基于深度学习的新型冠状病毒肺炎转归胸部CT评价

目的 分析基于深度学习的新型冠状病毒肺炎（COVID-19）不同临床转归患者胸部CT的差异,以提高对COVID-19转归的影像认识。 方法 回顾性分析2020年1月25日至3月29日来自内蒙古自治区COVID-19病例库的42例COVID-19患者（临床分型为普通型）的胸部CT资料,其中,男性20例、女性22例,年龄17个月~86岁[（48.74±17.18）岁]。根据是否转为重症（重型或危重型）将患者分为未转为重症的A组（n=29）和转为重症的B组（n=13）,比较2组患者年龄、性别及基于深度学习的胸部CT表现,评价感染肺叶病灶分布,累及肺叶侧别、数目,感染肺叶病灶体积,密度（CT值）和感染肺叶病灶体积占比等资料的差异。计量资料的比较采用两独立样本t检验、Mann-Whitney U非参数检验;计数资料的比较采用卡方检验或Fisher's确切概率法。 结果 2组患者的性别差异无统计学意义（χ2=0.016,P=1.000）。B组患者的年龄高于A组[（65.62±11.24）岁对（41.17±13.66）岁 ],且差异有统计学意义（t=5.64,P<0.001）。B组患者感染肺叶数以及各肺叶感染体积占比、总感染体积占比均高于A组,且差异有统计学意义（Z=2.505~3.605,均P<0.05）。2组患者肺部总体积差异无统计学意义（Z=1.456,P=0.146）,B组患者各肺叶感染体积及双肺总感染体积均高于A组,且差异有统计学意义（Z=2.301~3.254,均P<0.05）;B组患者在各CT阈值范围内的肺部感染体积占比均高于A组,且差异有统计学意义（Z=3.115~3.578,均P<0.05）。胸部CT和人工智能病灶识别图的图像结果显示,病灶均以磨玻璃密度影、实变为主,双肺下叶感染较多,右肺中叶较少。 结论 转为重症的COVID-19患者的胸部CT明显有别于未转为重症的患者。基于深度学习的人工智能可尽早评估有重症转归倾向的患者,有助于COVID-19重症率的控制。     

Chest Imaging in Patients Hospitalized With COVID-19 Infection - A Case Series

COVID-19 (Corona Virus Disease-19) is a zoonotic illness first reported in the city of Wuhan, China in December 2019, and is now officially a global pandemic as declared by the World Health Organization. The infection is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). COVID-19 infected patients can be asymptomatic carriers or present with mild-to-severe respiratory symptoms. Imaging, including computed tomography is not recommended to screen/diagnose COVID-19 infections, but plays an important role in management of these patients, and to rule out alternative diagnoses or coexistent diseases. In our multicenter case series, we outline the clinical presentations and illustrate the most common imaging manifestations in patients hospitalized with COVID-19.     

胸部疾病CT诊断的评价

本文通过２６１例Ｘ线与ＣＴ诊断比较，评价胸部ＣＴ在胸部疾病诊断中的价值。结果是（１）弥漫病变ＣＴ诊断正确率为８７．５％，Ｘ线为５８．９％；（２）纵隔肿块ＣＴ诊断正确率为６０．１％，Ｘ线为４８．０％；（３）胸膜肿块ＣＴ诊断正确率为７５．０％，Ｘ线为６６．６％；（４）肺段肺叶阴影ＣＴ诊断正确率为７１．０％，Ｘ线为６８．４％；（５）球块阴影ＣＴ诊断正确率为７３．０％，Ｘ线为７１．０％；（６）斑片阴影ＣＴ诊断正确率为６６．０％，Ｘ线为７２．０％。分析材料表明在Ｘ线检查基础上根据胸部疾病基本影像，在普遍胸部ＣＴ检查上附加高分辨、薄层及增强扫描可提高一些ＣＴ征象发现率，同时可以使胸部疾病ＣＴ诊断水平超过本文报道的水平。     

