Synthesizing Multi-Contrast MR Images Via Novel 3D Conditional Variational Auto-Encoding GAN
- PDF / 607,484 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 206 Views
Synthesizing Multi-Contrast MR Images Via Novel 3D Conditional Variational Auto-Encoding GAN Huan Yang 1,2,3 & Xianling Lu 2,3 & Shui-Hua Wang 4 & Zhihai Lu 5 & Jian Yao 6 & Yizhang Jiang 1,2 & Pengjiang Qian 1,2 Accepted: 20 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract As two different modalities of medical images, Magnetic Resonance (MR) and Computer Tomography (CT), provide mutuallycomplementary information to doctors in clinical applications. However, to obtain both images sometimes is cost-consuming and unavailable, particularly for special populations. For example, patients with metal implants are not suitable for MR scanning. Also, it is probably infeasible to acquire multi-contrast MR images during once clinical scanning. In this context, to synthesize needed MR images for patients whose CT images are available becomes valuable. To this end, we present a novel generative network, called CAE-ACGAN, which incorporates the advantages of Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN) with an auxiliary discriminative classifier network. We apply this network to synthesize multicontrast MR images from single CT and conduct experiments on brain datasets. Our main contributions can be summarized as follows: 1)We alleviate the problems of images blurriness and mode collapse by integrating the advantages of VAE and GAN; 2) We solve the complicated cross-domain, multi-contrast MR synthesis task using the proposed network; 3) The technique of random-extraction-patches is used to lower the limit of insufficient training data, enabling to obtain promising results even with limited available data; 4) By comparing with other typical networks, we are able to yield nearer-real, higher-quality synthetic MR images, demonstrating the effectiveness and stability of our proposed network. Keywords MR synthesis . 3D . Multi-contrast . Auto-encoding . Generative adversarial network
1 Introduction First of all, to facilitate reading and understanding, we list the main abbreviations and meanings throughout this manuscript in Table 1.
* Xianling Lu [email protected] * Pengjiang Qian [email protected] 1
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
2
Jiangsu Key Laboratory of Media Design and Software Technology, Jiangnan University, Wuxi 214122, China
3
School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China
4
School of Architecture Building and Civil Engineering, Loughborough University, Loughborough LE11 3TU, UK
5
School of Educational Science, Nanjing Normal University, Nanjing 210096, China
6
Wuxi IoT Innovation Center Co., Ltd, Wuxi 214000, China
In the field of biomedicine, CT and MR are two important medical images for doctors to carry out accurate clinical diagnosis, and each has its own advantages and disadvantages. CT has a good information on attenuation but soft tissue details are limited where MR is better. Owing to the better inherent contrasts, det
Data Loading...
