Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks

By Hoo-Chang Shin, Neil A. Tenenholtz, Jameson K. Rogers, C. Schwarz, Matthew L. Senjem, Jeffrey L. Gunter, Katherine P. Andriole, Mark H. Michalski. 2018

676 citations recorded by the source corpus.

Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a generative adversarial network using two publicly available data sets of brain MRI. We demonstrate two unique benefits that the synthetic images provide. First, we illustrate improved performance on tumor segmentation by leveraging the synthetic images as a form of data augmentation. Second, we demonstrate the value of generative models as an anonymization tool, achieving comparable tumor segmentation results when trained on the synthetic data versus when trained on real subject data. Together, these results offer a potential solution to two of the largest challenges facing machine learning in medical imaging, namely the small incidence of pathological findings, and the restrictions around sharing of patient data.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

1. Tao Lei
2. Ling Shao
3. Ertunç Erdil
4. L. Xing
5. Angela Zhang
6. James Y. Zou
7. Asoke Kumar Nandi
8. Jianbing Shen

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Jianbing Shen
3. Huan Fu
4. Tao Zhou
5. Wenguan Wang
6. Deng-Ping Fan
7. Geng Chen
8. Tao Lei

Citations in the corpus

• Enhancing Performance of Deep Learning Models with different Data Augmentation Techniques: A Survey (2020, methodology): “A method is proposed by [15] used generative adversarial network to train the synthetic MRI images with brain tumors.”
• Medical Image Segmentation Using Deep Learning: A Survey (2020, result): “In addition, there are also some other works [105] [106] using GAN or cGAN to generate images to achieve data enhancement.”
• A review of medical image data augmentation techniques for deep learning applications (2021, methodology): “The DL-based methods can augment image data across different imaging modalities and sequences, and with anatomical variance (e.g. change of size, shape and location of tumours), 86,119,144,145,152 – 154 , 157 which conventional augmentation methods generally do not account”
• Contrastive learning of global and local features for medical image segmentation with limited annotations (2020, methodology): “r medical image analyses in limited label 2 settings. Augmentation through random affine [13], elastic [49] and contrast transformations [29, 47], Mixup [62, 19] and synthetic data generation via GANs [22, 15, 52, 8] have been explored. Recent works also leveraged unlabeled data for augmentation eith”
• Shifting machine learning for healthcare from development to deployment and from models to data (2022, methodology): “…simulate the full spectrum of clinical scenarios and disease presentations, from dangerous and rare clinical scenarios such as incorrect surgery techniques 63 , to modelling the spectrum of brain-tumour presentation 19 , to exploring the disease progression of neurodegenerative diseases 65,66 .”
• Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis (2020, background): “Moreover, data with high-class imbalance or insufficient variability [55] often results in poor classification performance.”
• Manipulating Medical Image Translation with Manifold Disentanglement (2020, background): “For example, segmentation map to medical image [20], [21], MR reconstruction [22], [23], image denoising [24], [25] and cross-modality translation [26], [27], [28].”