March 18, 2020

COVID-19 GLOBAL PERSPECTIVES – THE RAPIDLY EVOLVING ROLE OF RADIOLOGY AND AI

March 18, 2020 [Updated on April 13 and May 18, 2020] – COVID-19 had affected 164 countries and territories around the world and 1 international conveyance (the Diamond Princess cruise ship harboured in Yokohama, Japan), the number of reported cases on March 18th exceeded 200,000 As of May 18, 2020, the Coronavirus is almost everywhere, with over 2.6 million active cases.

This is the seventh known Coronavirus to infect humans [1]. Two other notable examples include severe acute respiratory syndrome (SARS) and the Middle East respiratory syndrome (MERS), the former of which began in southern China and resulted in 774 deaths out of 8,098 infected individuals in 29 countries from November 2002 through July 2003, and the latter of which was first identified in Saudi Arabia and was responsible for 858 deaths among 2,494 individuals in 27 countries since September 2012 [2,3].

As COVID-19 spreads globally, there has been growing interest relating to the role of diagnostic imaging, appropriateness of Chest X-rays and CT scans when it comes to screening, detection and follow up management. There were also initial reports that indicated some technology startups were evaluating their machine learning algorithms to detect COVID-19 specific findings leveraging Chest X-rays and CT scans.

While the appropriateness of Chest X-rays or CT scans to pinpoint COVID-19 pneumonia is being evaluated, a group of Italian experts has been exploring the benefits of bedside ultrasound as one possible alternative for detection of COVID-19 pneumonia.

The data from Italy is preliminary and further studies are needed to confirm the role of lung ultrasound in the diagnosis and management of COVID-19, the authors are strongly recommending the use of bedside ultrasound for early diagnosis of COVID-19 pneumonia in all patients presenting to the emergency department with flu-like symptoms. The publication is available here.

Since there’s limited data, and we are still learning about this disease, and not enough peer-reviewed studies available regarding the role of AI, let’s focus first on the latest updates regarding the appropriateness of radiology imaging when it comes to detection and management of COVID-19.

UK: THE ROYAL COLLEGE OF RADIOLOGISTS UK, BSTI AND BIR

As of 12 March 2020, RCR UK view was that there is no current role for CT in the diagnostic assessment of patients with suspected Coronavirus infection in the UK. RCR did not believe that current evidence demonstrates a clear benefit in producing a definitive and positive management change based on CT information.

“CT does have a well-established role in the assessment of patients presenting with severe respiratory distress, particularly those that deteriorate clinically, based on specific advice from – and discussion with – intensive care and respiratory teams. This clinical assessment of the need for cross-sectional imaging will remain and while these requests may increase with increasing numbers of patients presenting with severe respiratory illness, we do not believe that patients with known or suspected coronavirus infection should be imaged any differently. The CT request should be based on clinical need and subsequent likely change to the clinical management plan.” RCR UK

The RCR noted that there is every chance that this advice will change over the coming days and weeks as the situation is changing rapidly. RCR is in ongoing contact with colleagues at the Academy of Medical Royal Colleges, NHSE/I, Public Health England and in the devolved nations, together with experts from the British Society of Thoracic Imaging (BSTI) and other chest-specific special interest groups and the Chief Medical Officers of the four nations. RCR is keen to ensure that their advice represents current best practice. Links to other useful sources of advice are available on RCR’s coronavirus resources page.

As of March 20, 2020 RCR UK provided the following update: The UK surgical Royal Colleges have produced advice and guidelines on COVID-19. The use of additional chest CT to assess for the presence of likely COVID-19 infection may have a role in stratifying risk in patients presenting acutely and requiring a CT abdomen, particularly those needing emergency surgery. In the absence of rapid access to other forms of COVID testing, this is appropriate if it will change the management of the patient. However, a negative scan would not exclude COVID-19 infection. As with all other advice at the moment, this may change. 

