[1]商奥雪,王 玉,王明泉,等.基于局部归一化互信息联合约束的三维头颈部 CT / MR 配准方法[J].机械与电子,2024,42(03):3-7.
　SHANG Aoxue,WANG Yu,WANG Mingquan,et al.3D Head and Neck CT / MR Registration Method Based on Local Normalized Mutual Information Joint Constraint[J].Machinery & Electronics,2024,42(03):3-7.
点击复制

基于局部归一化互信息联合约束的三维头颈部 CT / MR 配准方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年03期
页码:
3-7
栏目:
设计与研究
出版日期:
2024-03-25

文章信息/Info

Title:
3D Head and Neck CT / MR Registration Method Based on Local Normalized Mutual Information Joint Constraint
文章编号:
1001-2257 ( 2024 ) 03-0003-05
作者:
商奥雪; 王 玉; 王明泉; 贾 虎; 成向北; 李文波
中北大学信息与通信工程学院,山西 太原 030051
Author(s):
SHANG Aoxue ;  WANG Yu ;  WANG Mingquan ;  JIA Hu ;  CHENG Xiangbei ;  LI Wenbo
( School of Information and Communication Engineering , North University of China , Taiyuan 030051 , China )
关键词:
非刚性配准; 互信息; F 范数正则化; 归一化; 多模态配准
Keywords:
non-rigid registration ;  mutual information ;  F norm regularization ;  normalized mutual information ;  multi modal registration
分类号:
TP391.4
文献标志码:
A
摘要:
针对头颈部图像的复杂解剖结构和不同模态图像的差异,提出一种改进的多模态配准方法。该方法采用局部归一化互信息作为相似性测度,以捕捉局部图像区域的相似性,并减少不同区域间的强度差异对配准结果的影响。此外,为解决 MR 图像易受到噪声和伪影的影响产生畸变的问题,引入 F 范数约束配准过程,抑制不必要的畸变。实验结果表明,所提方法在降低均方误差、提高配准精度和鲁棒性方面均有所提高。
Abstract:
An improved multimodal registration method is proposed for the complex anatomical structure of head and neck images and the differences of different modal images.This method uses local normalized mutual information as a similarity measure to capture the similarity of local image regions and reduce the influence of intensity differences between different regions on the registration results.In addition , in order to solve the problem that MR images are susceptible to distortion caused by noise and artifacts , we introduce an F norm constrained registration process to suppress unnecessary distortion.Experimental results show that the proposed method improves the mean squared error , the registration accuracy and robustness.

参考文献/References:

[ 1 ] 陈菲,叶浩锋 . 基于互信息的胸腹部多模态图像配准[ J ] . 电脑知识与技术, 2021 , 17 ( 19 ): 143-144.

[ 2 ] 王雨婕,李志勇 . 颞下颌关节多模态图像配准及三维重建的研究进展 [ J ] . 口腔医学杂志, 2022 , 23 ( 2 ):147-152.
[ 3 ] 郑佳敏 . 面向精准医疗的智能医学图像配准方法研究及应用[ D ] . 无锡:江南大学,2021.
[ 4 ] HUANG X S , ZHANG F.Multi-modal medical image registration based on gradient of mutual information and morphological Haar wavelet [ C ]// 2010 International Conference on e-Education , e-Business , e-Management and e-Learning.New York : IEEE , 2010 :39-42.
[ 5 ] 李靖宇,沈焕泉,程燕,等 . 基于最大互信息的医学图像配准算法 [ J ]中国介入影像与治疗学,2010 , 7 ( 3 ):325-327.
[ 6 ] 魏本征,甘洁,尹义龙 . 基于边缘特征点互信息熵的医学图像配准方法[ J ] . 数据采集与处理,2018 , 33 ( 2 ):248-258.
[ 7 ] 张莉,李彬,田联房,等 . 基于局部结构张量 互信息的多模态图像配准[ J ] . 华南理工大学学报(自然科学版),2017 , 45 ( 7 ): 98-106.
[ 8 ] 张驰 . 基于 B 样条和互信息的多模态医学图像非刚性配准方法研究[ D ] . 杭州:浙江工业大学,2019.
[ 9 ] LOECKX D , SLAGMOLEN P , MAES F , et al.Nonrigid image registration using conditional mutual information. [ J ] .IEEE Transactions on medical imaging ,2009 , 29 ( 1 ): 19-29.
[ 10 ] 杨志杰,于明,张海哲 . 归一化互信息配准[ J ] . 计算机 与信息技术,2005 ( 6 ): 18-20 , 22.
[ 11 ] AVANTS B B , EPSTEIN C L , GROSSMAN M , et al.Symmetric diffeomorphic image registration with cross-correlation : evaluating automated labeling of elderly and neurodegenerative brain [ J ] .Medical image analysis , 2008 , 12 ( 1 ): 26-41.
[ 12 ] KLEIN S , STARING M , MURPHY K , et al.Elastix : a toolbox for intensity-based medical image registration [ J ] .IEEE Transactions on medical imaging ,2010 , 29 ( 1 ): 196-205.
[ 13 ] ROGELJ P , EL-HAJJ-CHEHADE W.Multi-modality non-rigid image registration using local similarity estimations [ J ] .International journal of uncertainty , fuzziness and knowledge-based systems ,2021 , 29 ( S1 ): 31-50.
[ 14 ] 赵帅,吕晓琪 . 基于局部互信息和自动更新的医学图像形变不均匀配准[ J ] . 中国医学物理学杂志, 2017 ,34 ( 8 ): 806-810.
[ 15 ] 汪军,梁凤梅 . 基于 P 样条和局部互信息的非刚性医学图像配准 [ J ] . 计算机应用研究,2017 , 34 ( 8 ):2538-2541.
[ 16 ] XU Y , PENG L , LI G Y.Multi modal registration of structural features and mutual information of medical image [ J ] .Future generation computer systems , 2019 , 93 : 499-505.
[ 17 ] VAKIL M I , MEGHERBI D B , MALAS J? A.A robust multi-stage information-theoretic approach for registration of partially overlapped hyperspectral aerial imagery and evaluation in the presence of system noise [ J ] .Signal processing : image communication , 2017 , 52 : 97-110.
[ 18 ] PODOBNIK G , STROJAN P , PETERLIN P , et al . HaN-Seg : the head and neck organ-at-risk CT and MR segmentation dataset [ J ] .Medical physics , 2023 , 50 ( 3 ): 1917-1927.
[ 19 ] LEIBFARTH S , M?NNICH D , WELZ S , et al.A strategy for multimodal deformable image registration to integrate PET / MR into radiotherapy treatment planning [ J ] .Acta oncologica , 2013 , 52 ( 7 ): 1353-1359.

备注/Memo

备注/Memo:
收稿日期: 2023-08-31
基金项目:山西省重点研发计划资助项目( 201803D121069 );山西省应用基础研究项目面上自然基金资助项目( 201801D121162 )
作者简介:商奥雪 ( 1999- ),女,硕士研究生,研究方向为图像处理、图像配准;王 玉 ( 1979- ),女,博士,副教授,硕士研究生导师,研究方向为图像处理、图像配准,通信作者。
更新日期/Last Update: 2024-03-22