人工智能在新型冠状病毒肺炎早期影像诊断中的应用

目的 探讨人工智能(AI)辅助胸部CT在新型冠状病毒肺炎(COVID-19)早期定量诊断中的应用价值.方法 选取经病毒核酸检测确诊为COVID-19的患者60例,所有患者均为早期感染,在出现症状3 d内接受胸部CT平扫检查.定量分析患者胸部CT中不同密度范围内病变体积、病变平均密度、病灶/全肺体积和病灶/肺叶体积.由2...     

人工智能在新型冠状病毒肺炎临床分型中的应用

目的 探讨人工智能在诊断新型冠状病毒肺炎(COVID-19)临床分型中的应用价值.方法 对158例最终经深圳疾控中心核酸检测阳性确诊COVID-19患者的胸部CT影像资料进行回顾性分析.把临床分型为普通型、重型、危重型的患者分为普通型和重型/危重型2组,应用推想科技影像人工智能软件(InferReadTM CT Pne...     

人工智能辅助影像学在新型冠状病毒肺炎诊治中的研究进展

目前新型冠状病毒肺炎（COVID-19）疫情仍在全球大流行,影像学检查可对疑似患者进行筛查、诊断、疗效评价及预后判断,并有利于科学地抗击疫情。人工智能（AI）技术有望克服影像学中人工阅片工作量大、主观性强、缺乏量化标准等不足,是COVID-19研究的热点之一。本文重点阐述AI辅助胸部X线和CT在COVID-19诊治中的...     

人工智能肺炎诊断系统在新型冠状病毒肺炎疫情期间胸部CT检查中的应用

目的 分析新型冠状病毒肺炎疫情期间人工智能(AI)在胸部CT诊断检查中的效能.方法 选取2020年2月至4月间行胸部CT扫描的受检者5 000例,分别通过AI和2名资深胸部影像诊断医师进行分析检测.结果 5 000例患者中,真阳性共1 084例,诊断正确率、错误率、灵敏度分别是72％、27％、47％.结论 AI在肺炎C...     

全球新型冠状病毒疫苗研发进展

2019年底暴发的新型冠状病毒肺炎疫情迅速席卷全球,造成了大量人员感染和死亡.应对疫情最有效的举措之一是加快疫苗研发与大规模临床应用.过去一年多以来,全球科学家为新型冠状病毒疫苗的研发与应用开展了大量的工作.该文综述了病毒灭活疫苗、减毒活病毒疫苗、亚单位疫苗、病毒载体疫苗、核酸疫苗等研发的主要技术路线,分析了全球新型冠...     

人工智能技术在新型冠状病毒肺炎诊治中的应用及价值

新型冠状病毒肺炎(COVID-19)全球大流行,导致医疗系统负担沉重,并造成全球范围大规模经济危机.人工智能(AI)技术作为一种新型高效的工具,对全面抗击COVID-19疫情起到举足轻重的作用.包括但不局限于从对疑似COVID-19患者进行筛查到对确诊感染患者进行辅助诊断、疗效评估及预后分析;从治疗方案设计的优化到加速...     

新型冠状病毒肺炎的研究进展

新型冠状病毒肺炎(COVID-19)临床上分为轻型、普通型、重型和危重型,轻型患者占大多数,一般无肺炎症状,主要表现为发热、乏力和干咳,少数伴鼻塞、流涕、咽痛和腹泻等;而重型和危重型发病后高热不退,1周后会出现呼吸困难和低氧血症,死亡率较高[1-3].笔者回顾性分析COVID-19的病原学简介、流行病学特点、致病机制及...     

Current status quo on COVID-19 including chest imaging

With each day the number coronavirus disease 2019 (COVID-19) cases continue to rise rapidly and our imaging knowledge of this disease is expeditiously evolving. The role of chest computed tomography (CT) in the screening or diagnosis of COVID-19 remains the subject of much debate. Despite several months having passed since identifying the disease, and numerous studies related to it, controversy and concern still exists regarding the widespread use of chest CT in the evaluation and management of COVID-19 suspect patients. Several institutes and organizations around the world have released guidelines, recommendations and statements against the use of CT for diagnosing or screening COVID-19 infection and advocating its use only for those cases with a strong clinical suspicion of complication or an alternate diagnosis. However, these guidelines and recommendations are in disagreement with majority of the widely available literature, which strongly favour CT as a pivotal tool in the early diagnosis, management and even follow-up of COVID-19 infection. This article besides comprehensively reviewing the current status quo on COVID-19 disease in general, also writes upon the current consensus statements/recommendations on the use of diagnostic imaging in COVID-19 as well as highlighting the precautions and various disinfection procedures being employed world-wide at the workplace to prevent the spread of infection.     

