采用分割一切模型的弱监督互学习三维医学图像配准方法

苏渝钦; 潘杭镇; 李锦江; 刘欢; 李钟毓; 刘杨

doi:null

您当前的位置：

首页 >

文章列表页 >

采用分割一切模型的弱监督互学习三维医学图像配准方法

更新时间：2026-06-09

- 采用分割一切模型的弱监督互学习三维医学图像配准方法
- Foundation Model Guided 3D Medical Registration Via Weakly-Supervised Mutual Learning
- 西安交通大学学报 2026年
- 作者机构：
  
  1.西安交通大学软件学院，710049，西安
  2.西安交通大学计算机科学与技术学院，710049，西安
  3.上海交通大学计算机学院，200032，上海
  4.西安交通大学网络空间安全学院，710049，西安
  5.西安交通大学智能网络与网络安全教育部重点实验室，710049，西安
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： TP391.41
- 收稿：2025-11-17，
  
  修回：2026-04-15，
  
  录用：2026-04-27，
- 稿件说明：
移动端阅览
苏渝钦, 潘杭镇, 李锦江, 等. 采用分割一切模型的弱监督互学习三维医学图像配准方法[J/OL]. 西安交通大学学报, 2026.

SU Yuqin, PAN Hangzhen, LI Jinjiang, et al. Foundation Model Guided 3D Medical Registration Via Weakly-Supervised Mutual Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026.
苏渝钦, 潘杭镇, 李锦江, 等. 采用分割一切模型的弱监督互学习三维医学图像配准方法[J/OL]. 西安交通大学学报, 2026. DOI：

SU Yuqin, PAN Hangzhen, LI Jinjiang, et al. Foundation Model Guided 3D Medical Registration Via Weakly-Supervised Mutual Learning[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026. DOI：

摘要

针对三维医学图像配准中无监督方法配准精度不足、弱监督方法依赖高质量分割标签且分割基础模型生成标签难以直接稳定指导配准训练的问题，提出了一种采用分割一切模型的弱监督互学习三维医学图像配准方法。首先，利用分割一切模型从不同视角提取主要解剖区域掩码，并通过融合构建交集掩码与并集掩码，以表征不同粒度的结构先验信息。其次，在弱监督配准框架中引入互学习机制，通过结合可信度与位置信息模块，促进不同掩码监督下配准模型之间的知识蒸馏与协同优化，从而实现互补信息的有效利用并提升训练稳定性。最后，在三组脑图像数据集上的实验结果表明，所提方法能够在充分利用标签信息的同时保持稳定训练，与现有三维图像配准方法相比，在区域重叠度等指标上表现更优，其中重叠系数提升约5%，体现出更高的配准精度与可靠性。

Abstract

To address the problems that unsupervised methods for 3D medical image registration suffer from limited accuracy

weakly supervised methods rely on high-quality segmentation labels

and labels generated by foundation segmentation models cannot directly and stably guide registration training

a weakly supervised mutual-learning method for 3D medical image registration guided by a foundation segmentation model is proposed. First

masks of major anatomical regions are extracted from different views using segment anything model

and intersection and union masks are constructed through mask fusion to represent structural prior information at different granularities. Second

a mutual-learning mechanism is introduced into the weakly supervised registration framework

where a confidence and position information module is incorporated to promote knowledge distillation and collaborative optimization between registration models under different mask supervision

thereby enabling effective utilization of complementary information and improving training stability. Finally

experimental results on three brain image datasets demonstrate that the proposed method can effectively exploit label information while maintaining stable training

and outperforms existing 3D image registration methods on multiple evaluation metrics

showing better registration accuracy and reliability.

关键词

Keywords

references

WANG Quanxin , DING Songlin , LI Yang , et al . The Allen mouse brain common coordinate framework: a 3D reference atlas [J ] . Cell , 2020 , 181 ( 4 ): 936 - 953 .

PENG Hanchuan , XIE Peng , LIU Lijuan , et al . Morphological diversity of single neurons in molecularly defined cell types [J ] . Nature , 2021 , 598 ( 7879 ): 174 - 181 .

LI Zhongyu , SHANG Z , LIU J , et al . D-LMBmap: a fully automated deep-learning pipeline for whole-brain profiling of neural circuitry [J ] . Nature Methods , 2023 , 20 ( 10 ): 1593 - 1604 .

BALAKRISHNAN G , ZHAO A , SABUNCU M R , et al . Voxelmorph: a learning framework for deformable medical image registration [J ] . IEEE transactions on medical imaging , 2019 , 38 ( 8 ): 1788 - 1800 .

余升林 , 吴彤 , 葛明锋 , 等 . 循环一致性的无监督可变形图像配准方法 [J ] . 计算机辅助设计与图形学学报 , 2023 , 35 ( 04 ): 516 - 524 .

YU Shenglin , WU Tong , GE Mingfeng , et al . Unsupervised deformable image registration method with cyclic consistency [J ] . Journal of Computer-Aided Design & Computer Graphics , 2023 , 35 ( 4 ): 516 - 524 .

