Data Augmentation for Brain-Tumor Segmentation: A Review

@article{Nalepa2019DataAF,
  title={Data Augmentation for Brain-Tumor Segmentation: A Review},
  author={Jakub Nalepa and Michal Marcinkiewicz and Michal Kawulok},
  journal={Frontiers in Computational Neuroscience},
  year={2019},
  volume={13}
}
Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks, and can be perceived as implicit regularization. It plays a pivotal role in scenarios in which the amount of high-quality ground-truth data is limited, and acquiring new examples is costly and time-consuming. This is a very common problem in medical image analysis, especially tumor delineation. In this paper, we review the current advances in data-augmentation techniques applied to… 
What is the best data augmentation approach for brain tumor segmentation using 3D U-Net?
TLDR
The conclusion is that brightness augmentation and elastic deformation works best, and that combinations of different augmentation techniques do not provide further improvement compared to only using one augmentation technique.
Whole Tumor Segmentation from Brain MR images using Multi-view 2D Convolutional Neural Network
TLDR
A U-Net architecture based 2D convolutional neural network is employed for each of the orthogonal planes (sagittal, coronal and axial) and fused their predictions to minimize Dice loss between the binary prediction and its actual labels for segmentation of brain tumor.
A review of medical image data augmentation techniques for deep learning applications
TLDR
A systematic review of the literature where data augmentation was utilised on medical images to train a deep learning model aims to give an insight to these techniques and confidence in the validity of the models produced.
Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art
TLDR
This paper presents a review of state-of-the-art deep learning methods for brain tumor segmentation, clearly highlighting their building blocks and various strategies and concludes with a critical discussion of open challenges in medical image analysis.
A Deep Learning Image Data Augmentation Method for Single Tumor Segmentation
TLDR
Compared with the traditional methods, the proposed data augmentation method has better performance in single tumor segmentation.
Spherical coordinates transformation pre-processing in Deep Convolution Neural Networks for brain tumor segmentation in MRI
TLDR
A 3D spherical coordinates transform during the pre-processing phase has been hypothesized to improve DCNN models’ accuracy and to allow more generalizable results even when the model is trained on small and heterogeneous datasets and translated into different domains.
MRI Images, Brain Lesions and Deep Learning
TLDR
The main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment.
Generative Adversarial Networks in Medical Image augmentation: A review.
Machine Learning Algorithms in Neuroimaging: An Overview.
TLDR
This chapter summarizes the basic concepts underlying ML application for neuroim imaging and discusses technical aspects of the most promising algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), in order to provide the readership with the fundamental theoretical tools to better understand ML in neuroimaging.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 107 REFERENCES
Data Augmentation via Image Registration
TLDR
This paper uses a set of MRI scans of 44 low-grade glioma patients, augmented it using the proposed technique, and exploited it to train U-Net-based deep networks, showing that the augmentation delivers statistically important boost of performance without sacrificing inference speed.
Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks
Glioma Segmentation with Cascaded Unet
TLDR
This paper proposes modifications to the 3D UNet architecture and augmentation strategy to efficiently handle multimodal MRI input and introduces approach to enhance segmentation quality with context obtained from models of the same topology operating on downscaled data.
Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks
TLDR
A novel automatic data augmentation method that uses generative adversarial networks to learn augmentations that enable machine learning based method to learn the available annotated samples more efficiently is proposed.
Automatic Brain Tumor Segmentation by Exploring the Multi-modality Complementary Information and Cascaded 3D Lightweight CNNs
TLDR
A mechanism is developed by training the CNNs like the annotation process by radiologists to improve the brain tumor segmentation accuracy compared with the common merging strategy and a 3D lightweight CNN is proposed to extract brain tumor substructures.
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images
TLDR
This paper proposes an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels, which allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network.
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images.
TLDR
This paper proposes an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels, which allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network.
Segmenting Brain Tumors from MRI Using Cascaded Multi-modal U-Nets
TLDR
A deep learning-powered approach for brain tumor segmentation which exploits multiple magnetic-resonance modalities and processes them in two cascaded stages, using multi-modal fully-convolutional neural nets inspired by U-Nets.
Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
TLDR
Experiments with BraTS 2018 training and validation set show that test-time augmentation can achieve higher segmentation accuracy and obtain uncertainty estimation of the segmentation results.
Deep Convolutional Neural Networks Using U-Net for Automatic Brain Tumor Segmentation in Multimodal MRI Volumes
TLDR
A fully automated and efficient brain tumor segmentation method based on 2D Deep Convolutional Neural Networks (DNNs) which automatically extracts the whole tumor and intra-tumor regions, including enhancing tumor, edema and necrosis, from pre-operative multimodal 3D-MRI.
...
1
2
3
4
5
...