Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review

Jacobi, Adam; Chung, Michael; Bernheim, Adam; Eber, Corey

doi:10.1016/j.clinimag.2020.04.001

Cited by 509 publications

(522 citation statements)

References 10 publications

Supporting

Mentioning

482

Contrasting

Unclassified

Order By: Relevance

“…The results achieved by the AI system compared to radiologist readings are noteworthy given the fact that the presentation of COVID-19 pneumonia on CXR can be highly variable ranging from peripheral opacifications only to diffuse opacifications making differentiation from other diseases challenging [5] [19] [20]. Chest radiographs may be normal initially or in mild disease, however Wong et al showed that of all patients with COVID-19 requiring hospitalization, 69% had an abnormal chest radiograph at admission [20].…”

Section: Discussionmentioning

confidence: 99%

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System

Murphy¹,

Smits²,

Knoops³

et al. 2020

Radiology

196

184

View full text Add to dashboard Cite

Background Chest radiography may play an important role in triage for coronavirus disease 2019 (COVID-19), particularly in low-resource settings. Purpose To evaluate the performance of an artificial intelligence (AI) system for detection of COVID-19 pneumonia on chest radiographs. Materials and Methods An AI system (CAD4COVID-XRay) was trained on 24 678 chest radiographs, including 1540 used only for validation while training. The test set consisted of a set of continuously acquired chest radiographs ( n = 454) obtained in patients suspected of having COVID-19 pneumonia between March 4 and April 6, 2020, at one center (223 patients with positive reverse transcription polymerase chain reaction [RT-PCR] results, 231 with negative RT-PCR results). Radiographs were independently analyzed by six readers and by the AI system. Diagnostic performance was analyzed with the receiver operating characteristic curve. Results For the test set, the mean age of patients was 67 years ± 14.4 (standard deviation) (56% male). With RT-PCR test results as the reference standard, the AI system correctly classified chest radiographs as COVID-19 pneumonia with an area under the receiver operating characteristic curve of 0.81. The system significantly outperformed each reader ( P < .001 using the McNemar test) at their highest possible sensitivities. At their lowest sensitivities, only one reader significantly outperformed the AI system ( P = .04). Conclusion The performance of an artificial intelligence system in the detection of coronavirus disease 2019 on chest radiographs was comparable with that of six independent readers. © RSNA, 2020

show abstract

Section: Discussionmentioning

confidence: 99%

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System

Murphy¹,

Smits²,

Knoops³

et al. 2020

Radiology

196

184

View full text Add to dashboard Cite

show abstract

“…However, when viewed retrospectively the two cases presented a clinical picture and laboratory changes (procalcitonin within the normal range, slight in ammation, and lymphopenia) compatible with a viral infection. The CXRs series of the rst patient showed lesions similar to those found in COVID-19 [10]. In addition, unlike the 25-year-old female patient who had no comorbidity, the 55-year-old male patient who had hypertension as comorbidity, developed a more severe acute respiratory distress which progressed to death.…”

Section: Discussionmentioning

confidence: 62%

On two cases of atypical respiratory distress in eastern Democratic Republic of the Congo months before the COVID-19 pandemic was declared: Could SARS-Cov-2 have been already spreading? Case report

Mateso¹,

Baguma²,

Mwene-Batu³

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundPredictions have been made that Africa would be the most vulnerable continent to the novel coronavirus disease 2019 (COVID-19). Interestingly, the spread of the disease in Africa seems to have been delayed and initially slower than in many parts of the World. Here we report on two cases which make us suspect that COVID-19 might have been present in our region before the official declaration of the disease in December 2019.Case presentationThese two cases (one 55-year-old man and one 25-year-old woman) of acute respiratory distress secondary to atypical pneumonia were seen in Bukavu, in eastern Democratic Republic of the Congo (DRC), between September and December 2019. One patient had returned from China and the other had close contacts with travellers from China in the 2 weeks prior to the onset of symptoms. In either case, the aetiology could not be accurately determined. However, the two cases presented a clinical picture (progressive dyspnoea, preceded by dry cough and fever) and laboratory changes (procalcitonin within the normal range, slight inflammation, and lymphopenia) compatible with a viral infection. The chest X-Rays series of the first patient showed lesions (reticulations, ground glass, and nodules ≤ 6 mm) similar to those found in COVID-19. In addition, unlike the 25-year-old female patient who had no comorbidity, the 55-year-old male patient who had hypertension as comorbidity, developed a more severe acute respiratory distress which progressed to death.ConclusionThese cases bring to the attention a number of facts which make us suspect that the COVID-19 epidemic may have already been present in the region months before the official beginning of the pandemic.

show abstract

“…However, many researchers found that patients with a positive RT-PCR may have a negative chest CT scan, and patients with a negative RT-PCR may have positive chest CT scan (4,7,12). Chest x-ray was regarded an insensitive tool reaching 69% (8,9,14,18).The American College of Radiologists (ACR) and the Fleischner Society have suggested that imaging is not advised for patients who tested positive by RT-PCR who were asymptomatic or have mild symptoms, and CT scan should be reserved for patients with a progressive disease course (19,20). Due to the high infectious rate of COVID-19 virus; infection control in radiology departments becomes a challenge in the CT scan suite, therefore, the ACR has also recommended that portable chest x-ray may be considered to minimize the risk of cross infection (14,19).…”

Section: Discussionmentioning

confidence: 99%

Chest X-Ray Findings and Temporal Lung Changes in Patients with COVID-19 Pneumonia

Rousan

El-Obeid

Karrar

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Chest CT scan and chest x-rays show characteristic radiographic findings in patients with COVID-19 pneumonia. Chest x-ray can be used in diagnosis and follow up in patients with COVID-19 pneumonia. The study aims at describing the chest x-ray findings and temporal radiographic changes in COVID-19 patients.Methods: From March 15 to April 20, 2020 patients with positive reverse transcription polymerase chain reaction (RT-PCR) for COVID-19 were retrospectively studied. Patients’ demographics, clinical characteristics, and chest x-ray findings were reported. Radiographic findings were correlated with the course of the illness and patients’ symptoms.Results: A total of 88 patients (50 (56.8%) females and 38 (43.2%) males) were admitted to the hospital with confirmed COVID-19 pneumonia. Their age ranged from 3-80 years (35.2 ±18.2 years). 48/88 (45%) were symptomatic, only 13/88 (45.5%) showed abnormal chest x-ray findings. A total of 190 chest x-rays were obtained for the 88 patients with a total of 59/190 (31%) abnormal chest x-rays. The most common finding on chest x-rays was peripheral ground glass opacities (GGO) affecting the lower lobes. In the course of illness, the GGO progressed into consolidations peaking around 6-11 days (GGO 70%, consolidations 30%). The consolidations regressed into GGO towards the later phase of the illness at 12-17 days (GGO 80%, consolidations 10%). There was increase in the frequency of normal chest x-rays from 9% at days 6- 11 up to 33% after 18 days indicating a healing phase. The majority (12/13, 92.3%) of patients with abnormal chest x-rays were symptomatic (P=0.005).Conclusion: The chest x-ray findings were similar to those reported on chest CT scan in patients with COVID-19, Chest x-ray can be used in diagnosis and follow up in patients with COVID-19 pneumonia.

show abstract

Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review

Cited by 509 publications

References 10 publications

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System

On two cases of atypical respiratory distress in eastern Democratic Republic of the Congo months before the COVID-19 pandemic was declared: Could SARS-Cov-2 have been already spreading? Case report

Chest X-Ray Findings and Temporal Lung Changes in Patients with COVID-19 Pneumonia

Contact Info

Product

Resources

About