CHEN Junyu , FREY E C , HE Y , et al . Transmorph: Transformer for unsupervised medical image registration [J ] . Medical image analysis , 2022 , 82 : 102615 .

GHAHREMANI M , KHATERI M , JIAN B , et al . H-vit: A hierarchical vision transformer for deformable image registration [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 2024 : 11513 - 11523 .

JIA Xi , LU W , CHENG X , et al . Decoder-only image registration [J ] . IEEE Transactions on Medical Imaging , 2025 .

KIM B , KIM D H , PARK S H , et al . CycleMorph: cycle consistent unsupervised deformable image registration [J ] . Medical image analysis , 2021 , 71 : 102036 .

ZHU Yongpei , LU S . Swin-voxelmorph: A symmetric unsupervised learning model for deformable medical image registration using swin transformer [C ] // International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer Nature Switzerland , 2022 : 78 - 87 .

赵海峰 , 姚丽莎 , 罗斌 . 改进的人工鱼群算法和Powell法结合的医学图像配准 [J ] . 西安交通大学学报 , 2011 , 45 ( 04 ): 46 - 52 .

ZHAO Haifeng , YAO Lisha , LUO Bin . Registration of multi-resolution medical images using a modified artificial fish-swarm algorithm combined with Powell’s method [J ] . Journal of Xi'an Jiaotong University , 2011 , 45 ( 4 ): 46 - 52 .

高军 , 李学伟 , 张建 , 等 . 基于模板匹配的图像配准算法 [J ] . 西安交通大学学报 , 2007 ,( 03 ): 307 - 311 .

GAO Jun , LIXuewei , ZHANGJian , et al . Image registration algorithm based on template matching [J ] . Journal of Xi'an Jiaotong University , 2007 , 41 ( 3 ): 307 - 311 .

吴攀超 , 王宗义 , 林欣堂 . 采用局部差分模型描述的彩色图像配准技术 [J ] . 西安交通大学学报 , 2011 , 45 ( 10 ): 30 - 37 .

WU Panchao , WANGZongyi , LINXintang . Color image registration technique based on local differential model [J ] . Journal of Xi'an Jiaotong University , 2011 , 45 ( 10 ): 30 - 37 .

YEW Z J , LEE G H . 3dfeat-net: Weakly supervised local 3d features for point cloud registration [C ] // Proceedings of the European conference on computer vision (ECCV) . 2018 : 607 - 623 .

顾峰 . 基于分割辅助和级联的医学图像配准 [D ] . 西安电子科技大学 , 2021 . DOI: 10.27389/d.cnki.gxadu.2021.002996 http://dx.doi.org/10.27389/d.cnki.gxadu.2021.002996 .

GU Feng . Medical image registration based on segmentation assistance and cascade [D ] . Xidian University , 2021 . DOI: 10.27389/d.cnki.gxadu. 2021.002996 http://dx.doi.org/10.27389/d.cnki.gxadu.2021.002996 .

HU Yipeng , MODAT M , GIBSON E , et al . Label-driven weakly-supervised learning for multimodal deformable image registration [C ] // 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) . IEEE , 2018 : 1070 - 1074 .

WU Menglin , HE X , LI F , et al . Weakly supervised volumetric prostate registration for MRI-TRUS image driven by signed distance map [J ] . Computers in biology and medicine , 2023 , 163 : 107150 .

XU Zhenlin , NIETHAMMER M . DeepAtlas: Joint semi-supervised learning of image registration and segmentation [C ] // International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer International Publishing , 2019 : 420 - 429 .

KIRILLOV A , MINTUN E , RAVI N , et al . Segment anything [C ] // Proceedings of the IEEE/CVF international conference on computer vision . 2023 : 4015 - 4026 .

HUANG Shiqi , XU T , SHEN Z , et al . One registration is worth two segmentations [C ] // International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer Nature Switzerland , 2024 : 665 - 675 .

XU Hao , XUE T , LIU D , et al . Sat-morph: Unsupervised deformable medical image registration using vision foundation models with anatomically aware text prompt [C ] // International Workshop on Foundation Models for General Medical AI . Cham : Springer Nature Switzerland , 2024 : 71 - 80 .

冯林 , 管慧娟 , 孙焘 , 滕弘飞 . 医学图像非刚性配准研究进展 [J ] . 北京生物医学工程 , 2006 , 25 ( 4 ): 437 - 440 .

FENG Lin , GUAN Huijuan , SUNTao , TENG Hongfei . Research Progress of Non-Rigid Registration in Medical Images [J ] . Beijing Biomedical Engineering , 2006 , 25 ( 4 ): 437 - 440 .

孟勋 . 典型医学图像配准方法及优化策略的研究进展 [J ] . 中国医疗设备 , 2015 , 30 ( 8 ): 64 - 69 .

MENG Xun . Research on the Typical Medical Image Registration Method and Its Optimization Strategies [J ] . China Medical Devices , 2015 , 30 ( 8 ): 64 - 69 .

