GUNDUA-HLANGANISA: COVID-19 DIAGNOSIS USING ASSEMBLING METHOD FOR IMAGERY

GUNDUA-HLANGANISA: COVID-19 DIAGNOSIS USING ASSEMBLING METHOD FOR IMAGERY

Clinical needs

Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus.
Most people infected with the COVID-19 virus will experience mild to moderate respiratory illness and recover without requiring special treatment. Older people, and those with underlying medical problems like cardiovascular disease, diabetes, chronic respiratory disease, and cancer are more likely to develop serious illness.

Developing countries are experiencing challenges in testing for COVID-19. There is low availability of RT-PCR tests across the African continent. The PCR test is an arduous task of intrusive extraction of genetic material, that is transported to the laboratory. Test results are communicated to the patient in 24 hours.

Testing kits are also being used to carry out COVID-19 testing. These test kits test for the presence of antibodies in blood samples.

During a pandemic national lockdown, nations are challenged as logistics do not work, making it difficult to get test kits and PCR kits by import from other countries, or to distribute locally to regions that need them.

Chest radiography (CXR) is a fast and relatively inexpensive imaging modality which is already available in many resource-constrained healthcare settings for other medical uses. However there is shortage of radiological skills in developing countries for accurate and fast interpretation of such images . An AI system may be a helpful tool to radiologists or technicians, in the common case that radiological expertise is not available.

Patients who test positive for pneumonia associated with the coronavirus largely share several findings visible on chest X-ray images. Knowing what symptoms will likely appear on these images can help health care providers recognize which individuals will need targeted treatment.

The common findings below briefly describes an example of how chest x-ray images are interpreted in terms of a COVID-19 suspected patient (depends on the onset of symptoms).

  1. Ground glass opacities (meaning that there are some portions of the lungs that look like a hazy shade of gray instead of being black with fine white lung markings for blood vessels.
  2.  Bilateral peripheral consolidation (peak at 10-12 days from onset symptoms ).
  3. Severity of lung shadowing on a chest X-ray can be classified by comparing the area of abnormal lung (white) with the area of normal lung (black). If there is more black than white then shadowing is classified as 'Mild'. If there is approximately equal white and black then shadowing is classified as 'Moderate'. If there is more white than black then shadowing is classified as 'Severe'.