In this paper, we describe how a patient-specific, ultrasound-probe-induced prostate motion model can be directly generated from a single preoperative MR image. Our motion model allows for sampling from the conditional distribution of dense displacement fields, is encoded by a generative neural network conditioned on a medical image, and accepts random noise as additional input. The generative network is trained by a minimax optimisation with a second discriminative neural network, tasked to distinguish generated samples from training motion data. In this work, we propose that 1) jointly optimising a third conditioning neural network that pre-processes the input image, can effectively extract patient-specific features for conditioning; and 2) combining multiple generative models trained separately with heuristically pre-disjointed training data sets can adequately mitigate the problem of mode collapse. Trained with diagnostic T2-weighted MR images from 143 real patients and 73,216 3D dense displacement fields from finite element simulations of intraoperative prostate motion due to transrectal ultrasound probe pressure, the proposed models produced physically-plausible patient-specific motion of prostate glands. The ability to capture biomechanically simulated motion was evaluated using two errors representing generalisability and specificity of the model. The median values, calculated from a 10-fold cross-validation, were 2.8+/-0.3 mm and 1.7+/-0.1 mm, respectively. We conclude that the introduced approach demonstrates the feasibility of applying state-of-the-art machine learning algorithms to generate organ motion models from patient images, and shows significant promise for future research.
Intraoperative Liver Surface Completion with Graph Convolutional VAE
Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London（伦敦大学学院惠康/工程与物理科学研究委员会介入与外科科学中心）；Centre For Medical Image Computing, University College London（伦敦大学学院医学图像计算中心）；Division of Surgery and Interventional Science, University College London（伦敦大学学院外科与介入科学系）
Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models
NCT/UCC Dresden（德累斯顿国家肿瘤疾病中心/德国癌症联盟德累斯顿分部）；DKFZ Heidelberg（德国癌症研究中心海德堡分部）；Faculty of Medicine & University Hospital Carl Gustav Carus TU Dresden（德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院及大学医院）；HZDR Dresden（德累斯顿亥姆霍兹中心）；The Centre for Tactile Internet with Human-in-the-Loop (CeTI)（以人为中心的触觉互联网中心）；Purdue University（普渡大学）；Indiana University（印第安纳大学）；University Hospital & Faculty of Medicine Carl Gustav Carus, TUD（德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院及大学医院）
Optimization-Based Calibration for Intravascular Ultrasound Volume Reconstruction
Inria；University of Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）；INSERM（法国国家医学研究院）；ICube（ICube研究中心）；UMR7357（UMR7357研究单位）；University of Basel（巴塞尔大学）；Department of Biomedical Engineering（生物医学工程系）；Institute of Image-Guided Surgery（影像引导手术研究所）；IHU Strasbourg（斯特拉斯堡IHU）
Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation
Center for Virtual Imaging Trials, Department of Radiology, Duke University School of Medicine, Durham, NC, USA Biomedical Imaging Group Rotterdam, Department of Radiology \& Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands Electrical；Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, USA
Reconstruct Spine CT from Biplanar X-Rays via Diffusion Learning
Beijing United Imaging Research Institute of Intelligent Imaging（北京联影智能影像研究院）；Beihang University（北京航空航天大学）；Tianjin University（天津大学）；United Imaging Intelligence（联影智能）
Conditional Diffusion Model with Anatomical-Dose Dual Constraints for End-to-End Multi-Tumor Dose Prediction
Faculty of Applied Sciences, Macao Polytechnic University（澳门理工大学应用科学学院）；Affiliated Hospital of Xiangnan University（湘南大学附属医院）；Jiangxi Cancer Hospital（江西省肿瘤医院）；Chenzhou Third People's Hospital（郴州第三人民医院）
CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis
Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）；Harvard University（哈佛大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Oak Ridge National Laboratory（橡树岭国家实验室）；University of Liverpool（利物浦大学）
Cold-Start Forecasting of New Product Life-Cycles via Conditional Diffusion Models
Guanghua School of Management, Peking University（北京大学光华管理学院）；Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology（香港科技大学工业工程与决策分析系）
Conditional Segmentation in Lieu of Image Registration
University College London（伦敦大学学院）；University of Oxford（牛津大学）；Siemens Healthineers（西门子医疗）；King’s College London（伦敦国王学院）
经典的成对图像配准方法搜索优化数字测量的空间变换，所述数字测量指示一对移动图像和固定图像对准得有多好。当前基于学习的配准方法已经采用相同的范例，并且通常针对任何新的输入图像对以密集位移场或空间变换模型的参数的形式预测密集对应。然而，在许多配准应用中，空间变换本身仅需要传播感兴趣的点或区域（ROI）。在这种情况下，这些ROI内部或外部的详细像素级或体素级对应通常没有什么临床价值。在本文中，我们提出了一种替代的范例，其中相应的图像特定的ROI的位置，在一个图像中定义的，在另一个图像的学习。这导致用条件分割算法代替图像配准，条件分割算法可以建立在典型的图像分割网络及其广泛采用的训练策略上。以前列腺3D MRI和超声图像的配准为例来演示这种新方法，我们报告了术中超声图像上定义的真实感兴趣区域与从术前传播的真实感兴趣区域之间的中位目标配准误差（TRE）为2.1 mm MR图像。与先前提出的空间变换预测配准网络相比，使用所提出的条件分割获得了显着更低（>34%）的TREs，所述空间变换预测配准网络针对单个图像对使用相同的多个ROI标签进行训练。我们结束这项工作，使用定量偏差方差分析，提供一个解释所观察到的注册精度的提高。
SP-DiffDose: A Conditional Diffusion Model for Radiation Dose Prediction Based on Multi-Scale Fusion of Anatomical Structures, Guided by SwinTransformer and Projector
University of the Chinese Academy of Sciences（中国科学院大学）；West China Hospital, Sichuan University（四川大学华西医院）；Sichuan University（四川大学）
Semantic segmentation of surgical hyperspectral images under geometric domain shifts
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；Heidelberg University Hospital（海德堡大学医院）
Towards Patient-Specific Deformable Registration in Laparoscopic Surgery
Biomedical Robotics Lab, Istituto Italiano di Tecnologia, Genoa, Italy（生物医学机器人实验室，意大利理工学院，热那亚）；Department of Computer Science, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genoa, Italy（计算机科学、生物工程、机器人与系统工程系（DIBRIS），热那亚大学，意大利）；Harvard Medical School, Brigham and Women’s Hospital, Boston, USA（哈佛医学院，布里洛妇女医院，美国波士顿）
3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image
Shenzhen Institutes 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）；School of Biomedical Engineering, Shenzhen University（深圳大学生物医学工程学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；College of Computer Science and Technology, Qingdao University（青岛大学计算机科学与技术学院）
Fast light-field 3D microscopy with out-of-distribution detection and adaptation through Conditional Normalizing Flows
Technical University of Munich（慕尼黑工业大学）；Munich Institute of Biomedical Engineering（慕尼黑生物医学工程研究所）；Massachusetts Institute of Technology（麻省理工学院）；University of Bern（伯尔尼大学）
Deep-Motion-Net: GNN-based volumetric organ shape reconstruction from single-view 2D projections
University of Leeds（利兹大学）；St James’s University Hospital, Leeds Teaching Hospitals NHS Trust（利兹教学医院NHS信托基金圣詹姆斯大学医院）；University of Manchester（曼彻斯特大学）；University of Sheffield（谢菲尔德大学）；University of Glasgow（格拉斯哥大学）