May 14, 2020 update: Routine pre-operative chest CT to screen for COVID-19 is NOT indicated – The relatively low pick up rate of COVID-19 in asymptomatic patients with positive RT-PCR and a 20% false-negative rate in symptomatic patients indicates that pre-operative CT chest is of limited utility. The updated statement is available here.

The British Society of Thoracic Imaging (BSTI)  in collaboration with NHS England has announced the COVID-19 Radiology Decision Support Tool which is accessible here.

One April 13, 2020, BSTI has provided additional guidelines on the following:

COVID-19 LUNG ULTRASOUND GUIDANCE: This video from the Radiology and Intensive Care departments of the Royal Brompton Hospital, London, describes lung ultrasound technique, its possible applications in the care of patients with CoVID-19 and its limitations.

GUIDANCE ON LUNG CANCER AND COVID IMAGING: Guidance from BSTI relating to CT scan of the chest during acute surgical abdomen, and lung cancer have been provided here.

COVID-19 REPORTING PROFORMA: BSTI has provided suggestion in regards to CT proforma with other details at this link.

World’s oldest radiological society, The British Institute of Radiology (BIR) has created comprehensive resources journal articles and webinars posted here.

THE AMERICAN COLLEGE OF RADIOLOGY® (ACR®)

The American College of Radiology® (ACR®) is closely monitoring guidance from the Centers for Disease Control and Prevention (CDC), World Health Organization (WHO) and other reliable sources regarding the Coronavirus (COVID-19).

The ACR believes that the following factors should be considered regarding the use of imaging for suspected or known COVID-19 infection:

  • The Centers for Disease Control (CDC) does not currently recommend CXR or CT to diagnose COVID-19. Viral testing remains the only specific method of diagnosis. Confirmation with the viral test is required, even if radiologic findings are suggestive of COVID-19 on CXR or CT.
  • For the initial diagnostic testing for suspected COVID-19 infection, the CDC recommends collecting and testing specimens from the upper respiratory tract (nasopharyngeal AND oropharyngeal swabs) or from the lower respiratory tract when available for viral testing.
  • Generally, the findings on chest imaging in COVID-19 are not specific and overlap with other infections, including influenza, H1N1, SARS and MERS. Being in the midst of the current flu season with a much higher prevalence of influenza in the U.S. than COVID-19, further limits the specificity of CT.
  • The current ACR Appropriateness Criteria® statement on Acute Respiratory Illness , last updated in 2018 states that chest CT is “Usually Not Appropriate.”
  • review from the Cochrane Database of Systematic Reviews on chest radiographs for acute lower respiratory tract infections concluded that CXR did not improve clinical outcomes (duration of illness) for patients with lower respiratory tract infection; the review included two randomized trials comparing use of CXRs to no CXRs in acute lower respiratory tract infections for children and adults.

The ACR recommends:

  • CT should not be used to screen for or as a first-line test to diagnose COVID-19
  • CT should be used sparingly and reserved for hospitalized, symptomatic patients with specific clinical indications for CT. Appropriate infection control procedures should be followed before scanning subsequent patients.
  • Facilities may consider deploying portable radiography units in ambulatory care facilities for use when CXRs are considered medically necessary. The surfaces of these machines can be easily cleaned, avoiding the need to bring patients into radiography rooms.
  • Radiologists should familiarize themselves with the CT appearance of COVID-19 infection in order to be able to identify findings consistent with infection in patients imaged for other reasons.

Updated March 22, 2020: As an interim measure, until more widespread COVID-19 testing is available, some medical practices are requesting chest CT to inform decisions on whether to test a patient for COVID-19, admit a patient or provide other treatment. The ACR strongly urges caution in taking this approach. A normal chest CT does not mean a person does not have COVID-19 infection – and an abnormal CT is not specific for COVID-19 diagnosis. A normal CT should not dissuade a patient from being quarantined or provided other clinically indicated treatment when otherwise medically appropriate. Clearly, locally constrained resources may be a factor in such decision making.

More details are available at ACR website.

