Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images
Southeast University(东南大学);Centre de Recherche en Information Biomédicale Sino-Français (CRIBs)(中法生物医学信息研究中心);Univ Rennes(雷恩大学);Inserm(法国国家健康与医学研究院);LTSI - UMR1099(信号与图像处理实验室)
Yuting He, Tiantian Li, Guanyu Yang, Youyong Kong, Yang Chen, Huazhong Shu, Jean-Louis Coatrieux, Jean-Louis Dillenseger, Shuo Li
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation. However, further adoption of the joint models are hindered: 1) the diversity of augmentation data is reduced limiting the further enhancement of segmentation, 2) misaligned regions in weakly supervised data disturb the training process, 3) lack of label-based region constraints in few-shot situation limits the registration performance. We propose a novel Deep Complementary Joint Model (DeepRS) for complex scene registration and few-shot segmentation. We embed a perturbation factor in the registration to increase the activity of deformation thus maintaining the augmentation data diversity. We take a pixel-wise discriminator to extract alignment confidence maps which highlight aligned regions in weakly supervised data so the misaligned regions' disturbance will be suppressed via weighting. The outputs from segmentation model are utilized to implement deep-based region constraints thus relieving the label requirements and bringing fine registration. Extensive experiments on the CT dataset of MM-WHS 2017 Challenge show great advantages of our DeepRS that outperforms the existing state-of-the-art models.
Medical Image Registration and Its Application in Retinal Images: A Review
Southern University of Science and Technology(南方科技大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Singapore Eye Research Institute(新加坡眼科研究所)
Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);The Hawkes Institute, University College London(霍克斯研究所,伦敦大学学院);AI Laboratory, Massachusetts Institute of Technology(人工智能实验室,麻省理工学院)
LLaMA-Reg: Using LLaMA 2 for Unsupervised Medical Image Registration
Faculty of Information Science Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息科学工程与自动化学院);Taizhou Hospital of Zhejiang Province Affiliated with Wenzhou Medical University(温州医科大学附属浙江省台州医院);Enze Hospital, Taizhou Enze Medical Centre (Group)(台州恩泽医疗中心(集团)恩泽医院);The Second Affiliated Hospital of Dalian Medical University(大连医科大学附属第二医院)
MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration
Image Processing Center, Beihang University, Beijing, China(北京航空航天大学图像处理中心);Robotics Institute, Beihang University, Beijing, China(北京航空航天大学机器人研究所);Tongji Hospital, Huazhong University of Science and Technology, Wuhan, China(华中科技大学同济医院)
Robust Rigid and Non-Rigid Medical Image Registration Using Learnable Edge Kernels
Department of Mathematics, University of Innsbruck(因斯布鲁克大学数学系);Department of Radiology, Medical University of Innsbruck(因斯布鲁克医学大学放射学系);Neuroimaging Research Core Facility, Medical University of Innsbruck(因斯布鲁克医学大学神经影像研究核心设施)
General Vision Encoder Features as Guidance in Medical Image Registration
Klinikum Rechts der Isar, Technical University of Munich(慕尼黑工业大学右岸医院);School of Computation, Information & Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich(亥姆霍兹慕尼黑中心生物医学影像机器学习研究所);Munich Center for Machine Learning(慕尼黑机器学习中心);Cancer Research UK Cambridge Institute, University of Cambridge(剑桥大学英国癌症研究剑桥研究所);Department of Oncology, University of Cambridge(剑桥大学肿瘤学系);German Cancer Consortium (DKTK), Partner Site Munich(德国癌症联盟慕尼黑合作站点);Department of Computing, Imperial College London(伦敦帝国理工学院计算机系)
在图像配准中,许多努力致力于开发流行的归一化互信息准则的替代方案。与这些努力同时,越来越多的作品已经证明,通过对齐图像的结构表示而不是图像本身,也可以实现配准精度的大幅提高。遵循这一研究路径,我们提出了一种新的方法,用于单模态和多模态图像配准的基础上对齐的正则化向量场的结构信息,如梯度向量流场,一种技术,我们称之为\textit{vector field similarity}。我们的方法可以以一种简单的方式与任何现有的注册框架相结合,通过取代向量场相似性的强度为基础的注册。在我们的实验中,我们表明,所提出的方法相比传统的图像对齐几个公共图像数据集使用的成像方式和解剖位置的多样性。
uniGradICON: A Foundation Model for Medical Image Registration
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of Salzburg(萨尔茨堡大学);University Paris-Est(巴黎东部大学);Brigham and Women’s Hospital(布莱根妇女医院);ÉTS Montréal(蒙特利尔工程学院);Boston University(波士顿大学)
Pyramid Attention Network for Medical Image Registration
School of Biomedical Engineering, Shenzhen University(深圳大学生物医学工程学院);Medical UltraSound Image Computing (MUSIC) Lab(医学超声图像计算实验室);Smart Medical Imaging, Learning and Engineering (SMILE) Lab(智能医学影像、学习与工程实验室)
Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
