[张贴报告]A Preliminary Study on Unsupervised Low-DoseCT Denoising Based on Bayesian Neural Network - 报告详情

A Preliminary Study on Unsupervised Low-DoseCT Denoising Based on Bayesian Neural Network
编号:76 稿件编号:58 访问权限:仅限参会人 更新:2021-10-30 18:53:13 浏览:524次 张贴报告

报告开始:2021年11月14日 22:05 (Asia/Shanghai)

报告时间:25min

所在会议:[PS1] Plenary Session 1 [CT1] Workshop on CT

视频 无权播放 演示文件

提示:该报告下的文件权限为仅限参会人,您尚未登录,暂时无法查看。

摘要
Low-dose computed tomography(CT) has attraced more attention due to its prevalence and advantages in reducing the potential radiation risk, while suffering from increased noise. In this paper, we propose an unsupervised low-dose CT denoising method based on Bayesian Neural Network(BNN) to enhance low-dose CT image quality. Different from supervised deep learning, this work only needs a single image, and not requiring massive label data sets for training. On the other hand, all weights in BNN are random variables represented by certain probability distributions, instead of a fixed value in the ordinary neural network. The results on simulated CT data show that the method captures the statistical characteristics of image structure better than the other methods in the sense of structural similarity.

 
关键字
Keywords—low-dose CT, denoising, unsupervised deep learning, Bayesian Neural Network.
报告人
jie guo
Information Engineering University;

稿件作者
jie guo Information Engineering University;
Ailong Cai IEU
Xiaohuan Yu Information Engineering University
Yizhong Wang Information Engineering University
libin hou Information Engineering University;
Bin Yan Information Engineering University
发表评论
验证码 看不清楚,更换一张
全部评论

倒计时

  • 00

  • 00

  • 00

  • 00

重要日期

摘要提交日期:

2021/08/31

2021/10/25

全文投稿日期:  

2021/09/15

2021/10/25

录取通知日期: 

2021/09/30

2021/11/01

会议日期:   2021-11-12-2021-11-14

联系我们

杨巾英 13675518597
智德波 15056085235
高嵩 13121880288
曹乐 15910809908
会议邮箱: icmipe2021@ustc.edu.cn