回顾性心电门控-支气管动脉CT成像前瞻性研究

目的 分别应用回顾性心电门控和常规螺旋CT扫描技术对支气管动脉(BA)进行CT成像,并探讨BA显示的差异.方法 将120例在本院行胸部肺动脉期增强CT的患者随机分为三组,每组40例,A组应用回顾性心电门控技术,B组和C组采用64排螺旋CT扫描技术,扫描速度分别为0.4 s/r和0.5 s/r,对BA的纵隔段及叶段采用容积再现(VR)、最大密度投影(MIP)、多平面重组(MPR)等后处理技术进行显示,并评价图像质量.结果 (1)A组纵隔段和叶段BA的显示率分别为100％和62％,高于B组和C组;A组图像质量评级为“优良”的血管为66个(66/95),高于B组和C组.A组肺动脉期扫描的平均有效剂量为15.6 mSv,高于B组和C组.(2)B组纵隔段和叶段BA的显示率分别为89％和33％,高于C组.B组图像质量评级为“优良”的血管30个(30/84),高于C组的11个(11/63).B组的平均扫描时间为3.2s,仅为A组(9 s)的36％.结论 回顾性心电门控-BA-CTA可提高BA的成像质量,但有效剂量(ED)偏大.使用0.4 s/r的64排螺旋CT扫描,BA的显示率和图像质量居中,有降低有效剂量和缩短扫描时间的优点,适用于咯血等急诊患者BA的CTA检查.     

Implementing a Novel Through-Glass Chest Radiography Technique for COVID-19 Patients: Image Quality,Radiation Dose Optimization,and Practical Considerations

Rationale and objectives: The novel coronavirus (COVID-19) pandemic has presented many logistical challenges, including unprecedented shortages of personal protective equipment (PPE). A technique of obtaining portable chest radiographs (pCXR) through glass doors or windows to minimize technologist-patient contact and conserve PPE has gained popularity, but remains incompletely evaluated in the literature. Our goal was to quickly implement this technique and evaluate image quality and radiation dose. Materials and methods: An infographic and video were developed to educate nurses and technologists on the through-glass pCXR technique. Imaging parameters were optimized using a phantom and scatter radiation was measured. Three reviewers independently evaluated 100 conventionally obtained and 100 through-glass pCXRs from March 13, 2020 to April 30, 2020 on patients with suspected COVID-19, using criteria for positioning and sharpness/contrast on a 1 (confident criteria not met) to 5 (confident criteria met) scale. Imaging parameters, including deviation index (DI) were recorded for all radiographs. Results: The through-glass method was rapidly adopted and conserved one isolation gown per interaction. Although there was a statistically significant difference in the positioning (P value 0.018) and sharpness/contrast (P value 0.016), the difference in mean ratings was small: 4.82 vs 4.65 for positioning and 4.67 vs 4.50 (conventional vs modified) for sharpness/contrast. Scatter radiation was measured using a thorax phantom and found to be acceptable for the patient and nearby personnel. Standard deviation was higher for the DI for the through-glass technique (2.8) compared to the conventional technique (1.8), although the means were similar. Conclusion: The through-glass technique was quickly implemented, producing diagnostic quality chest radiographs while conserving PPE and reducing risks to radiology staff. There was more variability with imaging technique and DI using the through-glass technique, likely due to technologist uncertainty regarding technical modifications. Further work to reduce this variation is necessary to optimize quality and dose.     

Optimizing Imaging Quality and Radiation Dose by the Age-Dependent Setting of Tube Voltage in Pediatric Chest Digital Radiography

Objective

The quality and radiation dose of different tube voltage sets for chest digital radiography (DR) were compared in a series of pediatric age groups.

Materials and Methods

Forty-five hundred children aged 0-14 years (yr) were randomly divided into four groups according to the tube voltage protocols for chest DR: lower kilovoltage potential (kVp) (A), intermediate kVp (B), and higher kVp (C) groups, and the fixed high kVp group (controls). The results were analyzed among five different age groups (0-1 yr, 1-3 yr, 3-7 yr, 7-11 yr and 11-14 yr). The dose area product (DAP) and visual grading analysis score (VGAS) were determined and compared by using one-way analysis of variance.

Results

The mean DAP of protocol C was significantly lower as compared with protocols A, B and controls (p < 0.05). DAP was higher in protocol A than the controls (p <0.001), but it was not statistically significantly different between B and the controls (p = 0.976). Mean VGAS was lower in the controls than all three protocols (p < 0.001 for all). Mean VGAS did not differ between protocols A and B (p = 0.334), but was lower in protocol C than A (p = 0.008) and B (p = 0.049).

Conclusion

Protocol C (higher kVp) may help optimize the trade-off between radiation dose and image quality, and it may be acceptable for use in a pediatric age group from these results.     

