[1]黄霞,许乙凯,张煜.基于卷积神经网络的宫颈CT图像的金属伪影去除[J].中国医学物理学杂志,2022,39(12):1466-1472.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.003]
　HUANG Xia,XU Yikai,ZHANG Yu,et al.Metal artifact reduction in cervical CT images using convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(12):1466-1472.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.003]
点击复制

基于卷积神经网络的宫颈CT图像的金属伪影去除()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第12期
页码:
1466-1472
栏目:
医学影像物理
出版日期:
2022-12-25

文章信息/Info

Title:
Metal artifact reduction in cervical CT images using convolutional neural network
文章编号:
1005-202X（2022）12-1466-07
作者:
黄霞1; 许乙凯1; 张煜2; 3
1.南方医科大学南方医院影像中心， 广东 广州 510515； 2.南方医科大学生物医学工程学院， 广东 广州 510515； 3.广东省医学图像处理重点实验室， 广东 广州 510515
Author(s):
HUANG Xia1;  XU Yikai1;  ZHANG Yu2;  3
1. Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China 2. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China 3. Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China
关键词:
金属伪影; 数据仿真; 卷积神经网络; 宫颈CT图像
Keywords:
Keywords: metal artifact data simulation convolutional neural network cervical CT image
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2022.12.003
文献标志码:
A
摘要:
目的：为了消除宫颈CT图像中存在的金属伪影，提出一种利用卷积神经网络（CNN）去除金属伪影的策略。方法：首先通过数值仿真得到金属伪影图像与目标图像（无伪影图像），构造训练测试数据集，利用含金属伪影的宫颈CT图像和对应的无伪影图像训练已搭建的CNN，进而得到去除宫颈CT图像金属伪影的CNN模型。结果：训练网络之前金属伪影图像与目标图像峰值信噪比（PSNR）平均值为26.098 0 dB。不同尺寸（25×25、50×50、100×100）的图像块训练网络得到去除金属伪影的图像与目标图像PSNR平均值分别为34.607 9、38.375 1、38.183 8 dB。结论：通过对仿真数据和临床数据进行实验，研究结果表明，本文方法能够快速有效地消除宫颈CT图像中的金属伪影，并且可以保留完整的组织结构信息。
Abstract:
Abstract: Objective To reduce metal artifacts in cervical CT images using convolutional neural network. Methods The metal artifact images and the target images (artifact-free images) were generated using numerical simulation for constructing training and test data sets. The cervical CT images with metal artifacts and paired cervical CT images without metal artifacts were input into the constructed convolutional neural network for training, and then a convolutional neural network model for metal artifact reduction in cervical CT images was obtained. Results Before network training, the average peak signal-to-noise ratio (PSNR) of the metal artifact images and the target images was 26.098 0 dB. The average PSNR of the metal artifact reduction images and the target images obtained by the training network trained by image patches of different sizes (25×25, 50×50, 100×100) was 34.607 9, 38.375 1, and 38.183 8 dB, respectively. Conclusion Through experiments on simulation data and clinical data, it is revealed that the proposed method can effectively reduce metal artifacts and can retain relatively complete tissue texture information in cervical CT images.

相似文献/References:

[1]骆众星,石健强,谢斯栋,等.T1 FLAIR PROPELLER序列在3.0T磁共振颅脑增强成像上对抑制各种伪影的应用[J].中国医学物理学杂志,2015,32(06):878.[doi:doi:10.3969/j.issn.1005-202X.2015.06.025]
　[J].Chinese Journal of Medical Physics,2015,32(12):878.[doi:doi:10.3969/j.issn.1005-202X.2015.06.025]
[2]宋威,鹿红,马珺,等.金属伪影对鼻咽癌放疗危及器官自动勾画的影响[J].中国医学物理学杂志,2021,38(10):1185.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.001]
　SONG Wei,LU Hong,MA Jun,et al.Effects of metal artifacts on automatic segmentation of organs-at-risk in patients receiving radiotherapy for nasopharyngeal carcinoma[J].Chinese Journal of Medical Physics,2021,38(12):1185.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.001]

备注/Memo

备注/Memo:
【收稿日期】2022-06-17 【基金项目】国家自然科学基金（61971213） 【作者简介】黄霞，硕士研究生，助理工程师，E-mail: 983956235@qq.com 【通信作者】张煜，教授，博士，博士生导师，E-mail: yuzhang@smu.edu.cn
更新日期/Last Update: 2022-12-23