Portal de Periódicos da CAPES

COVID-19 severity scoring systems in radiological imaging – a review

2020; Polish Medical Society of Radiology; Volume: 85; Linguagem: Inglês

10.5114/pjr.2020.98009

1899-0967

Piotr Gustaw Wasilewski, Bartosz Mruk, S. Mazur, Gabriela Półtorak-Szymczak, Katarzyna Sklinda, Jerzy Walecki,

Radiomics and Machine Learning in Medical Imaging

The current reference standard to make a definitive diagnosis of SARS-CoV-2 infection is the reverse transcription-<br /> polymerase chain reaction assay (rt-PCR). However, radiological imaging plays a crucial role in evaluating the course of COVID-19 and in choosing proper management of infected patients. Chest X-ray (CXR) is generally considered not to be sensitive for the detection of pulmonary abnormalities in the early stage of the disease. However, in the emergency setting CXR can be a useful diagnostic tool for monitoring the rapid progression of lung involvement in COVID-19, especially in patients admitted to intensive care units. The rapid course of SARS-CoV-2 infection and the severity and progression of lung aberrations require a method of radiological evaluation to implement and manage the appropriate treatment for infected patients. Computed tomography (CT) imaging is considered to be the most effective method for the detection of lung abnormalities, especially in the early stage of the disease. Moreover, serial chest CT imaging with different time intervals is also effective in estimating the evolution of the disease from initial diagnosis to discharge from hospital. Despite having low specificity in distinguishing abnormalities in viral infections, the high sensitivity of CT makes this method ideal for assessing the severity of the disease in patients with confirmed COVID-19.