[1]刘 源,王 玉,杨丽丽,等.脑部 MRI 图像配准中 CNN 与 Transformer 并行架构的算法研究[J].机械与电子,2025,(10):11-17.
　LIU Yuan,WANG Yu,YANG Lili,et al.Research on a CNN-Transformer Parallel Architecture for Brain MRI Image Registration[J].Machinery & Electronics,2025,(10):11-17.
点击复制

脑部 MRI 图像配准中 CNN 与 Transformer 并行架构的算法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年10期
页码:
11-17
栏目:
研究与设计
出版日期:
2025-10-25

文章信息/Info

Title:
Research on a CNN-Transformer Parallel Architecture for Brain MRI Image Registration
文章编号:
1001-2257 ( 2025 ) 10-0011-07
作者:
刘 源; 王 玉; 杨丽丽; 杨 洁; 张宇昊
中北大学信息与通信工程学院,山西 太原 030051
Author(s):
LIU Yuan ;  WANG Yu ;  YANG Lili ;  YANG Jie ;  ZHANG Yuhao
( School of Information and Communication Engineering , North University of China , Taiyuan 030051 , China )
关键词:
深度学习;  Transformer 架构; 图像配准; 卷积神经网络
Keywords:
deep learning ;  Transformer architecture ;  image registration ;  convolutional neural network
分类号:
TP391
文献标志码:
A
摘要:
针对当前基于深度学习的图像配准模型存在的局限性(如难以充分利用 CNN 与 Transformer 的互补优势、配准精度受限、难以有效保持原始图像的拓扑结构等问题),提出了一种无监督 CNN-Transformer 混合配准网络。所提模型选用目前配准精度最优的 Swin Transformer 和极具轻量化的 CNN 网络进行构建,并且将提取到的特征进行融合,使模型结合了 CNN 的局部特征提取能力和 Transformer 的全局建模能力,使配准更加精确和轻量化。在 2 个公开的脑 MRI 数据集( IXI 和 LPBA40 )上对该网络进行了评估。实验结果表明,所提模型配准性能较 VoxelMorph 、 Pvt 、 ViT-V-Net 和 TransMorph 在 DICE 、结构相似性等指标上有了明显提升,同时保持了基于学习方法的运行效率优势,展现出优越的配准性能。
Abstract:
To address the current limitations of deep learning based image registration models , such as the difficulty in effectively leveraging the complementary strengths of CNN and Transformers , limited registration accuracy , and challenges in preserving the topological structure of original images , we propose an unsupervised CNN Transformer hybrid registration network.The model is built using the Swin Transformer , known for its state of the art registration accuracy , and a lightweight CNN architecture. By fusing the extracted features , the model combines the local feature extraction capabilities of CNN with the global modeling strengths of Transformers , resulting in more accurate and lightweight registration.We evaluated the network on two public brain MRI datasets ( IXI and LPBA40 ) .Experimental results demonstrate that our model significantly outperforms VoxelMorph , Pvt , ViT-V-Net , andTransMorph in metrics such as DICE and structural similarity , while maintaining the efficiency advantages of learning-based methods , showcasing superior registration performance.

参考文献/References:

[ 1 ] 郭艳芬,崔喆,杨智鹏,等 . 基于深度学习的医学图像配准技术研究进展[ J ] . 计算机工程与应用, 2021 , 57 ( 15 ): 1-8.

