ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Learning low-dose CT degradation from unpaired data with flow-based model

Liu, Xuan; Liang, Xiaokun; Deng, Lei; Tan, Shan*; Xie, Yaoqin*华中科技大学; 中国科学院深圳先进技术研究院; 中国科学院
Medical Physics2022-12DOI: 10.1002/mp.15886
7被引5阅读
引用收藏
分享

摘要

Background There has been growing interest in low-dose computed tomography (LDCT) for reducing the X-ray radiation to patients. However, LDCT always suffers from complex noise in reconstructed images. Although deep learning-based methods have shown their strong performance in LDCT denoising, most of them require a large number of paired training data of normal-dose CT (NDCT) images and LDCT images, which are hard to acquire in the clinic. Lack of paired training data significantly undermines the practicability of supervised deep learning-based methods. To alleviate this problem, unsupervised or weakly supervised deep learning-based methods are required. Purpose We aimed to propose a method that achieves LDCT denoising without training pairs. Specifically, we first trained a neural network in a weakly supervised manner to simulate LDCT images from NDCT images. Then, simulated training pairs could be used for supervised deep denoising networks. Methods We proposed a weakly supervised method to learn the degradation of LDCT from unpaired LDCT and NDCT images. Concretely, LDCT and normal-dose images were fed into one shared flow-based model and projected to the latent space. Then, the degradation between low-dose and normal-dose images was modeled in the latent space. Finally, the model was trained by minimizing the negative log-likelihood loss with no requirement of paired training data. After training, an NDCT image can be input to the trained flow-based model to generate the corresponding LDCT image. The simulated image pairs of NDCT and LDCT can be further used to train supervised denoising neural networks for test. Results Our method achieved much better performance on LDCT image simulation compared with the most widely used image-to-image translation method, CycleGAN, according to the radial noise power spectrum. The simulated image pairs could be used for any supervised LDCT denoising neural networks. We validated the effectiveness of our generated image pairs on a classic convolutional neural network, REDCNN, and a novel transformer-based model, TransCT. Our method achieved mean peak signal-to-noise ratio (PSNR) of 24.43dB, mean structural similarity (SSIM) of 0.785 on an abdomen CT dataset, mean PSNR of 33.88dB, mean SSIM of 0.797 on a chest CT dataset, which outperformed several traditional CT denoising methods, the same network trained by CycleGAN-generated data, and a novel transfer learning method. Besides, our method was on par with the supervised networks in terms of visual effects. Conclusion We proposed a flow-based method to learn LDCT degradation from only unpaired training data. It achieved impressive performance on LDCT synthesis. Next, we could train neural networks with the generated paired data for LDCT denoising. The denoising results are better than traditional and weakly supervised methods, comparable to supervised deep learning methods.

学科与关键词

关键词
computed tomographyflow-based modelnoise synthesisweakly supervised learning
相关
加载中…
  • Noise2Context: Context-assisted learning 3D thin-layer for low-dose CT
    Zhang, Zhicheng; Liang, Xiaokun; Zhao, Wei*; Xing, Lei*Medical Physics, 2021, 48(10): 5794-5803.被引 16
  • Cross-Domain Unpaired Learning for Low-Dose CT Imaging
    Liu, Yang; Chen, Gaofeng; Pang, Shumao; Zeng, Dong; Ding, Youde; Xie, Guoxi; Ma, Jianhua; He, Ji*IEEE Journal of Biomedical and Health Informatics, 2023, 27(11): 5471-5482.被引 1
  • A dataset-free deep learning method for low-dose CT image reconstruction
    Ding, Qiaoqiao; Ji, Hui; Quan, Yuhui; Zhang, Xiaoqun*Inverse Problems, 2022, 38(10): 104003.
查看全部 →

发表信息

论文状态
公开发表
期刊
Medical Physics
发表日期
2022-12
卷期
第 49 卷, 第 12 期
页码
7516-7530
DOI
10.1002/mp.15886
语言
ENGLISH
期刊等级
3区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [U20A20373, 61871374, 62071197]; Chinese Academy of Sciences Special Research Assistant Grant Program; Young S&T Talent Training Program of Guangdong Provincial Association for ST [SKXRC202224]

作者

  • L

    Liu, Xuan (第一作者)

    huazhong univ sci & technol

  • L

    Liang, Xiaokun

    chinese acad sci · shenzhen inst adv technol

查看全部 5 位作者收起作者
  • D

    Deng, Lei

    chinese acad sci · shenzhen inst adv technol

  • T

    Tan, Shan (通讯)

    huazhong univ sci & technol

  • X

    Xie, Yaoqin (通讯)

    chinese acad sci · shenzhen inst adv technol

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417