[1]董国亚,宋立明,李雅芬,等.基于深度学习的跨模态医学图像转换[J].中国医学物理学杂志,2020,37(10):1335-1339.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.021]
 DONG Guoya,SONG Liming,et al.Cross-modality medical image synthesis based on deep learning[J].Chinese Journal of Medical Physics,2020,37(10):1335-1339.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.021]
点击复制

基于深度学习的跨模态医学图像转换()
分享到:

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

卷:
37
期数:
2020年第10期
页码:
1335-1339
栏目:
医学人工智能
出版日期:
2020-10-29

文章信息/Info

Title:
Cross-modality medical image synthesis based on deep learning
文章编号:
1005-202X(2020)10-1335-05
作者:
董国亚12宋立明123李雅芬3李文3谢耀钦3
1.省部共建电工装备可靠性与智能化国家重点实验室(河北工业大学), 天津 300132; 2.河北省电磁场与电器可靠性重点实验室(河北工业大学), 天津 300132; 3.中国科学院深圳先进技术研究院, 广东 深圳 440305
Author(s):
DONG Guoya1 2 SONG Liming1 2 3 LI Yafen3 LI Wen3 XIE Yaoqin3
1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300132, China 2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin 300132, China 3. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 440305, China
关键词:
深度学习CTMRIU-Net卷积神经网络图像模态转换合成MRI
Keywords:
Keywords: deep learning computed tomography magnetic resonance imaging U-Net convolutional neural network cross-modality image synthesis synthetic magnetic resonance imaging
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2020.10.021
文献标志码:
A
摘要:
运用深度学习的方法基于脑部CT扫描图像合成相应的MRI。将28例患者进行颅脑CT和MRI扫描得到的CT和MRI的断层图像进行刚性配准,随机选取20例患者的图像输入U-Net卷积神经网络进行训练,利用训练好的网络对未参与训练的8例患者的CT图像进行预测,得到合成的MRI。研究结果显示:通过对合成的MRI进行定量分析,利用基于L2损失函数构建的U-Net网络合成MRI效果良好,平均绝对平均误差(MAE)为47.81,平均结构相似性指数(SSIM)为0.91。本研究表明可以利用深度学习方法对CT图像进行转换,获得合成MRI,现阶段可以达到扩充MRI医学图像数据库的目的,随着合成图像精度的提高,可以用于帮助诊断等临床应用。
Abstract:
Abstract: The purpose of this research is to synthesize the corresponding magnetic resonance imaging (MRI) based on brain computed tomography (CT) images by deep learning. The tomographic images of CT and MRI obtained by brain CT and MRI scanning are rigidly registered in 28 patients, and the images of 20 patients are randomly input into U-Net convolutional neural network for training. The CT images of 8 patients who do not participate in the training are predicted by the trained network, thereby obtaining the synthetic MRI. The results reveal that through the quantitative analysis on synthetic MRI, the U-Net network constructed based on L2 loss function has a good performance in synthesizing MRI, with a mean absolute error of 47.81 and an average structural similarity index of 0.91. This study shows that deep learning method can be used to obtain synthetic MRI by converting CT images, thus achieving the purpose of expanding MRI medical database. With the improvement of the accuracy of image synthesis, it can be used in diagnosis and other clinical applications.

相似文献/References:

[1]庞皓文,孙小扬.基于快速自由形变的弹性配准算法在放疗CT中的应用[J].中国医学物理学杂志,2015,32(03):404.[doi:10.3969/j.issn.1005-202X.2015.03.023]
[2]梁 健.64排螺旋CT结肠成像技术诊断结直肠疾病的有效性分析[J].中国医学物理学杂志,2015,32(03):447.[doi:10.3969/j.issn.1005-202X.2015.03.033]
[3]程明渊,贺奇才,胡琴明,等.基于穿越长度权重迭代重建算法的研究[J].中国医学物理学杂志,2013,30(02):4012.[doi:10.3969/j.issn.1005-202X.2013.02.012]
[4]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
 [J].Chinese Journal of Medical Physics,2017,34(10):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[5]靳珍怡,王远军,聂生东. 梯度域三维头部PETCT图像融合[J].中国医学物理学杂志,2017,34(3):246.[doi:10.3969/j.issn.1005-202X.2017.03.006]
 [J].Chinese Journal of Medical Physics,2017,34(10):246.[doi:10.3969/j.issn.1005-202X.2017.03.006]
[6]王朝壮,王鑫,王恩敏,等. 不同厚度CT图像重建的DRR对射波刀治疗头部肿瘤精度的影响[J].中国医学物理学杂志,2017,34(9):882.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.005]
 [J].Chinese Journal of Medical Physics,2017,34(10):882.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.005]
[7]门阔,戴建荣. 利用深度反卷积神经网络自动勾画放疗危及器官[J].中国医学物理学杂志,2018,35(3):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
 MEN Kuo,DAI Jianrong. Automatic segmentation of organs at risk in radiotherapy using deep deconvolutional neural network[J].Chinese Journal of Medical Physics,2018,35(10):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
[8]李慧君,王琳婧,周露,等. 自适应图像全变差约束的有限角度CT重建算法[J].中国医学物理学杂志,2018,35(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2018.04.010]
 LI Huijun,WANG Linjing,ZHOU Lu,et al. An adaptive total p variation-constrained CT image reconstruction method for limited angle data[J].Chinese Journal of Medical Physics,2018,35(10):420.[doi:DOI:10.3969/j.issn.1005-202X.2018.04.010]
[9]冯庆,戴敏,马华怡,等. 恶性血液系统疾病患者肝脏真菌感染的CT表现[J].中国医学物理学杂志,2018,35(5):549.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.010]
 FENG Qing,DAI Min,MA Huayi,et al. CT characteristics of hepatic fungal infections in patients with malignant hematological diseases[J].Chinese Journal of Medical Physics,2018,35(10):549.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.010]
[10]张俊,朱金汉,庄永东,等. 基于卷积神经网络CT/CBCT影像质量自动分析[J].中国医学物理学杂志,2018,35(5):557.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.012]
 ZHANG Jun,ZHU Jinhan,ZHUANG Yongdong,et al. Automatic analysis of CT/CBCT image quality based on convolutional neural network[J].Chinese Journal of Medical Physics,2018,35(10):557.[doi:DOI:10.3969/j.issn.1005-202X.2018.05.012]

备注/Memo

备注/Memo:
【收稿日期】2020-05-12 【基金项目】深圳市配套项目(GJHS20170314155751703);国家重点研发计划(2016YFC0105102);国家自然科学基金(61871374);广东省特支计划领军人才(2016TX03R139);深圳市基础研究计划(JCYJ20170413162458312);广东省自然科学基金(2017B20170413162458312, 2015B020233011, 2014A03- 0312006) 【作者简介】董国亚,博士,副教授,主要研究方向:医学信号和图像处理、神经工程,E-mail: dong_guoya@126.com 【通信作者】谢耀钦,博士,研究员,E-mail: yq.xie@siat.ac.cn
更新日期/Last Update: 2020-10-29