Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Maryland School of Dentistry（马里兰大学牙医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Reese Timothy, Jerry L. Prince, Georges El Fakhri, Jonghye Woo
Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains. However, while the self-training UDA has demonstrated its effectiveness on discriminative tasks, such as classification and segmentation, via the reliable pseudo-label selection based on the softmax discrete histogram, the self-training UDA for generative tasks, such as image synthesis, is not fully investigated. In this work, we propose a novel generative self-training (GST) UDA framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning. The fast test-time adaptation is achieved by a round-based alternative optimization scheme. We validated our framework on the tagged-to-cine magnetic resonance imaging (MRI) synthesis problem, where datasets in the source and target domains were acquired from different scanners or centers. Extensive validations were carried out to verify our framework against popular adversarial training UDA methods. Results show that our GST, with tagged MRI of test subjects in new target domains, improved the synthesis quality by a large margin, compared with the adversarial training UDA methods.
Towards Cardiac Intervention Assistance: Hardware-aware Neural Architecture Exploration for Real-Time 3D Cardiac Cine MRI Segmentation
University of Notre Dame（圣母大学）；Guangdong Cardiovascular Institute（广东省心血管病研究所）；Guangdong Provincial People’s Hospital（广东省人民医院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Pittsburgh（匹兹堡大学）
Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI
Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学弗里德里希-亚历山大分校埃尔朗根大学医院放射学研究所）；CAIMED（CAIMED机构）；L3S（L3S机构）；Institut für Informationsverarbeitung, Leibniz University Hannover（汉诺威莱布尼茨大学信息处理研究所）
Dual-cycle Constrained Bijective VAE-GAN For Tagged-to-Cine Magnetic Resonance Image Synthesis
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland School of Dentistry（马里兰大学牙科学院）
Left Ventricle Segmentation and Quantification from Cardiac Cine MR Images via Multi-task Learning
National Library of Medicine, National Institutes of Health（美国国立卫生研究院国家医学图书馆）；Rochester Institute of Technology（罗切斯特理工学院）；TAJ Technologies Inc.（TAJ科技公司）
左心室的分割和各种心脏收缩功能的量化对于心血管疾病的及时诊断和治疗至关重要。传统上，这两项任务是独立处理的。在这里，我们提出了一个基于卷积神经网络的多任务学习方法，同时执行这两个任务，这样，网络学习更好的数据表示，提高泛化性能。问题的概率公式化使得能够在训练过程中学习任务的不确定性，这些不确定性用于自动计算任务的权重。我们对通过STACOM LV分割挑战获得的97个患者4维心脏电影-MRI数据集上从所提出的多任务网络获得的心肌分割与所提供的金标准心肌分割进行了五重交叉验证，获得了$0.849 \pm 0.036$的Dice重叠和$0.274 \pm 0.083$ mm的平均表面距离，同时估计心肌面积，平均绝对差误差为$205\pm198$ mm $^2$。
Training deep learning based dynamic MR image reconstruction using synthetic fractals
UCL Centre for Translational Cardiovascular Imaging, University College London（伦敦大学学院UCL转化心血管影像中心）；Department of Cardiology, Royal Free London NHS Foundation Trust（皇家自由伦敦NHS基金会信托心脏病科）；Institute of Cardiovascular Science, University College London（伦敦大学学院心血管科学研究所）
CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI
Department of Biomedical Engineering, National University of Singapore, Singapore（新加坡国立大学生物医学工程系）；School of Automation, Southeast University, Nanjing, China（东南大学自动化学院）；Department of Medicine, National University of Singapore, Singapore（新加坡国立大学医学系）；Department of Cardiology, National University Heart Centre Singapore, Singapore（新加坡国立心脏中心心内科部）
本文提出 CineMesh4D，一种端到端的 4D 全心脏重建方法，通过跨域映射从多视角 2D cine MRI 直接重建患者特定的全心脏网格，提升重建质量和运动一致性。
Structure-aware Unsupervised Tagged-to-Cine MRI Synthesis with Self Disentanglement
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland School of Dentistry（马里兰大学牙医学院）
CMRINet: Joint Groupwise Registration and Segmentation for Cardiac Function Quantification from Cine-MRI
Leiden University Medical Center（莱顿大学医学中心）；University of Sheffield（谢菲尔德大学）；INSIGNEO；Institute for In Silico Medicine（计算医学研究所）；Department of Infection, Immunity and Cardiovascular Disease（感染、免疫与心血管疾病部门）；Sheffield Teaching Hospitals（谢菲尔德教学医院）；Department of Clinical Radiology（临床放射学部门）
Speech Map: A Statistical Multimodal Atlas of 4D Tongue Motion During Speech from Tagged and Cine MR Images