CANADIAN SOCIETY OF THORACIC RADIOLOGY AND CANADIAN ASSOCIATION OF RADIOLOGISTS (CAR)

May 8, 2020: The Canadian Society of Thoracic Radiology and the Canadian Association of Radiologists published a consensus statement outlining the role of imaging in COVID-19 patients. The objectives of this publication are to answer key questions related to COVID-19 imaging of the chest and provide guidance for radiologists who are interpreting such studies during this pandemic.

The latest publication discusses the following key points:

  • When Is CXR Appropriate in Patients With Suspected or Confirmed COVID-19 Infection?
  • Recommendations on Reporting Chest Radiographic Findings
  • Suggested Categorization and Reporting Language
  • When Is Chest CT Appropriate in Patients With Suspected or Confirmed COVID-19 Infection?
  • Detection of Intrathoracic Complications
  • Immunosuppressed or High-Risk Patients With Suspected Respiratory Infection and a Negative Chest Radiograph
  • Initial Negative RT-PCR Result but Ongoing High Clinical Suspicion or Clinical Deterioration After a Normal Chest Radiograph
  • Recommendations on Reporting Chest CT Findings
  • Suggested Categorization and Reporting Language
  • How Should a Radiologist Deal With Incidental Findings of COVID-19 on Chest CT Done for Other Indications?
  • Should Lung Ultrasound (LUS) Be Used to Diagnose or Exclude COVID-19 Pneumonia?

More information on CAR website.

THE FLEISCHNER SOCIETY

The Fleischner Society is an international, multidisciplinary medical society for thoracic radiology, dedicated to the diagnosis and treatment of diseases of the chest. The society has published a multinational consensus position paper on the use of imaging in COVID-19.

A detailed and very interesting publication is available here.  It represents the collective opinions and perspectives of thoracic radiology, pulmonology, intensive care, emergency medicine, laboratory medicine, and infection control experts practicing in 10 countries, representative of the highest burden of COVID-19 worldwide. It also represents opinion at a moment in time within a highly-dynamic environment where the status of regional epidemics and the availability of critical resources to combat those epidemics vary daily.

Some of the highlights of this paper are the following:

  • CXR is insensitive in mild or early COVID-19 infection
  • CT is more sensitive for early parenchymal lung disease, disease progression, and alternative diagnoses including acute heart failure from COVID-19 myocardial injury
  • The use of imaging but do not articulate the relative merit of CXR versus CT
  • Ultimately, the choice of imaging modality is left to the judgement of clinical teams at the point-of-care accounting for the differing attributes of CXR and CT, local resources, and expertise

Additional key questions that this paper discusses are the following:

  • Daily chest radiographs are not indicated in stable intubated patients with COVID-19 
  • CT scan is indicated in a patient who has a functional impairment and/or hypoxemia after recovery from COVID-19
  • COVID-19 testing is indicated in a patient who is found incidentally to have typical findings of COVID-19 on a CT scan.
THE ROYAL AUSTRALIAN AND NEW ZEALAND COLLEGE OF RADIOLOGISTS (RANZCR)

RANZCR is advocating the application of normal appropriate use criteria for imaging patients presenting with an acute respiratory illness. CT should not be used for routine screening for COVID-19 disease. As with other causes of acute lung injury, it has a role in the evaluation of patients for potential complications. 

On April 9, 2020 RANZCR has published a document and updated their advice on appropriate use of CT throughout the COVID-19 pandemic. Key messages from this recent update are the following:

• Compared to the UK, USA and some European centres, Australia and New Zealand currently have less community transmission, better access to PPE and better access to PCR testing. Guidelines from these international centres may therefore be inappropriate in the Australian and New Zealand context.
• CT chest has a radiation exposure risk.
• CT chest has poor sensitivity for Covid-19 in asymptomatic patients or those early in the disease and should have no bearing on determining appropriate infection precautions.
• Surgical patients under investigation for Covid-19 (based on history or clinical presentations or findings) should be managed as such with droplet +/- aerosol precautions irrespective of CXR or CT findings.
• Routine CT chest of surgical patients who do not meet the criteria for coronavirus PCR testing is not currently justified in the Australian and New Zealand context.

