Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ's shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperforms the state-of-the art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen, with respect to the original U-Net's prediction. Finally, we discuss the results and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available.
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）
IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
Nanchang University（南昌大学）；Medical AI Research Center, 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）
Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological images
Norwegian University of Science and Technology（挪威科技大学）；St. Olavs Hospital, Trondheim University Hospital（圣奥拉夫医院，特隆赫姆大学医院）；SINTEF Digital（挪威科技工业研究院数字研究所）
A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Images
Shanghai AI Lab（上海人工智能实验室）；Shenzhen Yino Intelligence Techonology Co., Ltd.（深圳一诺智能科技有限公司）；Shenying Medical Technology (Shenzhen) Co., Ltd.（深盈医疗科技（深圳）有限公司）；School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；Institute of Medical Robotics, Shanghai Jiao Tong University（上海交通大学医疗机器人研究所）；Shenzhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院深圳计算机视觉与模式识别重点实验室、SIAT-商汤联合实验室）；Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute 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）；Peng Cheng Laboratory（鹏城实验室）；Pazhou Lab（琶洲实验室）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；SIAT-SenseTime Joint Lab（SIAT-商汤联合实验室）；Shenzhen Key Lab of Computer Vision and Pattern Recognition（深圳计算机视觉与模式识别重点实验室）
放射疗法（RT）在临床上广泛用于治疗头颈部（HaN）癌症。RT计划的一个重要步骤是在HaN CT图像中准确分割各种危及器官（OAR）。然而，考虑到典型的HaN CT图像包含数十至数百个切片，手动分割OAR是耗时、繁琐且容易出错的。迫切需要自动分割算法。最近，卷积神经网络（CNN）在这项任务上得到了广泛的研究。特别地，3D CNN经常被采用来处理3D HaN CT图像。幼稚的3D CNN有两个问题。首先，3D CT图像的深度分辨率通常比平面内分辨率低几倍。直接使用3D CNN而不区分这种差异可能会导致提取失真的图像特征并影响最终的分割性能。第二，存在严重的类别不平衡问题，大器官可能比小器官大几倍。很难同时实现对所有器官的准确分割。为了解决这些问题，我们提出了一种新的混合CNN，融合2D和3D卷积，以打击不同的空间分辨率，并提取有效的边缘和语义特征，从3D HaN CT图像。为了适应大型和小型器官，我们的最终模型名为OrganNet2.5D，仅由两个而不是经典的四个下采样操作组成，并引入混合扩张卷积来维持各自的场。在MICCAI 2015挑战数据集上的实验表明，与最先进的方法相比，OrganNet2.5D实现了令人满意的性能。
Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices
University of Electronic Science and Technology of China（电子科技大学）；King’s College London（伦敦国王学院）；University Hospitals KU Leuven（鲁汶大学附属医院）；University College London（伦敦大学学院）；SenseTime Research（商汤科技研究院）
Heart Segmentation From MRI Scans Using Convolutional Neural Network
University of Karachi（卡拉奇大学）；Zhejiang University（浙江大学）；Iqra University（伊克拉大学）；Karachi Institute of Economics and Technology（卡拉奇经济与技术学院）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）
Cranial Implant Prediction using Low-Resolution 3D Shape Completion and High-Resolution 2D Refinement
Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（Isar河畔临床中心）；TranslaTUM Center for Translational Cancer Research（TranslaTUM转化癌症研究中心）；Department for Oral & Maxillofacial Surgery, University Hospital Schleswig-Holstein, Campus Kiel（石勒苏益格-荷尔斯泰因大学医院基尔校区口腔颌面外科）
