Synthetic data augmentation using GAN for improved liver lesion classification
By Maayan Frid-Adar, Eyal Klang, Michal Marianne Amitai, Jacob Goldberger, Hayit Greenspan. 2018
847 citations recorded by the source corpus.
In this paper, we present a data augmentation method that generates synthetic medical images using Generative Adversarial Networks (GANs). We propose a training scheme that first uses classical data augmentation to enlarge the training set and then further enlarges the data size and its diversity by applying GAN techniques for synthetic data augmentation. Our method is demonstrated on a limited dataset of computed tomography (CT) images of 182 liver lesions (53 cysts, 64 metastases and 65 hemangiomas). The classification performance using only classic data augmentation yielded 78.6% sensitivity and 88.4% specificity. By adding the synthetic data augmentation the results significantly increased to 85.7% sensitivity and 92.4% specificity.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Medical Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Trevor Darrell
- Yoshua Bengio
- Dacheng Tao
- Pieter Abbeel
- Bernt Schiele
- Cordelia Schmid
- Mohit Bansal
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Andrew Zisserman
- Trevor Darrell
- Andrea Vedaldi
- Jitendra Malik
In Generative Models
- Richard Zhang
- Jun-Yan Zhu
- Eli Shechtman
- Phillip Isola
- Alexei A. Efros
- Stefano Ermon
- Mario Fritz
- Dong Chen
In Medical Imaging
- Xiaosong Wang
- Ronald M. Summers
- Arvid Lundervold
- Nassir Navab
- Daniel Rueckert
- Dan Boneh
- Florian Tramèr
Citations in the corpus
- Adversarial AutoAugment (2019, methodology): “, 2014), which has recently attracted lots of research attention due to its fascinating performance, and also been used to enlarge datasets through directly synthesizing new images (Tran et al., 2017; Perez & Wang, 2017; Antoniou et al., 2017; Gurumurthy et al., 2017; Frid-Adar et al., 2018).”
- Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules (2019, background): “Augmentation has been shown to have a large impact on image modalities where data is scare or expensive to generate, like medical imaging (Bowles et al., 2018; Frid-Adar et al., 2018) or non-supervised learning approaches (Mundhenk et al., 2017).”
- GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks (2018, background): “It also suggests that when used together they are potentially synergistic, an observation which agrees with the results in [5].”
- An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “Other applications are unsupervised synthesis of T1weighted brain MRI using a GAN [179]; image synthesis with context-aware GANs [216]; synthesis of patientspecific transmission image for PET attenuation correction in PET/MR imaging of the brain using a CNN [217]; pseudo-CT synthesis for pelvis PET/”
- Modeling Visual Context is Key to Augmenting Object Detection Datasets (2018, background): “If varies from trivial geometrical transformations such as horizontal flipping, cropping with color perturbations, and adding noise to an image [27], to synthesizing new training images [28,29].”
- Regularizing Generative Adversarial Networks under Limited Data (2021, neutral): “The GAN models are the corner-stone techniques for numerous vision applications, such as data augmentation [12, 13], domain adaptation [19, 20], image extrapolation [10, 66], image-to-image translation [22, 37, 86], and visual content creation [1, 4, 21, 23, 70, 72].”
- Data Augmentation Using GANs (2019, methodology): “Regarding the two applications addressed in this work (balancing data and generating synthetic data sets), there is some previous work in the literature using GANs, such as Mariani et al. (2018), Springenberg (2015) and Frid-Adar et al. (2018)).”
- Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection (2022, background): “Moreover, different from previous works that use adversarial training to enlarge datasets through directly synthesizing new images [46, 37, 4, 18, 16], Zhang et al.”
- Ensembling with Deep Generative Views (2021, background): “Specifically in the medical community, synthesizing additional images to augment limited-size datasets has been beneficial for classification [40, 60, 17, 22, 48] or segmentation tasks [32, 11, 20].”
- A Comprehensive Survey of Image Augmentation Techniques for Deep Learning (2022, background): “Model-based Unconditional DCGAN [41], [42, 43, 44] Label-conditional BDA [45], ImbCGAN [46], BAGAN [47], DAGAN [48], MFC-GAN [49], IDA-GAN [50].”