In this work, we exploit the task of joint classification and weakly supervised localization of thoracic diseases from chest radiographs, with only image-level disease labels coupled with disease severity-level (DSL) information of a subset. A convolutional neural network (CNN) based attention-guided curriculum learning (AGCL) framework is presented, which leverages the severity-level attributes mined from radiology reports. Images in order of difficulty (grouped by different severity-levels) are fed to CNN to boost the learning gradually. In addition, highly confident samples (measured by classification probabilities) and their corresponding class-conditional heatmaps (generated by the CNN) are extracted and further fed into the AGCL framework to guide the learning of more distinctive convolutional features in the next iteration. A two-path network architecture is designed to regress the heatmaps from selected seed samples in addition to the original classification task. The joint learning scheme can improve the classification and localization performance along with more seed samples for the next iteration. We demonstrate the effectiveness of this iterative refinement framework via extensive experimental evaluations on the publicly available ChestXray14 dataset. AGCL achieves over 5.7\% (averaged over 14 diseases) increase in classification AUC and 7%/11% increases in Recall/Precision for the localization task compared to the state of the art.
Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
KAIST(韩国科学技术院)
气胸是一种相对常见的疾病,但在某些情况下,它可能很难发现胸部X线摄影。在本文中,我们提出了一种在胸部X光检查中检测气胸的新方法。我们提出了一个集成模型的相同的卷积神经网络(CNN)与三个不同大小的射线照相图像。传统的方法可能无法正确地表征丢失的特征,同时将大尺寸图像重新定位为256 x 256或224 x 224尺寸。我们的模型与胸部X射线数据集,其中包含超过100,000个胸部X射线摄影图像进行了评估。作为实验的结果,所提出的模型显示AUC 0.911,这是气胸检测的最新结果。我们的方法预计将是有效的应用时,CNN大尺寸的医学图像。
OXnet: Omni-supervised Thoracic Disease Detection from Chest X-rays
The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of Science and Technology(香港科技大学);Imsight AI Research Lab(Imsight人工智能研究实验室);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Anatomy-Structured Hierarchical MIL for Weakly-Supervised Thoracic Disease Detection in Chest X-rays
Ewha Womans University(梨花女子大学);Ewha Medical Artificial Intelligence Research Institute(梨花女子大学医学人工智能研究所);REMEDI Inc.(瑞美迪公司);Ewha Womans University Seoul Hospital(梨花女子大学首尔医院)
Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment
Massachusetts Institute of Technology(麻省理工学院);Philips Research North America(飞利浦北美研究院);Beth Israel Deaconess Medical Center, Harvard Medical School(哈佛医学院贝斯以色列女执事医疗中心)
An Ordinal Regression Framework for a Deep Learning Based Severity Assessment for Chest Radiographs
RWTH Aachen University Hospital(亚琛工业大学医院);Visual Computing Institute, RWTH Aachen University(亚琛工业大学视觉计算研究所);Institute of Medical Informatics, RWTH Aachen University Hospital(亚琛工业大学医院医学信息学研究所);Department of Oral and Maxillofacial Surgery, RWTH Aachen University Hospital(亚琛工业大学医院口腔颌面外科)
From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
Perceptra Co., Ltd.(Perceptra有限公司);Radiology Department, Faculty of Medicine Siriraj Hospital, Mahidol University(玛希隆大学诗里拉吉医院医学院放射科);Institute of Field Robotics, King Mongkut’s University of Technology Thonburi(泰国国王科技大学吞武里分校野外机器人研究所)
A Generative Foundation Model for Chest Radiography