[ 2 ] SHI J C , HE Y T , KONG Y Y , et al.Xmorpher : full Transformer for deformable medical image registrationvia cross attention [ C ] ∥Proceedings of the International Conference on Medical Image Computingand Computer-Assisted Intervention ( MICCAI ), 2022 : 217-226.
[ 3 ] SOKOOTI H , VOS B D , BERENDSEN F , et al.Nonrigid image registration using multi-scale 3D convolutional neural networks [ C ] ∥Medical Image Computing and Computer Assisted Intervention ( MICCAI ), 2017 : 232-239.
[ 4 ] MIAO S , WANG Z J , LIAO R.A CNN regression approach for real-time 2D / 3D registration [ J ] .IEEE Transactions on medical imaging , 2016 , 35 ( 5 ): 1352-1363.
[ 5 ] JI H Z , LI Y S , DONG E Q , et al.A non-rigid image registration method based on multi-level B-spline and L2-regularization [ J ] .Signal , image and video processing , 2018 , 12 : 1217-1225.
[ 6 ] KIM H , SONG W J.LAS : Locality-aware scheduling for GEMM-accelerated convolutions in GPUs [ J ] . IEEE Transactions on parallel and distributed systems , 2023 , 34 ( 5 ): 1479-1494.
[ 7 ] GHAHREMANI M , KHATERI M , JIAN B L , et al.H ViT : a hierarchical vision Transformer for deformable image registration [ C ] ∥2024 IEEE / CVF Conference on Computer Vision and Pattern Recognition ( CVPR ), 2024 : 11513-11523.
[ 8 ] ZHANG Y G , PEI Y R , ZHA H B.Learning dual Transformer network for diffeomorphic registration [ C ] ∥ Medical Image Computing and Computer Assisted Intervention ( MICCAI ), 2021 : 129-138.
[ 9 ] LIU Z , LIN Y T , CAO Y , et al.Swin Transformer : hierarchical vision transformer using shifted windows [ C ] ∥IEEE / CVF International Conference on Computer Vision ( ICCV ), 2021 : 9992-10002.
[ 10 ] LIU L H , HUANG Z N , LI? P , et al.You only look at patches : a patch-wise framework for 3D unsupervised medical image registration [ C ] ∥International Workshop on Biomedical Image Registration , 2022 : 190-193.
[ 11 ] CHEN J Y , FREY E C , HE Y F , et al.TransMorph : Transformer for unsupervised medical image registration [ J ] .Medical image analysis , 2022 , 82 : 1-34.
[ 12 ] KIM H H , YU S Z , YUAN S , et al.Cross-attention Transformer for video interpolation [ C ] ∥Proceedings of the Asian Conference on Computer Vision , 2022 : 320-337.
[ 13 ] 邹茂扬,杨昊,潘光晖,等 . 深度学习在医学图像配准上的研究进展与挑战 [ J ] . 生物医学工程学杂志,2019 , 36 ( 4 ): 677-683.
[ 14 ] HERING A , HANSEN L , MOK T C W , et al.Learn2Reg : comprehensive multi-task medical image registration challenge , dataset and evaluation in the era of deep learning [ J ] .IEEE Transactions on medical imaging , 2022 , 42 ( 3 ): 697-712.
[ 15 ] GUO M H , LIU Z N , MU T J , et al.Beyond self-attention : external attention using two linear layers for visual tasks [ J ] .IEEE Transactions on pattern analysis and machine intelligence , 2022 , 45 ( 5 ): 5436-5447.
[ 16 ] CHEN J Y , LIU Y H , HE Y F , et al.Deformable cross-attention Transformer for medical image registration [ C ] ∥International Workshop on Machine Learning in Medical Imaging , 2023 : 115-125.
[ 17 ] KUMTHEKAR A , REDDY G R.An integrated deep learning framework of U-Net and inception modulefor cloud detection of remote sensing images [ J ] .Arabian journal of geosciences , 2021 , 14 ( 18 ): 1900.
[ 18 ] CHEN Y P , DAI X Y , LIU M C , et al.Dynamic convolution : attention over convolution kernels [ C ] ∥Proceedings of the IEEE / CVF Conference on Computer Vision and Pattern Recognition , 2020 : 11030-11039.
[ 19 ] WAN Z H , YANG H , XU J P , et al.BACNN : Multi scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification [ J ] . Journal of forestry research , 2024 , 35 ( 1 ): 1-13.
[ 20 ] MARCUS D S , WANG T H , PARKER J , et al.Open access series of imaging studies ( OASIS ): Cross sectional MRI data in young , middle aged , nondemented , and demented older adults [ J ] .Journal of cognitive neuroscience , 2007 , 19 ( 9 ): 1498-1507.

相似文献/References:

[1]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
　WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(10):29.
[2]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
　LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(10):67.
[3]肖倩宏,康 鹏,杜 江,等.深度学习在电网智能调控系统中应用研究[J].机械与电子,2021,(01):38.
　XIAO Qianhong,KANG Peng,DU Jiang,et al.Research on the Application of Deep Learning Theory in Power Grid Intelligent Dispatching[J].Machinery & Electronics,2021,(10):38.
[4]许 哲,张少帅,郭 璐,等.无人机深度学习去雾算法[J].机械与电子,2021,(04):13.
　XU Zhe,ZHANG Shaoshuai,GUO Lu,et al. Deep Learning Defogging Algorithm for UAV[J].Machinery & Electronics,2021,(10):13.
[5]齐爱玲１,李 琳１,朱亦轩２,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
　QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(10):15.
[6]徐先峰,郑少杰,赵 依,等.基于数据分解与重构的光伏发电功率超短期预测[J].机械与电子,2022,(04):20.
　XU Xianfeng,ZHENG Shaojie,ZHAO Yi,et al.Ultra-short-term Prediction of Photovoltaic Power Generation Based on Data Decomposition and Deconstruction[J].Machinery & Electronics,2022,(10):20.
[7]江 励,熊达明,汤健华,等.自然光线环境中的空间物体快速识别和定位算法研究[J].机械与电子,2022,(06):8.
　JIANG Li,XIONG Daming,TANG Jianhua,et al.Recognition and Positioning Algorithm of Space Objects in Natural Light Environment[J].Machinery & Electronics,2022,(10):8.
[8]王西志,管声启,张理博,等.基于视觉引导的工业棒材上料系统研究[J].机械与电子,2023,41(05):19.
　WANG Xizhi,GUAN Shengqi,ZHANG Libo,et al.Research on Industrial Bar Feeding System Based on Visual Guidance[J].Machinery & Electronics,2023,41(10):19.
[9]王 青,吕绪山,党 帅,等.基于深度学习的纱管识别方法研究[J].机械与电子,2023,41(12):20.
　WANG Qing,LYU Xushan,DANG Shuai,et al.Research on Yarn Bobbin Detection Method Based on Deep Learning[J].Machinery & Electronics,2023,41(10):20.
[10]姜越夫,王 青,吕绪山.改进 YOLOv5s 的纱管目标检测方法[J].机械与电子,2024,42(02):29.
　JIANG Yuefu,WANG Qing,LYU Xushan.Improved YOLOv5s Method for Yarn Tube Object Detection[J].Machinery & Electronics,2024,42(10):29.

备注/Memo

备注/Memo:
收稿日期: 2025-06-10
基金项目:山西省应用基础研究项目面上自然基金项目( 201801D121162 );山西省重点研发计划资助项目( 201803D121069 );中北大学重点实验室开发研究基金资助项目( DXMBJJ2024-04 )
作者简介:刘 源 ( 2000- ),男,山西吕梁人,硕士研究生,研究方向为图像处理、图像配准;王 玉 ( 1979- ),女,山西太原人,博士,副教授,研究生导师,研究方向为信号与信息处理、图像配准与融合等,通信作者, E-mail : 1600447356@qq.com 。
更新日期/Last Update: 2025-11-12