Current Concepts Imaging in COVID-19 and the Challenges for Low and Middle Income Countries

Abstract

With nearly 3,800,000 cases and 270,000 deaths reported worldwide, COVID-19 is a global pandemic unlike any we have seen in our lifetimes (1). As early as 1995, the WHO was warning of a global infectious disease crisis, citing 30 new infectious diseases emerging in the past 20 years, loss of antibiotic effectiveness, low rates of immunization, poverty, and inadequate investment in public health contributing to the more than 17 million people dying each year from infectious diseases, principally in Low and Middle Income countries (LMIC) (2). Unlike previous infectious diseases, at the time of this writing over 63% of the total reported cases of COVID-19 are in 6 High Income Countries (HIC): USA, Italy, Spain, France, Germany and the UK. Information concerning the imaging findings in COVID-19 has been rapidly disseminated from the centers first affected by the pandemic. This article attempts to summarize the current state of knowledge regarding the imaging findings in COVID-19, focusing on pulmonary findings, and offer recommendation for the use of imaging for diagnosis and surveillance of COVID-19, particularly in LMIC.

On the role of artificial intelligence in medical imaging of COVID-19

“…40 A key diagnostic challenge is the non-specificity of COVID-19 patterns and their differentiation from non-COVID-19 viral pneumonia. 41 Here, non-imaging assessments such as anamnesis can contribute to the diagnosis. Second, asymptomatic patients with unaffected lungs are notoriously challenging to be detected.…”

On the Role of Artificial Intelligence in Medical Imaging of COVID-19

“…We highlight that imaging is not recommended for COVID-19 diagnosis by the ACR due to overlapping symptoms with viral infections. CT should be reserved for cases with inconclusive findings in initial assessments via CXR and LUS and LUS can be performed as first-line examination during triage [21]. Notably, clinical diagnosis should by no means solely base on algorithmic predictions.…”

“…However, compared to nucleic acid tests, CTs may be more sensitive at a single time point for the diagnosis of COVID-19 40 . A key diagnostic challenge is the non-specificity of COVID-19 patterns and their differentiation from non-COVID-19 viral pneumonia 41 . Here, non-imaging assessments like anamnesis can contribute to the diagnosis.…”

“…However, while chest CT may have improved sensitivity, the American College of Radiology (ACR) conservatively discourages to use imaging for diagnosis † . The two main diagnostic challenges are the differentiation from † https://www.acr.org/Advocacy-and-Economics/ACR-Position-Statements/Recommendations-non-COVID-19 viral pneumonia [21] and the detection of asymptomatic patients with unaffected lungs.…”

“…Over the past decades, increasing evidence for the diagnostic value of US in pulmonary conditions such as ARDS or pneumothorax has led to increased recommendation of LUS [41], [42]. Especially for resourcelimited settings such as during triage or in low-income countries, LUS is superior to CXR in diagnosing pneumonia [43] or COVID-19 [44] and may resemble a viable first-line examination method [21]. SARS-CoV-2 induces patterns characteristic for viral pneumonia, most prevalently Blines (vertical, comet-tail artifacts arising from the pleural line [45]) and pleural line abnormalities such as pleural thickening [46].…”