双能减影与常规数字摄影的胸部影像对比研究

目的比较双能减影(DES)和常规数字摄影(DR)对胸部结构的显示能力。资料与方法连续抽取100例胸部DES和DR图像，由3位放射科医师评价两种检查方法对胸部肺纹理、气管支气管和骨骼的显示效果，分别计算两种检查方法的优显率。结果DES对肺野内中带肺纹理、气管、右主支气管、右上叶支气管开口、中间支气管、左上叶支气管开口、肺野内肋骨的显示优于DR；DR对肺野外带肺纹理、心影后肺纹理、膈下肺纹理、左主支气管、左下叶支气管、胸廓边缘肋骨、心影后肋骨、膈下肋骨、胸椎、锁骨、肩胛骨的显示优于DES。结论DES能分别观察胸部软组织与骨骼，提供更多的影像信息，是DR有益的补充。     

Chest CT findings of coronavirus disease 2019 (COVID-19): A comprehensive meta-analysis of 9907 confirmed patients

ObjectivesWe performed a systematic review and meta-analysis of the prevalence of chest CT findings in patients with confirmed COVID-19 infection.MethodsSystematic review of the literature was performed using PubMed, Scopus, Embase, and Google Scholar to retrieve original studies on chest CT findings of patients with confirmed COVID-19, available up to 10 May 2020. Data on frequency and distribution of chest CT findings were extracted from eligible studies, pooled and meta-analyzed using random-effects model to calculate the prevalence of chest CT findings.ResultsOverall, 103 studies (pooled population: 9907 confirmed COVID-19 patients) were meta-analyzed. The most common CT findings were ground-glass opacities (GGOs) (77.18%, 95%CI = 72.23–81.47), reticulations (46.24%, 95%CI = 38.51–54.14), and air bronchogram (41.61%, 95%CI = 32.78–51.01). Pleural thickening (33.35%, 95%CI = 21.89–47.18) and bronchial wall thickening (15.48%, 95%CI = 8.54–26.43) were major atypical and airway findings. Lesions were predominantly distributed bilaterally (75.72%, 95%CI = 70.79–80.06) and peripherally (65.64%, 95%CI = 58.21–72.36), while 8.20% (95%CI = 6.30–10.61) of patients had no abnormal findings and pre-existing lung diseases were present in 6.01% (95%CI = 4.37–8.23).ConclusionsThe most common CT findings in COVID-19 are GGOs with/without consolidation, reticulations, and air bronchogram, which often involve both lungs with peripheral distribution. However, COVID-19 might present with atypical manifestations or no abnormal findings in chest CT, which deserve clinicians' notice.     

Chest CT imaging features and clinical outcome of coronavirus disease 2019 (COVID-19): A single-center case study in Ningbo,China

ObjectiveThe purpose of this study was to investigate the chest CT imaging features and clinical outcome of coronavirus disease 2019 (COVID-19) in Ningbo, China.MethodsIn this retrospective study, twenty-eight confirmed and seven highly suspected cases of COVID-19 were enrolled in Ningbo first hospital from January 26, 2020 to March 5, 2020. Cases were confirmed by real-time polymerase chain reaction (RT-PCR). The initial and follow-up chest CT imaging features, epidemiological history, and outcome were analyzed.ResultsThe average age of the patients was 57.3 ± 15.3 years (range: 27–96 years), including 25 females and 10 males. On CT images, 89.3% (25/28) confirmed and 100% (7/7) suspected patients had ground-glass opacities (GGOs), and GGOs with mixed consolidations were observed in 35.7% (10/28) confirmed and 42.9% (3/7) suspected cases, most of these lesions were distributed under the peripheral of both lungs. 17 confirmed and 4 suspected cases had a history of participating in Ningbo Tian-tong Temple rituals and all had GGOs in their lungs during the initial CT scan. As of March 25, 2020, the lung lesions of our cases were significantly resolved and all patients have been discharged from the hospital.ConclusionThe most common chest CT features are multiple bilateral and peripheral GGOs with mixed consolidations or not in the lungs of patients with COVID-19. Chest CT plays an important role in the diagnosis and monitoring treatment response of this disease. There was no reported death in our cases.     

Characterization of Pediatric Imaging Trends and Likelihood of Exam Cancellation in the COVID-19 Pandemic

1. Download : Download high-res image (60KB)
2. Download : Download full-size image

     

肾移植术后卡氏肺孢子虫肺炎X线平片和CT表现

目的 探讨肾移植术后卡氏肺孢子虫肺炎的X线、CT表现特征.资料与方法 对6例经病理证实肾移植术后卡氏肺孢子虫肺炎患者的胸部X线平片(6例)和CT资料(5例)进行回顾性分析.结果 6例X线平片中,3例双肺呈弥漫性磨玻璃阴影,3例呈斑片状、网状结节影;1例合并气胸.5例CT检查中,主要表现为肺部磨玻璃影,间以线状、条状及网状小结节影;4例胸膜下见"月弓征",3例见肺气囊;合并肺门、纵隔淋巴结肿大3例,合并气胸l例.结论 卡氏肺孢子虫肺炎影像学表现呈多样性,CT对其诊断较X线平片敏感,最后确诊仍需病理.