Synthetic data augmentation using GAN for improved liver lesion classification

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

doi:10.1109/isbi.2018.8363576

Cited by 591 publications

(345 citation statements)

References 12 publications

Supporting

Mentioning

302

Contrasting

Unclassified

Order By: Relevance

“…Because in such level of accuracy, sometimes the so-called improvement is just one kind of overfitting to the current data set. Moreover, some recent studies validate the effectiveness of using synthetic images in a low-data regime (Antoniou et al, 2017;Frid-Adar et al, 2018;Salimans et al, 2016;Zhang et al, 2018). Thus, in this section, a special case under the condition of complex detection problem, low-data regime, and restricted computational power is designed and discussed.…”

Section: Synthetic Data Aggregation and Fine-tuningmentioning

confidence: 92%

“…Antoniou, Storkey, and Edwards (2017) proposed Data Augmentation GAN (DAGAN) and compared the performance of DAGAN trained classifier with other basic ones based on Omniglot, EMNIST, and VGG-Face data sets, showing promising enhancement. Frid-Adar, Klang, Amitai, Goldberger, and Greenspan (2018) applied DCGAN to generate synthetic medical images and proposed a training scheme by adding synthetic images. The classification performance with synthetic data augmentation outperformed the classical augmentation method with 7% improvement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep leaf‐bootstrapping generative adversarial network for structural image data augmentation

Gao

Kong

Mosalam

2019

Computer aided Civil Eng

109

View full text Add to dashboard Cite

Employing Deep Learning (DL) technologies to solve Civil Engineering problems is an emerging topic in recent years. However, due to the lack of labeled data, it is difficult to obtain accurate results with DL. One commonly used method to tackle this issue is to use affine transformation to augment the data set, but it can only generate new images that are highly correlated with the original ones. Moreover, unlike normal natural objects, distribution of structural images is much more complex and mixed. To address these challenges, Generative Adversarial Network (GAN) can be one feasible choice. We introduce one specific generative model, namely, Deep Convolutional Generative Adversarial Network (DCGAN) and propose a Leaf‐Bootstrapping (LB) method to improve the performance of this DCGAN. To effectively and quantitatively evaluate the quality of the synthetic images generated by DCGAN to complement human evaluation, Self‐Inception Score (SIS) and Generalization Ability (GA) are proposed. We also propose a pipeline based on Transfer Learning (TL) using synthetic images to help enhance a weak classifier performance under the condition of low‐data regime and limited computational resources. Finally, we conduct computer experiments with the proposed methods for two scenarios (scene level identification and damage state check) and one special synthetic data aggregation case. The results demonstrate the effectiveness and robustness of the proposed methods.

show abstract

Section: Synthetic Data Aggregation and Fine-tuningmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Deep leaf‐bootstrapping generative adversarial network for structural image data augmentation

Gao

Kong

Mosalam

2019

Computer aided Civil Eng

109

View full text Add to dashboard Cite

show abstract

“…Mok et al [55] reported that a PGGAN-based augmentation improved the dice coefficient of segmentation of a brain tumor by 0.03 (0.81 → 0.84) over a traditional augmentation approach. Frid-Adar et al [56] reported that a DCGAN-based augmentation improved the classification of a liver lesion by 7.1% (78.6% → 85.7%) in sensitivity and 4.0% (88.4% → 92.4%) in specifity over a traditional augmentation approach.…”

Section: Unconditional Synthesismentioning

confidence: 99%

Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging

Kaji

Kida²

2019

Radiol Phys Technol

119

View full text Add to dashboard Cite

Since the advent of deep convolutional neural networks (DNNs), computer vision has seen an extremely rapid progress that has led to huge advances in medical imaging. Every year, many new methods are reported of in conferences such as the International Conference on Medical Image Computing and Computer Assisted Intervention (MIC-CAI) and Machine Learning for Medical Image Reconstruction (MLMIR), or published online at the preprint server arXiv. There is a plethora of surveys on applications of neural networks in medical imaging (see [1] for a relatively recent comprehensive survey). This article does not aim to cover all aspects of the field but focuses on a particular topic, image-to-image translation. Although the topic may not sound familiar, it turns out that many seemingly irrelevant applications can be understood as instances of image-to-image translation. Such applications include (1) noise reduction, (2) super-resolution, (3) image synthesis, and (4) reconstruction. The same underlying principles and algorithms work for various tasks. Our aim is to introduce some of the key ideas on this topic from a uniform point of view. We introduce core ideas and jargon that are specific to image processing by use of DNNs. Having an intuitive grasp of the core ideas of and a knowledge of technical terms would be of great help to the reader for understanding the existing and future applications.Most of the recent applications which build on imageto-image translation are based on one of two fundamental The two authors contributed equally to this work.

show abstract

“…In [12], a SVM model was used for feature selection in gait classification of leg length and distal mass. A discussion on synthetic data augmentation using generative adversarial networks for improved liver classification is provided in [13].…”

Section: Related Workmentioning

confidence: 99%

Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks

Doshi¹

2019

State Recognition Symposium

View full text Add to dashboard Cite

Object detection and recognition has been an ongoing research topic for a long time in the field of computer vision. Even in robotics, detecting the state of an object by a robot still remains a challenging task. Also, collecting data for each possible state is also not feasible. In this literature, we use a deep convolutional neural network with SVM as a classifier to help with recognizing the state of a cooking object. We also study how a generative adversarial network can be used for synthetic data augmentation and improving the classification accuracy. The main motivation behind this work is to estimate how well a robot could recognize the current state of an object.

show abstract

Synthetic data augmentation using GAN for improved liver lesion classification

Cited by 591 publications

References 12 publications

Deep leaf‐bootstrapping generative adversarial network for structural image data augmentation

Deep leaf‐bootstrapping generative adversarial network for structural image data augmentation

Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging

Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks

Contact Info

Product

Resources

About