Recent rising interests in patient-specific thoracic surgical planning and simulation require efficient and robust creation of digital anatomical models from automatic medical image segmentation algorithms. Deep learning (DL) is now state-of-the-art in various radiological tasks, and U-shaped DL models have particularly excelled in medical image segmentation since the inception of the 2D UNet. To date, many variants of U-shaped models have been proposed by the integration of different attention mechanisms and network configurations. Systematic benchmark studies which analyze the architecture of these models by leveraging the recent development of the multi-label databases, can provide valuable insights for clinical deployment and future model designs, but such studies are still rare. We conduct the first systematic benchmark study for variants of 3D U-shaped models (3DUNet, STUNet, AttentionUNet, SwinUNETR, FocalSegNet, and a novel 3D SwinUnet with four variants) with a focus on CT-based anatomical segmentation for thoracic surgery. Our study systematically examines the impact of different attention mechanisms, the number of resolution stages, and network configurations on segmentation accuracy and computational complexity. To allow cross-reference with other recent benchmarking studies, we also included a performance assessment of the BTCV abdominal structural segmentation. With the STUNet ranking at the top, our study demonstrated the value of CNN-based U-shaped models for the investigated tasks and the benefit of residual blocks in network configuration designs to boost segmentation performance.
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Georgia Institute of Technology（佐治亚理工学院）
Thoracic disease detection from chest radiographs using deep learning methods has been an active area of research in the last decade. Most previous methods attempt to focus on the diseased organs of the image by identifying spatial regions responsible for significant contributions to the model's prediction. In contrast, expert radiologists first locate the prominent anatomical structures before determining if those regions are anomalous. Therefore, integrating anatomical knowledge within deep learning models could bring substantial improvement in automatic disease classification. Motivated by …
PAII Inc.（PAII公司）；The First Affiliated Hospital Zhejiang University（浙江大学附属第一医院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Ping An Insurance Company of China（中国平安保险（集团）股份有限公司）；Zhejiang Provincial People’s Hospital（浙江省人民医院）
Lymph node station (LNS) delineation from computed tomography (CT) scans is an indispensable step in radiation oncology workflow. High inter-user variabilities across oncologists and prohibitive laboring costs motivated the automated approach. Previous works exploit anatomical priors to infer LNS based on predefined ad-hoc margins. However, without voxel-level supervision, the performance is severely limited. LNS is highly context-dependent - LNS boundaries are constrained by anatomical organs - we formulate it as a deep spatial and contextual parsing problem via encoded anatomical organs. Thi…
Deepwise AI Lab（深睿医疗人工智能实验室）；School of Electronics Engineering and Computer Science, University of Peking（北京大学电子工程与计算机科学学院）；School of Automation, University of Northwestern Polytechnical（西北工业大学自动化学院）；Department of Computer Science, University of Hong Kong（香港大学计算机科学系）
Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net consists of three relation modules: 1. the anatomical structure relation module encoding spatial relations between diseases and anatomical parts. 2. the contextual relation module aggregating clues based on query-key pair of disease RoI and lung fields. 3. the disease relation modul…
Attention-Driven Framework for Non-Rigid Medical Image Registration
Department of Computer Sciences, Quaid-i-Azam University (QAU)（夸赞大学计算机科学系）；School of Engineering and Technology, Centre for Intelligent Systems, CQU Sydney（悉尼大学工程与技术学院）；MBZUAI（穆扎布哈大学）；UNSW Sydney（悉尼新南威尔士大学）
A Computational Pipeline for Patient-Specific Modeling of Thoracic Aortic Aneurysm: From Medical Image to Finite Element Analysis
Department of Computer Science, University of Miami（迈阿密大学计算机科学系）；Sutra Medical Inc（Sutra医疗公司）；Aortic Institute at Yale-New Haven Hospital, Yale University School of Medicine（耶鲁-纽黑文医院主动脉研究所，耶鲁大学医学院）
Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesis
Centre de recherche du CHU de Québec-Université Laval（魁北克大学拉瓦尔医院研究中心）；Centre de recherche de l’Institut universitaire de cardiologie et de pneumologie de Québec-Université Laval（魁北克大学拉瓦尔心血管与呼吸病学研究所）
Leveraging Anatomical Constraints with Uncertainty for Pneumothorax Segmentation
Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Duke University（杜克大学）；Singapore General Hospital（新加坡中央医院）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）
Fluorescent Neuronal Cells v2: Multi-Task, Multi-Format Annotations for Deep Learning in Microscopy
National Institute of Nuclear Physics（国家核物理研究所）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；University of Bologna（博洛尼亚大学）
AirMorph: Topology-Preserving Deep Learning for Pulmonary Airway Analysis
Institute of Medical Robotics, Shanghai Jiao Tong University（上海交通大学医疗机器人研究院）；Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University（上海交通大学图像处理与模式识别研究所）；Shanghai Chest Hospital（上海市胸科医院）
Technical University of Munich（慕尼黑工业大学）；University Medical Center Freiburg（弗莱堡大学医学中心）
With the advent of deep learning algorithms, fully automated radiological image analysis is within reach. In spine imaging, several atlas- and shape-based as well as deep learning segmentation algorithms have been proposed, allowing for subsequent automated analysis of morphology and pathology. The first Large Scale Vertebrae Segmentation Challenge (VerSe 2019) showed that these perform well on normal anatomy, but fail in variants not frequently present in the training dataset. Building on that experience, we report on the largely increased VerSe 2020 dataset and results from the second iterat…
Department of Computer Science, Johns Hopkins University（约翰霍普金斯大学计算机科学系）；Department of Pharmacy and Biotechnology, University of Bologna（博洛尼亚大学药学与生物技术系）；Center for Biomolecular Nanotechnologies, Istituto Italiano di Tecnologia（意大利技术研究院生物分子纳米技术中心）；Faculty of Mathematics and Computer Science, Jagiellonian University（杰齐兰大学数学与计算机科学学院）；Department of Cardiology and Internal Medicine, University of Warmia and Mazury（马尔堡大学心内科与内科系）；Diagnostic and Treatment Center Gammed（Gammed诊断与治疗中心）；Department of Bioengineering, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校生物工程系）；Department of General Surgery, Peking University Third Hospital（北京大学第三医院普外科）；Department of Radiology & Biomedical Imaging, University of California, San Francisco（加州大学旧金山分校放射科与生物医学成像系）；Department of Bioengineering, University of California, Berkeley（加州大学伯克利分校生物工程系）；Department of Radiation Oncology, Johns Hopkins School of Medicine（约翰霍普金斯医学院放射肿瘤学系）；NVIDIA Code, Models & Data（NVIDIA代码、模型与数据）
University of Toronto（多伦多大学）；Sunnybrook Research Institute（桑尼布鲁克研究所）；Western University（西部大学）
Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new …
