RESUMO
Interpretive artificial intelligence (AI) tools are poised to change the future of radiology. However, certain pitfalls may pose particular challenges for optimal AI interpretative performance. These include anatomic variants, age-related changes, postoperative changes, medical devices, image artifacts, lack of integration of prior and concurrent imaging examinations and clinical information, as well as the satisfaction-of-search effect. Model training and development should account for such pitfalls, to minimize errors and optimize interpretation accuracy. More broadly, AI algorithms should be exposed to diverse and complex training data sets, to yield a holistic interpretation that considers all relevant information beyond the individual examination. Successful clinical deployment of AI tools will require that radiologist end-users recognize these pitfalls and other limitations of the available models. Furthermore, developers should incorporate explainable AI techniques (e.g., heat maps) into their tools, to improve radiologists' understanding of model outputs and to enable radiologists to provide feedback for guiding continuous learning and iterative refinement. In this article, we provide an overview of common pitfalls that radiologists may encounter when using interpretive AI products in daily practice. We present how such pitfalls lead to AI errors and offer potential strategies that AI developers may use for their mitigation.
RESUMO
Artificial intelligence (AI) and its recent increasing healthcare integration has created both new opportunities and challenges in the practice of radiology and medical imaging. Recent advancements in AI technology have allowed for more workplace efficiency, higher diagnostic accuracy, and overall improvements in patient care. Limitations of AI such as data imbalances, the unclear nature of AI algorithms, and the challenges in detecting certain diseases make it difficult for its widespread adoption. This review article presents cases involving the use of AI models to diagnose intracranial hemorrhage, spinal fractures, and rib fractures, while discussing how certain factors like, type, location, size, presence of artifacts, calcification, and post-surgical changes, affect AI model performance and accuracy. While the use of artificial intelligence has the potential to improve the practice of emergency radiology, it is important to address its limitations to maximize its advantages while ensuring the safety of patients overall.
RESUMO
Coronary CT angiograms are commonly performed for the evaluation of coronary artery disease and coronary arterial anatomy. However, extracardiac findings are frequently detected on these examinations and often can explain patients' underlying symptoms, having a significant impact on patient management. Here in, we discuss three cases of incidentally detected novel COVID-19-infected pneumonia (NCIP). This case series highlights the image findings in NCIP and emphasizes the importance of evaluating all organs in the field of view on coronary CT angiograms. In addition, with the ongoing outbreak of COVID-19 and exponentially increasing incidence throughout the world, this report stresses the need for including NCIP in the differential diagnosis of patients with typical image findings in at-risk populations, as early diagnosis is crucial for appropriate patient management and post-exposure recommendations.
Assuntos
Angiografia por Tomografia Computadorizada , Infecções por Coronavirus/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Adulto , Betacoronavirus , COVID-19 , Teste para COVID-19 , Técnicas de Laboratório Clínico , Infecções por Coronavirus/diagnóstico , Diagnóstico Diferencial , Feminino , Humanos , Achados Incidentais , Masculino , Pessoa de Meia-Idade , Pandemias , SARS-CoV-2RESUMO
Coronavirus disease 2019 (COVID-19), the first pandemic caused by a human infecting coronavirus, has drawn global attention from the first time it appeared in Wuhan city of China in late December 2019. Detection of the responsible viral pathogen, named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by WHO, and its possible pathogenesis lead to the forming of many hypotheses about the factors that may affect the patients' outcome. One of the SARS-CoV-2 infection concerns was the potential role of angiotensin-converting enzyme (ACE) inhibitors and angiotensin-receptor blockers (ARBs) in COVID-19 patients' morbidity and mortality. Studies demonstrated that because SARS-CoV-2 uses human ACE2 cell receptors as an entry receptor to invade the cells, there might be an association between antihypertensive drugs such as RAAS inhibitors (specifically ACEIs and ARBs) and the COVID-19 disease. Data are scarce and conflicting regarding ACEI or ARB consumption and how it influences disease outcomes, and a single conclusion has not been reached yet. According to the literature review in our article, the most evidentially supported theory about the use of RAAS inhibitors in COVID-19 is that these medications, including ACEI/ARB, are not associated with the increased risk of infection, disease severity, and patient prognosis. However, further studies are needed to support the hypothesis.
RESUMO
COVID-19 is principally a respiratory illness and pulmonary manifestations constitute main presentations of the disease. According to the reported studies, SARS-CoV-2 infection is not limited to the respiratory system and other organs can be also affected. Renal dysfunction, gastrointestinal complications, liver dysfunction, cardiac manifestations, mediastinal findings, neurological abnormalities, and hematological manifestations are among the reported extrapulmonary features. Considering the broad spectrum of clinical manifestations and the increasing worldwide burden of the disease, there is an urgent need to rapidly scale up the diagnostic capacity to detect COVID-19 and its complications. This paper focuses on the most common extrapulmonary manifestations in patients with COVID-19 pneumonia. Further studies are needed to elaborate and confirm the causative relationship between SARS-CoV-2 and the reported extrapulmonary manifestations of COVID-19.