For more information visit RANZCR website for latest updates.

SPAIN: WHAT DID WE HEAR SO FAR

Chest X-ray is the first imaging method to diagnose COVID-19 coronavirus infection in Spain, but in the light of new evidence, this may change soon, according to Milagros Martí de Gracia, Vice President of the Spanish Society of Radiology (SERAM) and head of the emergency radiology unit at La Paz Hospital in Madrid, one of the hot spots for viral re-production of COVID-19.

Patients with respiratory symptoms must remain isolated and wear a mask. If clinical suspicion persists after the examination, a sample of nasopharyngeal exudate is taken to test reverse-transcription polymerase chain reaction (RT-PCR). Then, we perform a chest X-ray. Getting the results of the PCR test may take several hours. The chest X-ray is a discriminating element; if the clinical situation and the chest X-ray film are normal, patients can go home and wait for the results of the etiological test. But if the film shows pathological findings, patients are admitted to the hospital for observation.

Usually the absence or presence of pathological findings on chest X-ray is determining to send the patient home or keep him/her under observation But if the clinical suspicion is high and the PCR or/and chest X-ray is normal, a chest CT is indicated.

Detailed interview published here.

ITALY - ROLE OF BEDSIDE ULTRASOUND AS AN ALTERNATIVE

While we explore the appropriateness of Chest X-rays or CT scans to pinpoint COVID-19 pneumonia, a group of Italian experts is exploring the benefits of bedside ultrasound as one possible alternative for early diagnosis of COVID-19 pneumonia.

While their data is preliminary and further studies are needed to confirm the role of lung ultrasound in the diagnosis and management of COVID-19, but the authors are strongly recommending the use of bedside ultrasound for early diagnosis of COVID-19 pneumonia in all patients presenting to the emergency department with flu-like symptoms. The publication is available here.

Another study from Italy, which has undergone full peer review discusses the role of lung ultrasound and how it has helped in clinical decision making and reduced the use of both chest x‐rays and computed tomography (CT). The publication is available here.

CHINA: THINKING BEYOND CHEST X-RAYS AND CT

Another study funded by National Natural Science Foundation of China and National Natural Science Foundation of China was published recently. According to this publication, as lung abnormalities may develop before clinical manifestations and nucleic acid detection, experts have recommended early chest computerized tomography (CT) for screening suspected patients. The high contagiousness of SARS-CoV-2 and the risk of transporting unstable patients with hypoxemia and hemodynamic failure make chest CT a limited option for the patient with suspected or established COVID-19. Lung ultrasonography gives the results that are similar to chest CT and superior to standard chest radiography for evaluation of pneumonia and/or adult respiratory distress syndrome (ARDS) with the added advantage of ease of use at point of care, repeatability, absence of radiation exposure, and low cost [References]

These two recent publications (Peng et al and Huang et al) have characterized important lung ultrasound findings in patients with COVID-19. A review of these two publications is highly recommended if you plan on incorporating bedside ultrasound into your clinical management of suspected COVID-19 patients. The role of bedside ultrasound as the stethoscope of the new millennium is discussed on this website here.

COVID-19, AI AND DATA ANALYTICS:

Globally, healthcare startups have already begun testing AI algorithms to study COVID-19 pattern recognition or relevant variations that may help with early disease detection. Countries are releasing emergency funds to aid in research and development of diagnostic kits, vaccines and medicines.

There’s already some work in progress internationally to study the role of deep learning algorithms relating to pattern recognition on Chest CT scans. When it comes to detecting abnormalities in lung imaging, focused work has already been done in this space, hence with COVID-19 it may not require a lot of work to further improve the sensitivity and specificity of AI algorithms. However, there’s still more work to be done and international validation required.

On March 11, the ACR® Data Science Institute® (DSI) has published an artificial intelligence (AI) use case on COVID-19 , which is now open for public comment. Expert radiologists rapidly developed the use case to offer the developer community medical context — including necessary inputs, outputs and possible corollary features — for developing an AI solution to detect COVID-19.

