The disease caused by the new coronavirus, or COVID-19, has been recently described and became a health issue worldwide. Its diagnosis of certainty is given by polymerase chain reaction. High-resolution computed tomography, however, is useful in the current context of pandemic, especially for the most severe cases, in assessing disease extent, possible differential diagnoses and searching complications. In patients with suspected clinical symptoms and typical imaging findings, in which there is still no laboratory test result, or polymerase chain reaction is not available, the role of this test is still discussed. In addition, it is important to note that part of the patients present false-negative laboratory tests, especially in initial cases, which can delay isolation, favoring the spread of the disease. Thus, knowledge about the COVID-19 and its imaging manifestations is extremely relevant for all physicians involved in the patient care, clinicians or radiologists.
Figure 2. Bedside anteroposterior chest X-ray images demonstrate the radiographic evolution of the nosocomial infection with multiple areas of consolidation in both lungs
The COVID-19 became a pandemic in early 2020. It was found, at first, that the main manifestations of this new virus occur through respiratory and constitutional symptoms. Therefore, chest tomography was elected as the best imaging test to assess the extent of pulmonary involvement and as a good prognostic predictor for the disease. However, as new studies were produced, the gastrointestinal involvement of COVID-19 becomes more evident, with reports from patients who manifested mainly or only gastrointestinal symptoms in the course of the disease. Thus, in some cases, the initial investigation is carried out at the emergency department with an abdominal computed tomography. We report a case series of ten patients who came to the emergency department of our institution with a chief gastrointestinal complaint, and were initially submitted to an abdominal computed tomography as the first investigation. Although most of the patients did not have significant changes in the abdominal images, most reported patients had pulmonary findings visualized at the lung bases, which were later designated as typical COVID-19 pulmonary findings on chest computed tomography. Only one patient had atypical COVID-19 lung changes on chest computed tomography. All patients had a positive real-time polymerase chain reaction for COVID-19. It is imperative to alert radiologists, especially abdominal radiologists, with the possibility of COVID-19 isolated gastrointestinal symptoms. Besides, it must become a habit to radiologists to assess the pulmonary basis on abdominal scans, a site commonly affected by the new coronavirus.
Chest radiographs allow for the meticulous examination of a patient’s chest but demands specialized training for proper interpretation. Automated analysis of medical imaging has become increasingly accessible with the advent of machine learning (ML) algorithms. Large labeled datasets are key elements for training and validation of these ML solutions. In this paper we describe the Brazilian labeled chest x-ray dataset, BRAX: an automatically labeled dataset designed to assist researchers in the validation of ML models. The dataset contains 24,959 chest radiography studies from patients presenting to a large general Brazilian hospital. A total of 40,967 images are available in the BRAX dataset. All images have been verified by trained radiologists and de-identified to protect patient privacy. Fourteen labels were derived from free-text radiology reports written in Brazilian Portuguese using Natural Language Processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.