung Infection based on 3D U-Net](https://mlsanity.com/paper/2007.04774/) (2020)
- [GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation](https://mlsanity.com/paper/2010.09456/) (2020)
- [ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection](https://mlsanity.com/paper/1910.01256/) (2019)
- [IDA: Improved Data Augmentation Applied to Salient Object Detection](https://mlsanity.com/paper/2009.08845/) (2020)
- [D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism](https://mlsanity.com/paper/2102.05210/) (2021)
- [Can Giraffes Become Birds? An Evaluation of Image-to-image Translation for Data Generation](https://mlsanity.com/paper/2001.03637/) (2020)
- [Spark in the Dark: Evaluating Encoder-Decoder Pairs for COVID-19 CT's Semantic Segmentation](https://mlsanity.com/paper/2109.14818/) (2021)

## Built on by (most cited first, 2 of 2)

- [A First Look at Dataset Bias in License Plate Recognition](https://mlsanity.com/paper/2208.10657/) (2022)
- [DACov: A Deeper Analysis of Data Augmentation on the Computed Tomography Segmentation Problem](https://mlsanity.com/paper/2303.05912/) (2023)

## Abstract (arXiv)

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.