Southern Medical University(南方医科大学);Shenzhen University(深圳大学)
形变场估计是医学图像配准中一个重要而又具有挑战性的问题。近年来,深度学习技术已成为简化配准问题的一种很有前途的方法,并逐渐应用于医学图像配准。但是,现有的大多数深度学习配准都没有考虑到当感受野不能覆盖运动图像和固定图像中的相应特征时,无法输出准确的位移值的问题。事实上,由于感受野的限制,3 x 3内核在高/原始分辨率下难以覆盖相应的特征。多分辨率和多卷积技术可以改善但无法避免这个问题。在这项研究中,我们在移动和固定图像上构建了金字塔特征集,并使用扭曲的移动和固定特征来估计每个尺度下的“残余”变形场,称为金字塔残余变形场估计模块(PRDFE模块)。该方法通过上采样和加权求和各尺度下的"残余"形变场,计算出各尺度下的"总"形变场,有效准确地将形变场从低分辨率转换到高分辨率,并用于各尺度下运动特征的变形。仿真和真实脑数据实验结果表明,该方法提高了配准的准确性和形变场的合理性。
XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention
Southeast University(东南大学);Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing(江苏省医学信息处理联合国际研究实验室);University of Western Ontario(西安大略大学)
有效的骨干网络对于基于深度学习的形变医学图像配准(Deformable Medical Image Registration,DMIR)非常重要,因为它可以提取和匹配两幅图像之间的特征,以发现相互之间的对应关系,从而实现精细配准。然而,现有的深度网络集中在单个图像的情况下,并且在配对图像上执行的配准任务受到限制。因此,我们提出了一种新的骨干网络,XMorpher,在DMIR有效的对应特征表示。1)提出了一种新的完整的Transformer架构,包括双并行特征提取网络,通过交叉注意交换信息,从而发现多层次的语义对应,同时逐渐提取各个特征,最终实现有效的配准。2)提出了交叉注意力Transformer(CAT)模块,建立图像间的注意力机制,能够自动发现对应关系,促使特征在网络中有效融合。3)该算法将注意力计算限制在不同大小的基窗口和搜索窗口之间,从而集中在变形配准的局部变换上,同时提高了计算效率。在没有任何额外功能的情况下,我们的XMorpher在DSC上提供了Voxelmorph 2.8%的改进,证明了它在DMIR中有效地表示了配对图像的特征。我们相信我们的XMorpher在更多配对的医学图像中具有巨大的应用潜力。我们的XMorpher在https://github.com/Solemoon/XMorpher上开放
SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformation
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Alibaba Group(阿里巴巴集团);Johns Hopkins University(约翰斯·霍普金斯大学);The First Affiliated Hospital of Zhejiang University(浙江大学附属第一医院)
SpikeReg: Energy-Efficient 3D Deformable Medical Image Registration with Spiking Neural Networks
School of Electrical and Computer Engineering, College of Engineering, University of Tehran(德黑兰大学电气与计算机工程学院);Max Planck Institute for Brain Research(马克斯·普朗克脑科学研究所);School of Computer Engineering, Iran University of Science and Technology (IUST)(伊朗科学技术大学计算机工程学院);Department of Electrical and Computer Engineering, University of Waterloo(滑铁卢大学电气与计算机工程系)
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
Computer Science and Artificial Intelligence Lab, MIT(麻省理工学院计算机科学与人工智能实验室);Meinig School of Biomedical Engineering, Cornell University(康奈尔大学迈尼格生物医学工程学院);Martinos Center for Biomedical Imaging, MGH, HMS(麻省总医院哈佛医学院马蒂诺生物医学成像中心)
On-the-Fly Guidance Training for Medical Image Registration
University of Leeds(利兹大学);University of California, Irvine(加州大学欧文分校);Tongji University(同济大学);Huazhong University of Science and Technology(华中科技大学);Fudan Univeristy(复旦大学);University of California, San Diego(加州大学圣迭戈分校)
Deep Learning for Medical Image Registration: A Comprehensive Review
Bangladesh University of Engineering and Technology(孟加拉国工程技术大学);Cincinnati Children’s Hospital Medical Center(辛辛那提儿童医院医疗中心);University of Cincinnati College of Medicine(辛辛那提大学医学院);University of Cincinnati(辛辛那提大学)
QUIZ: An Arbitrary Volumetric Point Matching Method for Medical Image Registration
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Guangdong Medical University(广东医科大学)
Robust registration of medical images in the presence of spatially-varying noise
University of California, San Francisco(加州大学旧金山分校);Weill Institute for Neurosciences(威尔神经科学研究所);Iran Science and Technology University(伊朗科技大学);Sharif University of Technology(谢里夫理工大学)
Unsupervised Multimodal 3D Medical Image Registration with Multilevel Correlation Balanced Optimization
College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University(湖南大学机器人视觉感知与控制技术国家工程研究中心);Cornell University(康奈尔大学)
Medical Image Registration Meets Vision Foundation Model: Prototype Learning and Contour Awareness
The University of Sydney(悉尼大学);Harvard Medical School(哈佛医学院);University of Electronic Science and Technology of China(电子科技大学);Brigham and Women’s Hospital(布莱根妇女医院)
针对无监督医学图像配准缺乏解剖知识的问题,提出融合 SAM 分割先验、原型学习与轮廓感知损失的配准框架,在多数据集上显著提升复杂结构和模糊边界场景的配准性能。
Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration
DAMO Academy, Alibaba Group(阿里巴巴达摩院);Hupan Lab(湖畔实验室);College of Computer Science and Technology, Zhejiang University, China(浙江大学计算机科学与技术学院);Shengjing Hospital of China Medical University, China(中国医科大学附属盛京医院)
Data-Driven Tissue- and Subject-Specific Elastic Regularization for Medical Image Registration
School of Computation, Information and Technology, Technical University of Munich(慕尼黑工业大学计算、信息与技术学院);Munich Center for Machine Learning(慕尼黑机器学习中心);Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich(亥姆霍兹慕尼黑生物医学成像机器学习研究所);German Cancer Consortium (DKTK)(德国癌症联盟);School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与成像科学学院)