Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification

Frid-Adar, Maayan; Klang, Eyal; Amitai, Michal Marianne; Goldberger, Jacob; Greenspan, Hayit

doi:10.48550/arxiv.1801.02385

Cited by 14 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This provides strong evidence that the additional information provided by the two augmentation methods are independent. It also suggests that when used together they are potentially synergistic, an observation which agrees with the results in [5]. This could be due to the two methods acting in different ways, with GANs providing an effective alternative to traditional augmentation when attempting to interpolate within the training distribution, but cannot extrapolate beyond its extremes without the aid of traditional augmentation like rotation.…”

Section: Discussionsupporting

confidence: 66%

“…The results reported in [5,15] suggest that GANs can have a significant benefit when used for data augmentation in some classification tasks. In this paper we thoroughly investigate this use of GANs in different domains for the purpose of medical image segmentation.…”

Section: Contributionmentioning

confidence: 99%

“…In [1], the authors train a conditional GAN on unlabelled data to generate alternative versions of a given real image, and in [23], the authors use a similar GAN to impose emotions on neutral faces to expand underrepresented classes. However, the use of nonconditional GANs to augment training data directly as a preprocessing step with no additional data has only very recently been explored [5,15], with promising results in medical image classification tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

Bowles,

Chen,

Guerrero

et al. 2018

Preprint

115

129

View full text Add to dashboard Cite

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on the availability of expert observers. The limited amount of training data can inhibit the performance of supervised machine learning algorithms which often need very large quantities of data on which to train to avoid overfitting. So far, much effort has been directed at extracting as much information as possible from what data is available. Generative Adversarial Networks (GANs) offer a novel way to unlock additional information from a dataset by generating synthetic samples with the appearance of real images. This paper demonstrates the feasibility of introducing GAN derived synthetic data to the training datasets in two brain segmentation tasks, leading to improvements in Dice Similarity Coefficient (DSC) of between 1 and 5 percentage points under different conditions, with the strongest effects seen fewer than ten training image stacks are available.

show abstract

Section: Discussionsupporting

confidence: 66%

Section: Contributionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

Bowles,

Chen,

Guerrero

et al. 2018

Preprint

115

129

View full text Add to dashboard Cite

show abstract

“…They also compare their approach with images generated using a GAN and traditional methods. For medical images, a generative solution [14] was proposed for the classification of liver lesion. The paper studied the usage of classical data augmentation followed by a GAN based approach to generate synthetic dataset.…”

Section: Related Workmentioning

confidence: 99%

Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images

Karki,

Cho,

2020

Preprint

View full text Add to dashboard Cite

Data augmentation can effectively resolve a scarcity of images when training machine-learning algorithms. It can make them more robust to unseen images. We present a lesion conditional Generative Adversarial Network (LcGAN ) to generate synthetic Computed Tomography (CT) images for data augmentation. A lesion conditional image (segmented mask) is an input to both the generator and the discriminator of the LcGAN during training. The trained model generates contextual CT images based on input masks. We quantify the quality of the images by using a fully convolutional network (FCN) score and blurriness. We also train another classification network to select better synthetic images. These synthetic CT images are then augmented to our hemorrhagic lesion segmentation network. By applying this augmentation method on 2.5%, 10% and 25% of original data, segmentation improved by 12.8%, 6% and 1.6% respectively. Introduction Although deep learning architectures have solved challenging computer vision tasks in recent years [1], [2],[3], they require large amounts of data. In the medical field, collecting this vast amount of data is still quite challenging, and models tend to overfit if trained with limited data. As a solution to this problem, synthetic data is commonly added. Standard image transformation techniques like rotations, rescaling and contrast changes are some traditional methods of augmenting image datasets. These methods provide some variations in the dataset when there are a small number of samples. Nonetheless, these methods are still limited [4], as each new synthetic image is a transformation of a single image.

show abstract

“…The core idea is that we generate CISLs based on GAN and combine these generated samples and real data to train the CNN classifier. Unlike the method in [14] that uses the traditional data augmentation to extend the training data of the GAN model and trains the liver lesion classifier with the mixture of the generated data and real data, we train the GAN with only the real data and adopt the two-stages training scheme (i.e. pre-training with generated data and fine-tuning with real data).…”

Section: Introductionmentioning

confidence: 99%

Lung CT Imaging Sign Classification through Deep Learning on Small Data

He¹

2019

Preprint

View full text Add to dashboard Cite

The annotated medical images are usually expensive to be collected. This paper proposes a deep learning method on small data to classify Common Imaging Signs of Lung diseases (CISL) in computed tomography (CT) images. We explore both the real data and the data generated by Generative Adversarial Network (GAN) to improve the reliability and the generalization of learning. First, we use GAN to generate a large number of CISLs from small annotated data, which are difficult to be distinguished from real counterparts. These generated samples are used to pre-train a Convolutional Neural Network (CNN) for classifying CISLs. Second, we fine-tune the CNN classification model with real data. Experiments were conducted on the LISS database of CISLs. We successfully convinced radiologists that our generated CISLs samples were real for 56.7% of our experiments. The pre-trained CNN model achieves 88.4% of mean accuracy of binary classification, and after fine-tuning, the mean accuracy is significantly increased to 95.0%. For multi-classification of all types of CISLs and normal tissues, through the two stages of training, the mean accuracy, sensitivity and specificity are up to about 91.83%, 92.73% and 99.0%, respectively. To our knowledge, this is the best result achieved on the LISS database, which demonstrates that the proposed method is effective and promising for fulfilling deep learning on small data.

show abstract

Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification

Cited by 14 publications

References 0 publications

GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images

Lung CT Imaging Sign Classification through Deep Learning on Small Data

Contact Info

Product

Resources

About