Department of Radiation Oncology, Stanford University School of Medicine(斯坦福大学医学院放射肿瘤科);Department of Computer Science, School of Computing and Data Science, The University of Hong Kong(香港大学计算机科学系);Department of Population Medicine and Diagnostic Sciences, College of Veterinary Medicine, Cornell University(康奈尔大学兽医学院人口医学与诊断科学系);Department of Radiology, The First Affiliated Hospital of Jinan University(暨南大学第一附属医院放射科);Department of Radiology, Stanford University School of Medicine(斯坦福大学医学院放射科);Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系);Department of Biomedical Informatics, Harvard Medical School(哈佛医学院生物医学信息学系)
CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs
Stanford Center for Artificial Intelligence in Medicine and Imaging, Stanford University(斯坦福大学医学与影像人工智能中心);Department of Radiology, Stanford University(斯坦福大学放射学系)
HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology & Neuroscience, King’s College London(生物统计学与健康信息学系,精神病学、心理学与神经科学研究所,伦敦国王学院)
Automated Estimation of Total Lung Volume using Chest Radiographs and Deep Learning
Radboud university medical center(拉德堡德大学医学中心)
肺总容积是一种重要的定量生物标志物,用于评估限制性肺部疾病。在这项研究中,我们研究了几种深度学习方法的性能,用于自动测量胸片中的总肺容量。从有胸部CT的患者中收集了7621张后前位和侧位胸片(CXR)。同样,从具有肺功能检查(PFT)结果的患者中选择了928项CXR研究。分别根据CT或PFT数据上的肺分割计算参考总肺体积。该数据集用于训练深度学习架构,以根据胸片预测总肺容量。实验以逐步增加复杂性的方式构建,以证明仅使用CT衍生标签进行训练的效果和错误来源。最优模型在291例CXR研究中进行了测试,参考肺体积从PFT获得。最佳深度学习回归模型显示,使用正面和侧面胸片作为输入,MAE为408 ml,MAPE为8.1%,Pearson r = 0.92。CT衍生的标签对于预训练是有用的,但是通过用PFT衍生的标签微调网络来获得最佳性能。我们首次证明,最先进的深度学习解决方案可以从普通胸片中准确测量总肺容量。所提出的模型可用于获得总肺体积从常规采集的胸片在没有额外的成本,并可能是一个有用的工具,以确定随着时间的推移,定期提交胸部X射线的患者的趋势。
Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation
Centre for Perceptual and Interactive Intelligence(感知与交互智能中心);the Chinese University of Hong Kong(香港中文大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Sensetime Research(商汤科技研究院);Department of Electronic Engineering(电子工程系)
Deep Learning to Quantify Pulmonary Edema in Chest Radiographs
Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Harvard Medical School(哈佛医学院);Massachusetts Institute of Technology(麻省理工学院);Philips Research(飞利浦研究院)
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
Imperial College London(帝国理工学院);Causality in Healthcare AI Hub(医疗AI因果关系中心);University of Edinburgh(爱丁堡大学);Cleveland Clinic London(克利夫兰诊所伦敦);Department of Perioperative Medicine, CHU Clermont-Ferrand(克莱蒙费朗大学医院围手术期医学科);Department of Medicine, Massachusetts General Hospital(麻省总医院医学部);Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所)
A Generic Approach to Lung Field Segmentation from Chest Radiographs using Deep Space and Shape Learning
Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Health System(儿童国家卫生系统谢赫扎耶德儿科外科创新研究所);Children’s National Health System(儿童国家卫生系统);San Francisco State University(旧金山州立大学);School of Medicine and Health Sciences, George Washington University(乔治华盛顿大学医学与健康科学学院)
已提出将计算机辅助诊断(CAD)技术用于成人队列的胸片(CXR)肺野分割,但很少用于儿科受试者。统计形状模型(SSM),最先进的基于CXR的肺野分割方法的主力,不能有效地适应在儿科发育阶段的肺野的形状变化。我们工作的主要贡献是:(1)来自CXR的通用肺野分割框架,适应成人和儿科队列的大形状变化;(2)深度表示学习检测机制\emph{ensemble space learning},用于鲁棒的对象定位;以及(3)\emph{marginal shape deep learning},用于形状变形参数估计。与传统SSM的迭代方法不同,所提出的形状学习机制将参数空间转换为边缘子空间,这些边缘子空间使用递归表示学习机制有效地求解。此外,我们的方法是第一个在基于CXR的肺分割中包括具有挑战性的心脏后区域,以进行准确的肺活量估计。该框架在3个月至89岁的患者的668个CXR上进行评估。我们得到平均Dice相似系数为$0.96\pm0.03$(包括心脏后区域)。对于一个给定的精度,所提出的方法也被发现比传统的基于SSM的迭代分割方法更快。所提出的通用框架的计算简单性可以类似地应用于其他可变形对象的快速分割。