Recently, some papers have been published reviewing the role of RT-PCR and Chest CT Scans and how CT can play a vital role in the early detection and management of COVID-19. However, it is worth emphasizing that a patient with reverse-transcription polymerase chain reaction (RT-PCR) confirmed COVID-19 infection may have normal chest CT findings at admission. (Ref: link)

A couple of early CT imaging patient case studies coming out of China in the past months reported COVID-19 was preliminarily diagnosed from CT scans in several patients before they started to show positive RT-PCR test results. Additional COVID-19 radiology research can be found at Special Focus: COVID-19.

AI and Analytics for forecasting the trajectory of COVID-19: As an alternative to epidemiological models for transmission dynamics of Covid-19 in China, a recent paper proposes artificial intelligence (AI)-inspired methods for real-time forecasting of Covid-19 to estimate the size, lengths and ending time of Covid-19 across China.

According to this paper, the accuracy of the AI-based methods for forecasting the trajectory of Covid-19 was high. They predicted that the epidemics of Covid-19 will be over by the middle of April. “If the data are reliable and there are no second transmissions, we can accurately forecast the transmission dynamics of the Covid-19 across the provinces/cities in China. The AI-inspired methods are a powerful tool for helping public health planning and policy-making.”

COVID-19 Open Research Dataset (CORD-19): In a recent briefing, research leaders across tech, academia and the government joined the White House to announce an open data set full of scientific literature on the novel coronavirus. The dataset is freely available for the global research community to apply recent advances in natural language processing and other AI techniques to generate new insights in support of the ongoing fight against this infectious disease.

Supporting our care providers with technology and flexible workflows while they are coping with the COVID-19 challenge:

The need for digital imaging and fast access to radiology scans via remote reading applications is on the rise. Just recently, Agfa HealthCare shared the experience of how it’s Enterprise Imaging Radiologist workstation was deployed speedily within 20 minutes at a Radiologist’s home in the UK who was concerned about being able to work should the need to self-isolate arise. Further details regarding how Agfa HealthCare is supporting its clients with an Enterprise Imaging strategy are posted here.

The Royal College of Radiology UK has also released guidance on information technology requirements for homeworking. RCR resources have been developed to strike a balance between the urgent need for pragmatic home working solutions in response to COVID-19 and the quality of images needed for radiologists to interpret images. Details are available on RCR UK website.

To understand the broader technology and service provider landscape, KLAS Research reached out to vendor community to learn more about what they are doing/can do to help organizations in this crisis. The “COVID-19 Technology & Services Solutions Guide” from KLAS Research is available here.

The COVID-19 situation is fast evolving, more evidence relating to screening, detection, diagnosis and management is being captured. In the meantime, the key takeaway for each and every one of us is to help ease the burden on our health systems by practicing the guidelines being emphasized by local health authorities, so that the care providers at the forefront of care delivery may focus on looking after the ones impacted the most.

Wishing you all, the best of health, well-being and safety.

Published March 18, 2020 – Further updated on April 13 and May 18, 2020

About the author: Dr. Anjum Ahmed is a global speaker and thought leader on digital health and AI. He is the Chief Medical Officer and Global Director of Enterprise Imaging and Artificial Intelligence Innovation at a Belgium based leading provider of healthcare IT solutions across the globe. Dr. Anjum has to his credit research and thought-provoking publications on value-based care, digital transformation in healthcare, and evidence-based application of AI.
Additional references

1] Zhu N, Zhang D, Wang W et al. A novel coronavirus from patients with pneumonia in China, 2019. N Engl J Med 2020 January 24 (Epub ahead of print), doi: 10.1056/NEJMoa2001017.

2] Lam CW, Chan MH, Wong CK. Severe acute respiratory syndrome: clinical and laboratory manifestations. Clin Biochem Rev 2004; 25:121-132

3] The Middle East Respiratory Syndrome (MERS). WHO

LinkedIn
Facebook
Twitter
WhatsApp

dranjum.com