ROHR K , STIEHL H S , SPRENGEL R , et al . Landmark-based elastic registration using approximating thin-plate splines [J ] . IEEE Transactions on medical imaging , 2002 , 20 ( 6 ): 526 - 534 .

靳峰 , 冯大政 . 利用空间序列描述子的快速准确的图像配准算法 [J ] . 西安交通大学学报 , 2014 , 48 ( 6 ): 6 . DOI: 10.7652/xjtuxb201406004 http://dx.doi.org/10.7652/xjtuxb201406004 .

JIN Feng , FENG Dazheng . Fast and accurate image registration algorithm using spatial sequence descriptor [J ] . Journal of Xi'an Jiaotong University , 2014 , 48 ( 6 ): 6 . DOI: 10.7652/xjtuxb201406004 http://dx.doi.org/10.7652/xjtuxb201406004 .

DETONE D , MALISIEWICZ T , RABINOVICH A . Deep image homography estimation [J ] . arXiv preprint arXiv: 1606.03798 , 2016 .

ROHÉ M M , DATAR M , HEIMANN T , et al . SVF-Net: learning deformable image registration using shape matching [C ] // International conference on medical image computing and computer-assisted intervention . Cham : Springer International Publishing , 2017 : 266 - 274 .

马露凡 , 罗凤 , 严江鹏 , 徐哲 , 罗捷 , 李秀 . 深度医学图像配准研究进展：迈向无监督学习 [J ] . 中国图象图形学报 , 2021 , 26 ( 9 ): 2037 - 2057 .

MA Lufan , LUOFeng , YAN Jiangpeng , XU Zhe , LUO Jie , LI Xiu . Deep-learning based medical image registration pathway: towards unsupervised learning [J ] . Journal of Image and Graphics , 2021 , 26 ( 9 ): 2037 - 2057 .

RONNEBERGER O , FISCHER P , BROX T . U-net: Convolutional networks for biomedical image segmentation [C ] // International Conference on Medical image computing and computer-assisted intervention . Cham : Springer international publishing , 2015 : 234 - 241 .

JADERBERG M , SIONYAN K , ZISSERMAN A . Spatial transformer networks [J ] . Advances in neural information processing systems , 2015 , 28 .

BLENDOWSKI M , HANSEN L , HEINRICH M P . Weakly-supervised learning of multi-modal features for regularised iterative descent in 3D image registration [J ] . Medical image analysis , 2021 , 67 : 101822 .

LI Yiwen , FU Y , GAYO I J M B , et al . Semi-weakly-supervised neural network training for medical image registration [J ] . arXiv preprint arXiv: 2402.10728 , 2024 .

ZHAO Ziheng , ZHANG Y , WU C , et al . One model to rule them all: Towards universal segmentation for medical images with text prompts [J ] . arXiv preprint arXiv: 2312.17183 , 2023 .

MA Jun , HE Y , LI F , et al . Segment anything in medical images [J ] . Nature Communications , 2024 , 15 ( 1 ): 654 .

HINTON G , VINYALS O , DEAN J . Distilling the knowledge in a neural network [J ] . arXiv preprint arXiv: 1503.02531 , 2015 .

ZHANG Ying , XIANG T , HOSPEDALES T M , et al . Deep mutual learning [C ] // Proceedings of the IEEE conference on computer vision and pattern recognition . 2018 : 4320 - 4328 .

PANG Youwei , ZHAO X , ZHANG L , et al . Multi-scale interactive network for salient object detection [C ] // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition . 2020 : 9413 - 9422 .

YOU Chenyu , ZHOU Y , ZHAO R , et al . Simcvd: Simple contrastive voxel-wise representation distillation for semi-supervised medical image segmentation [J ] . IEEE Transactions on Medical Imaging , 2022 , 41 ( 9 ): 2228 - 2237 .

KONG Lintong , YANG Jie . MDFlow: Unsupervised optical flow learning by reliable mutual knowledge distillation [J ] . IEEE Transactions on circuits and systems for video technology , 2022 , 33 ( 2 ): 677 - 688 .

LIU Jun , WANG W , SHEN N , et al . Mutualreg: mutual learning for unsupervised medical image registration [C ] // ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . IEEE , 2024 : 1561 - 1565 .

AVANTS B B , TUSTISON N J , SONG G , et al . A reproducible evaluation of ANTs similarity metric performance in brain image registration [J ] . Neuroimage , 2011 , 54 ( 3 ): 2033 - 2044 .

KLEIN S , STARING M , MURPHY K , et al . Elastix: a toolbox for intensity-based medical image registration [J ] . IEEE transactions on medical imaging , 2009 , 29 ( 1 ): 196 - 205 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向高海拔空冷发电机防晕性能演化规律的电热耦合研究

EBSILON软件在热电联产系统优化中的应用综述

采用机器学习的大规模并行程序I/O性能建模与预测方法

扇贝仿生密封腔室内超临界二氧化碳泄漏流湍动能耗散机理研究

电子级超纯氮深冷空分流程节能优化研究