Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation
Not on the map. Why?
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.
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
26 of 35 references.
References · 26
- 2017Mask R-CNNcited by 7,277
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
- 2017Random Erasing Data Augmentationcited by 1,239
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
- 2018Albumentations: fast and flexible image augmentationscited by 560
- 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
- 2020GridMask Data Augmentationcited by 123
- 2020MosMedData: Chest CT Scans With COVID-19 Related Findings Datasetcited by 104
- 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
- 2019Augmentation for small object detectioncited by 73
- 2020Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19cited by 62
14 more
- 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
- 2021RegNet: Self-Regulated Network for Image Classificationcited by 44
- 2018Improved Mixed-Example Data Augmentationcited by 42
- 2020Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Imagescited by 24
- 2022On the Cross-dataset Generalization in License Plate Recognitioncited by 22
- 2020Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approachcited by 12
- 2021Detection and severity classification of COVID-19 in CT images using deep learningcited by 12
- 2020Automated Chest CT Image Segmentation of COVID-19 Lung Infection based on 3D U-Netcited by 10
- 2020GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentationcited by 5
- 2019ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detectioncited by 4
- 2020IDA: Improved Data Augmentation Applied to Salient Object Detectioncited by 4
- 2021D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanismcited by 4
- 2020Can Giraffes Become Birds? An Evaluation of Image-to-image Translation for Data Generationcited by 3
- 2021Spark in the Dark: Evaluating Encoder-Decoder Pairs for COVID-19 CT's Semantic Segmentationcited by 2
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.