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Maryland Dental School（马里兰大学牙医学院）；MGH Institute of Health Professions（麻省总医院健康职业学院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Contrast-Free Myocardial Scar Segmentation in Cine MRI using Motion and Texture Fusion
University of Oxford（牛津大学）；University of Southampton（南安普顿大学）；National University of Singapore（新加坡国立大学）；Fudan University（复旦大学）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）
Personalized 4D Whole Heart Geometry Reconstruction from Cine MRI for Cardiac Digital Twins
Department of Biomedical Engineering, National University of Singapore, Singapore（新加坡国立大学生物医学工程系）；School of Data Science, Fudan University, Shanghai, China（复旦大学数据科学学院）；Department of Engineering Science, University of Oxford, Oxford, UK（牛津大学工程科学系）；Department of Medicine, National University of Singapore, Singapore（新加坡国立大学医学系）；Department of Cardiology, National University Heart Centre Singapore, Singapore（新加坡国立心脏中心心内科部）
Cine cardiac MRI reconstruction using a convolutional recurrent network with refinement
Institute for Digital Communications, University of Edinburgh（爱丁堡大学数字通信研究所）；Institute of Information Science and Technologies “Alessandro Faedo”, National Research Council of Italy (CNR)（意大利国家研究委员会信息科学与技术研究所（亚历山德罗·法埃多））；Department of Information Engineering, University of Pisa（比萨大学信息工程系）；Institute for Infrastructure and Environment, University of Edinburgh（爱丁堡大学基础设施与环境研究所）；The Alan Turing Institute（阿兰·图灵研究所）
Enhancing Implicit Neural Representations with Image Feature Embedding for Unsupervised Cardiac Cine MRI Reconstruction
Division of Image Processing, Department of Radiology, Leiden University Medical Center（莱顿大学医学中心放射科图像处理部）；C.J. Gorter Center, Department of Radiology, Leiden University Medical Center（莱顿大学医学中心放射科C.J. 戈特中心）；Cardio Vascular Imaging Group, Department of Radiology, Leiden University Medical Center（莱顿大学医学中心放射科心血管成像组）；Philips Innovative Technologies（飞利浦创新技术公司）
Quality-aware Cine Cardiac MRI Reconstruction and Analysis from Undersampled k-space Data
School of Biomedical Engineering & Imaging Sciences, King’s College London, UK（伦敦国王学院生物医学工程与成像科学学院）；Technical University of Munich, Germany（慕尼黑工业大学）；Biomedical Image Analysis Group, Imperial College London, UK（帝国理工学院生物医学图像分析组）；Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, London, UK（盖伊和圣托马斯国民健康服务信托基金会成人及儿科心脏病科）；Coimbra Institute for Biomedical Imaging and Translational Research, University of Coimbra, Portugal（科英布拉大学科英布拉生物医学成像与转化研究学院）；Helmholtz Center Munich, Germany（慕尼黑亥姆霍兹中心）
KP-INR: A Dual-Branch Implicit Neural Representation Model for Cardiac Cine MRI Reconstruction
Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands（莱顿大学医学中心放射科）；Cardiologs, Philips, Paris, France（法国巴黎Philips心血管部门）；Faculty of Computer Science, Eindhoven University of Technology, Eindhoven, The Netherlands（埃因霍温理工大学计算机科学学院）；Philips Innovative Technologies, Hamburg, Germany（德国汉堡Philips创新技术）
Reconstruction of Cardiac Cine MRI Using Motion-Guided Deformable Alignment and Multi-Resolution Fusion
School of Health Science and Engineering, University of Shanghai for Science and Technology（上海理工大学健康科学与工程学院）；ToolSensing Technologies Co., Ltd（拓深科技有限公司）；School of Medical Instruments, Shanghai University of Medicine and Health Sciences（上海健康医学院医疗器械学院）；Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication & Electronic Engineering, East China Normal University（华东师范大学通信与电子工程学院多维信息处理上海重点实验室）
Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI with Explicit Cardiac Motion Modeling
Department of Biomedical Engineering, National University of Singapore, Singapore（新加坡国立大学生物医学工程系）；Department of Computer Science, National University of Singapore, Singapore（新加坡国立大学计算机科学系）；Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand（奥克兰大学生物工程研究所）；School of Biomedical Engineering and Imaging Sciences, King’s College London, UK（伦敦国王学院生物医学工程与成像科学学校）；Department of Medicine, National University of Singapore, Singapore（新加坡国立大学医学系）；Department of Cardiology, National University Heart Centre Singapore, Singapore（新加坡国立心脏中心心血管科）
CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment
Institute for Artificial Intelligence, University of Central Florida（中佛罗里达大学人工智能研究所）；Nemours Cardiac Center, Nemours Children’s Hospital, Florida（佛罗里达州内穆尔斯儿童医院内穆尔斯心脏中心）；Children’s Heart Center, WVU Golisano Children’s, West Virginia（西弗吉尼亚大学戈利萨诺儿童医院儿童心脏中心）；Department of Clinical Sciences, College of Medicine, University of Central Florida（中佛罗里达大学医学院临床科学系）
Personalized 3D Myocardial Infarct Geometry Reconstruction from Cine MRI for Cardiac Digital Twins
Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）；Department of Medicine, National University of Singapore（新加坡国立大学医学系）；Department of Cardiology, National University Heart Centre Singapore（新加坡国立心脏中心心内科部）
Personalized 4D Whole-Heart Mesh Reconstruction from Cine MRI via Multi-Scale Temporal Modeling and Differentiable Contour Rendering
Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）；School of Automation, Southeast University（东南大学自动化学院）；Department of Medicine, National University of Singapore（新加坡国立大学医学系）；Department of Cardiology, National University Heart Centre Singapore（新加坡国立大学心脏中心心脏病学系）
DINOMotion: advanced robust tissue motion tracking with DINOv2 in 2D-Cine MRI-guided radiotherapy
Department of Computer Science and Software Engineering, Concordia University（计算机科学与软件工程系，康科迪亚大学）；Department of Electrical and Computer Engineering, Concordia University（电气与计算机工程系，康科迪亚大学）；Elekta Ltd.（Elekta公司）；Diagnos Medical Systems（Diagnos医疗系统）
Chain of Flow: ECG-Conditioned 4D Cardiac Cine Generation from Patient-Specific Anatomical Anchor
School of Engineering, College of Engineering and Physical Sciences, University of Birmingham（英国伯明翰大学工程学院）；William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University London（伦敦Queen Mary大学威廉·哈里维研究所）；Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust（巴特勒医院心脏中心，圣巴塞洛缪医院，巴特勒健康 NHS信托）；Division of Cardiology, Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院心脏病科）
提出Chain of Flow (COF)框架，利用患者特定MRI和当前ECG生成4D心脏电影，在UK Biobank上实现高图像保真度和下游功能性能。
High-Resolution Maps of Left Atrial Displacements and Strains Estimated with 3D Cine MRI using Online Learning Neural Networks
Imperial College London（帝国理工学院）；Spinoza Centre for Neuroimaging（斯宾诺莎神经成像中心）；University of Minho（米尼奥大学）；King’s College London（伦敦国王学院）；Royal Free Hospital（皇家自由医院）；UCL Queen Square Institute of Neurology（伦敦大学学院女王广场神经学研究所）；National Heart & Lung Institute（国家心肺研究所）
An Unsupervised Deep Learning Method for Multi-coil Cine MRI
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院医学人工智能研究中心）；Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences（中国科学院大学深圳先进技术学院）；The State University of New York, Buffalo（纽约州立大学布法罗分校）
Gabor Primitives for Accelerated Cardiac Cine MRI Reconstruction
Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany（人工智能在医疗与医学中的chair，慕尼黑技术大学（TUM）和慕尼黑技术大学医院，德国慕尼黑）；School of Computation and Information Technology, Technical University of Munich, Munich, Germany（计算与信息科技学院，慕尼黑技术大学，德国慕尼黑）；Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany（生物医学影像中的机器学习研究所，海德堡慕尼黑，德国纽赫堡）；Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, USA（放射科，波士顿儿童医院和哈佛医学院，美国波士顿）；Munich Center for Machine Learning, Technical University of Munich, Munich, Germany（慕尼黑机器学习中心，慕尼黑技术大学，德国慕尼黑）；GE HealthCare, Munich, Germany（通用电气医疗系统，德国慕尼黑）；School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom（生物医学工程与成像科学学院，伦敦国王学院，英国伦敦）；Department of Computing, Imperial College London, London, United Kingdom（计算学院，伦敦帝国学院，英国伦敦）
本文提出 Gabor 原始要素用于加速心脏 cine MRI 重建，通过调制高斯包络实现灵活频谱支持，提升对光滑结构和锐利边界的表示能力。
MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI
Imperial College London（帝国理工学院）；Technical University Munich（慕尼黑工业大学）；University of Edinburgh（爱丁堡大学）；MRC London Institute of Medical Sciences（MRC伦敦医学科学研究所）
A latent ODE approach to full-cycle biventricular cardiac motion modeling from cine MRI
Swiss Data Science Center, EPFL and ETH Zürich（瑞士数据科学中心，EPFL 和 ETH 苏黎世）；Diagnostic and Interventional Radiology, University Hospital Zürich（诊断与介入放射学，苏黎世大学医院）；Institute for Biomedical Engineering, University and ETH Zürich（生物医学工程研究所，苏黎世大学和 ETH 苏黎世）；Biomedical Informatics Group, ETH Zürich（生物医学信息学小组，ETH 苏黎世）；Division of Preventive Medicine, Brigham and Women’s Hospital / Harvard Medical School（预防医学部，布莱根妇女医院/哈佛医学院）
DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue
Johns Hopkins University（约翰斯·霍普金斯大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Maryland School of Medicine（马里兰大学医学院）