人工智能定量测量对新型冠状病毒肺炎患者胸部CT炎性病灶动态变化的评估价值

目的:探讨人工智能（AI）辅助定量测量评估新型冠状病毒肺炎（COVID-19）胸部CT动态变化的价值。方法:回顾性分析2020年1月15日至3月10日在华中科技大学同济医学院附属武汉市中心医院接受治疗的99例确诊COVID-19患者的临床和胸部CT动态影像资料。依据最终诊断,99例患者分为普通型（36例）、重型（33例...     

Abdominal imaging in COVID-19

Initially thought of as a respiratory infection, coronavirus disease-2019 (COVID-19) is now recognized as a complex disease with a wide clinical spectrum, including digestive involvement. While several studies have evaluated chest imaging findings in COVID-19, few papers have looked at the abdominal imaging features of these patients. Liver, biliary, pancreas and bowel involvement have been reported in COVID-19 infected patients. In this review, we aim to summarize currently available data related to abdominal imaging techniques in COVID-19, in accordance with relevant clinical and laboratory workup of these patients. Underlying mechanisms, indications and imaging findings related to COVID-19 are discussed based on published data. Also, practice points for clinicians are highlighted in order to adequately recognize digestive-related injuries of severe acute respiratory syndrome coronavirus 2 infection. While there’s been a steady accumulation of data with respect to abdominal imaging findings in COVID-19, currently available recommendations are based on limited research. There is a wide spectrum of abdominal imaging findings in COVID-19, which includes hepato-biliary, pancreatic and luminal pathology.     

医学影像人工智能新进展

随着人工智能（AI）与各个领域的结合,AI已经成为当今社会的研究热点。目前医疗行业人员的短缺及医学诊断准确率的提高使得AI在医疗行业的应用非常重要,尤其是医学影像诊断方面。AI辅助诊断将会提高疾病的检出率,为临床医师提供更有效的诊断和治疗信息,同时减少影像医师的重复工作,节省出更多的时间研究疑难病例。笔者简要介绍医学影像AI,结合国内外最新和最有影响力的研究成果,阐述医学影像AI的研究新进展。     

Computer-aided diagnosis and artificial intelligence in clinical imaging

Computer-aided diagnosis (CAD) is rapidly entering the radiology mainstream. It has already become a part of the routine clinical work for the detection of breast cancer with mammograms. The computer output is used as a "second opinion" in assisting radiologists' image interpretations. The computer algorithm generally consists of several steps that may include image processing, image feature analysis, and data classification via the use of tools such as artificial neural networks (ANN). In this article, we will explore these and other current processes that have come to be referred to as "artificial intelligence." One element of CAD, temporal subtraction, has been applied for enhancing interval changes and for suppressing unchanged structures (eg, normal structures) between 2 successive radiologic images. To reduce misregistration artifacts on the temporal subtraction images, a nonlinear image warping technique for matching the previous image to the current one has been developed. Development of the temporal subtraction method originated with chest radiographs, with the method subsequently being applied to chest computed tomography (CT) and nuclear medicine bone scans. The usefulness of the temporal subtraction method for bone scans was demonstrated by an observer study in which reading times and diagnostic accuracy improved significantly. An additional prospective clinical study verified that the temporal subtraction image could be used as a "second opinion" by radiologists with negligible detrimental effects. ANN was first used in 1990 for computerized differential diagnosis of interstitial lung diseases in CAD. Since then, ANN has been widely used in CAD schemes for the detection and diagnosis of various diseases in different imaging modalities, including the differential diagnosis of lung nodules and interstitial lung diseases in chest radiography, CT, and position emission tomography/CT. It is likely that CAD will be integrated into picture archiving and communication systems and will become a standard of care for diagnostic examinations in daily clinical work.     

人工智能在心脏影像诊断中的研究进展

人工智能(AI)中的传统机器学习和深度学习依赖于数据的训练来实现对疾病精确诊断及分类,在心脏影像诊断中各具优势。近年AI在心脏超声、CT、MRI、单光子发射体层成像(SPECT)和正电子发射体层成像(PET)中的应用以心脏分割和快速成像为核心,不断深入对低辐射剂量扫描、精确的自动化数据测量以及准确的预后评估的研究。就AI基本原理及基于AI的不同影像检查方法在心脏成像中的研究进展予以综述。     

Thoracic imaging outcomes in COVID-19 survivors

The coronavirus disease 2019 (COVID-19) pandemic presents a significant global public health challenge. One in five individuals with COVID-19 presents with symptoms that last for weeks after hospital discharge, a condition termed “long COVID”. Thus, efficient follow-up of patients is needed to assess the resolution of lung pathologies and systemic involvement. Thoracic imaging is multimodal and involves using different forms of waves to produce images of the organs within the thorax. In general, it includes chest X-ray, computed tomography, lung ultrasound and magnetic resonance imaging techniques. Such modalities have been useful in the diagnosis and prognosis of COVID-19. These tools have also allowed for the follow-up and assessment of long COVID. This review provides insights on the effectiveness of thoracic imaging techniques in the follow-up of COVID-19 survivors who had long COVID.