Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks

被引:68
|
作者
Kwon, Gihyun [1 ]
Han, Chihye [1 ]
Kim, Dae-shik [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea
基金
新加坡国家研究基金会;
关键词
Generative Adversarial Networks; MRI; Data augmentation; 3D; Image synthesis;
D O I
10.1007/978-3-030-32248-9_14
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
As deep learning is showing unprecedented success in medical image analysis tasks, the lack of sufficient medical data is emerging as a critical problem. While recent attempts to solve the limited data problem using Generative Adversarial Networks (GAN) have been successful in generating realistic images with diversity, most of them are based on image-to-image translation and thus require extensive datasets from different domains. Here, we propose a novel model that can successfully generate 3D brain MRI data from random vectors by learning the data distribution. Our 3D GAN model solves both image blurriness and mode collapse problems by leveraging alpha-GAN that combines the advantages of Variational Auto-Encoder (VAE) and GAN with an additional code discriminator network. We also use the Wasserstein GAN with Gradient Penalty (WGAN-GP) loss to lower the training instability. To demonstrate the effectiveness of our model, we generate new images of normal brain MRI and show that our model outperforms baseline models in both quantitative and qualitative measurements. We also train the model to synthesize brain disorder MRI data to demonstrate the wide applicability of our model. Our results suggest that the proposed model can successfully generate various types and modalities of 3D whole brain volumes from a small set of training data.
引用
收藏
页码:118 / 126
页数:9
相关论文
共 50 条
  • [21] 3D Model Generation and Reconstruction Using Conditional Generative Adversarial Network
    Haisheng Li
    Yanping Zheng
    Xiaoqun Wu
    Qiang Cai
    International Journal of Computational Intelligence Systems, 2019, 12 : 697 - 705
  • [22] 3D microstructural generation from 2D images of cement paste using generative adversarial networks
    Zhao, Xin
    Wang, Lin
    Li, Qinfei
    Chen, Heng
    Liu, Shuangrong
    Hou, Pengkun
    Ye, Jiayuan
    Pei, Yan
    Wu, Xu
    Yuan, Jianfeng
    Gao, Haozhong
    Yang, Bo
    CEMENT AND CONCRETE RESEARCH, 2025, 187
  • [23] Tooth Segmentation of 3D Scan Data Using Generative Adversarial Networks
    Kim, Taeksoo
    Cho, Youngmok
    Kim, Doojun
    Chang, Minho
    Kim, Yoon-Ji
    APPLIED SCIENCES-BASEL, 2020, 10 (02):
  • [24] Automatic Video Colorization Using 3D Conditional Generative Adversarial Networks
    Kouzouglidis, Panagiotis
    Sfikas, Giorgos
    Nikou, Christophoros
    ADVANCES IN VISUAL COMPUTING, ISVC 2019, PT I, 2020, 11844 : 209 - 218
  • [25] Brain Magnetic Resonance Imaging Generation using Generative Adversarial Networks
    Alogna, Emanuel
    Giacomello, Edoardo
    Loiacono, Daniele
    2020 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2020, : 2528 - 2535
  • [26] 3D Human Pose Estimation With Generative Adversarial Networks
    Xia, Hailun
    Xiao, Meng
    IEEE ACCESS, 2020, 8 : 206198 - 206206
  • [27] GENERATIVE ADVERSARIAL NETWORKS FOR SINGLE PHOTO 3D RECONSTRUCTION
    Kniaz, V. V.
    Remondino, F.
    Knyaz, V. A.
    8TH INTERNATIONAL WORKSHOP 3D-ARCH: 3D VIRTUAL RECONSTRUCTION AND VISUALIZATION OF COMPLEX ARCHITECTURES, 2019, 42-2 (W9): : 403 - 408
  • [28] 3D Isotropic Super-resolution Prostate MRI Using Generative Adversarial Networks and Unpaired Multiplane Slices
    Liu, Yucheng
    Liu, Yulin
    Vanguri, Rami
    Litwiller, Daniel
    Liu, Michael
    Hsu, Hao-Yun
    Ha, Richard
    Shaish, Hiram
    Jambawalikar, Sachin
    JOURNAL OF DIGITAL IMAGING, 2021, 34 (05) : 1199 - 1208
  • [29] 3D Isotropic Super-resolution Prostate MRI Using Generative Adversarial Networks and Unpaired Multiplane Slices
    Yucheng Liu
    Yulin Liu
    Rami Vanguri
    Daniel Litwiller
    Michael Liu
    Hao-Yun Hsu
    Richard Ha
    Hiram Shaish
    Sachin Jambawalikar
    Journal of Digital Imaging, 2021, 34 : 1199 - 1208
  • [30] Artificial Intelligence Choreography: 3D Dance Generation Based on Deep Generative Adversarial Networks
    Li, Kai
    Santos, Elena
    Journal of Network Intelligence, 2024, 9 (03): : 1725 - 1741