Journal of the American College of Radiology : JACR
-
Natural language processing (NLP) enables conversion of free text into structured data. Recent innovations in deep learning technology provide improved NLP performance. We aimed to survey deep learning NLP fundamentals and review radiology-related research. ⋯ Research and use of deep learning NLP in radiology is increasing. Acquaintance with this technology can help prepare radiologists for the coming changes in their field.
-
In December 2019, a novel coronavirus (COVID-19) pneumonia emerged in Wuhan, China. Since then, this highly contagious COVID-19 has been spreading worldwide, with a rapid rise in the number of deaths. Novel COVID-19-infected pneumonia (NCIP) is characterized by fever, fatigue, dry cough, and dyspnea. ⋯ The purpose of the present review is to briefly discuss the known epidemiology and the imaging findings of coronavirus syndromes, with a focus on the reported imaging findings of NCIP. Moreover, the authors review precautions and safety measures for radiology department personnel to manage patients with known or suspected NCIP. Implementation of a robust plan in the radiology department is required to prevent further transmission of the virus to patients and department staff members.
-
The diagnosis of pulmonary embolism (PE) remains a challenge. CT pulmonary angiography (CTPA) for suspected PE has become the primary imaging modality, but concerns regarding overutilization, overdiagnosis, radiation, and costs have led to algorithms that combine a clinical decision rule (CDR) and highly sensitive d-dimer to identify patients in whom PE can be safely excluded without further studies. This has been identified as a top five Choosing Wisely recommendation in pulmonary medicine, but adherence is modest at best and actual utilization is unknown. Therefore, a survey was conducted to determine the prevalence of this approach in the Veterans Administration (VA) healthcare system. ⋯ CDR-guided strategies are recommended in the evaluation of suspected PE. Adherence within the VA healthcare system is very low. Further investigation is warranted to better characterize and improve the adherence to CDR-guided strategies and CTPA utilization.
-
Overall, 55% of surveyed radiology practice leaders reported that burnout was a very significant problem, and 22% reported that burnout was a significant problem. Burnout did not vary by geographical region but did vary by practice size. Overall, 71% of respondents reported stress from workplace factors, and 36% reported stress from personal or social factors very significantly affected radiologist employee wellness; both sets of factors varied by geographical region, practice size, and practice type. Only 19% of practice leader respondents reported mechanisms to assess burnout, which varied by region and practice type.