Evaluating the Performance of a Commercially Available Artificial Intelligence Algorithm for Automated Detection of Pulmonary Embolism on Contrast-Enhanced Computed Tomography and Computed Tomography Pulmonary Angiography in Patients With Coronavirus Disease 2019.

Objective: To investigate the performance of a commercially available artificial intelligence (AI) algorithm for the detection of pulmonary embolism (PE) on contrast-enhanced computed tomography (CT) scans in patients hospitalized for coronavirus disease 2019 (COVID-19). Patients and Methods: Retrospective analysis was performed of all contrast-enhanced chest CT scans of patients admitted for COVID-19 between March 1, 2020 and December 31, 2021. Based on the original radiology reports, all PE-positive examinations were included (n=527). Using a reversed-flow single-gate diagnostic accuracy case-control model, a randomly selected cohort of PE-negative examinations (n=977) was included. Pulmonary parenchymal disease severity was assessed for all the included studies using a semiquantitative system, the total severity score. All included CT scans were sent for interpretation by the commercially available AI algorithm, Aidoc. Discrepancies between AI and original radiology reports were resolved by 3 blinded radiologists, who rendered a final determination of indeterminate, positive, or negative. Results: A total of 78 studies were found to be discrepant, of which 13 (16.6%) were deemed indeterminate by readers and were excluded. The sensitivity and specificity of AI were 93.2% (95% CI, 90.6%-95.2%) and 99.6% (95% CI, 98.9%-99.9%), respectively. The accuracy of AI for all total severity score groups (mild, moderate, and severe) was high (98.4%, 96.7%, and 97.2%, respectively). Artificial intelligence was more accurate in PE detection on CT pulmonary angiography scans than on contrast-enhanced CT scans (P<.001), with an optimal Hounsfield unit of 362 (P=.048). Conclusion: The AI algorithm demonstrated high sensitivity, specificity, and accuracy for PE on contrast-enhanced CT scans in patients with COVID-19 regardless of parenchymal disease. Accuracy was significantly affected by the mean attenuation of the pulmonary vasculature. How this affects the legitimacy of the binary outcomes reported by AI is not yet known.

U.S. Newspaper Coverage of Lung Cancer Screening From 2010 to 2022.

BACKGROUND. Newspapers are an important source of information for the public about low-dose CT (LDCT) lung cancer screening (LCS) and may influence public perception and knowledge of this important cancer screening service. OBJECTIVE. The purpose of this article was to evaluate the volume, content, and other characteristics of articles pertaining to LCS that have been published in U.S. newspapers. METHODS. The ProQuest U.S. Newsstream database was searched for U.S. newspaper articles referring to LCS published between January 1, 2010 (the year of publication of the National Lung Screening Trial results), and March 28, 2022. Search terms included "lung cancer screening(s)," "lung screening(s)," "low dose screening(s)," and "LDCT." Search results were reviewed to identify those articles mentioning LCS. Characteristics of included articles and originating newspapers were extracted. Articles were divided among nine readers, who independently assessed article sentiment regarding LCS and additional article content using a standardized form. RESULTS. The final analysis included 859 articles, comprising 816 nonsyndicated articles published in a single newspaper and 43 syndicated articles published in multiple newspapers. Sentiment regarding LCS was positive in 76% (651/859) of articles, neutral in 21% (184/859), and negative in 3% (24/859). Frequency of positive sentiment was lowest (61%) for articles published from 2010 to 2012; frequency of negative sentiment was highest (8%) for articles published in newspapers in the highest quartile for weekly circulation. LCS enrollment criteria were mentioned in 52% of articles, smoking cessation programs in 28%, need for annual CT in 27%, and shared decision-making in 4%. Cost or insurance coverage for LCS was mentioned in 33% in articles. A total of 64% of articles mentioned at least one benefit of LCS (most commonly early detection or possible cure of lung cancer), and 23% mentioned at least one harm (most commonly false-positives). A total of 9% of articles interviewed or mentioned a radiologist. CONCLUSION. The sentiment of U.S. newspaper articles covering LCS from 2010 to 2022 was overall positive. However, certain key elements of LCS were infrequently mentioned. CLINICAL IMPACT. The findings highlight areas for potential improvement of LCS media coverage; radiologists have an opportunity to take a more active role in this coverage.

Diseases of the pulmonary arteries: imaging appearances and pearls.

A wide spectrum of pathology, both congenital and acquired, can affect the pulmonary arteries. While some of these are commonly seen in everyday clinical practice, some are rare. These entities may be discovered incidentally at imaging for other reasons in an asymptomatic patient, however patients may go on to develop symptoms over the course of their lifetime. Although an enlarged pulmonary artery can be visualized on chest X-ray (CXR), for the most part, CXR is insensitive for detecting abnormalities of the pulmonary arteries. Contrast-enhanced chest CT (CECT) is a better test to evaluate the pulmonary arteries as it is readily available, quick to perform, able to provide multiplanar reformatted images, and noninvasive. CECT is not only able to assess the lumen and wall of the pulmonary artery, but also provides a detailed evaluation of the entire thorax, including the heart, mediastinal structures, and lungs, often times picking up associated findings, and is the mainstay for evaluating disorders of the pulmonary vasculature. MRI allows for detailed evaluation of the vessel wall which can be especially helpful in cases where malignancy or vasculitis are suspected, and is also able to provide useful physiologic data such as quantification of flow. It is important for the radiologist to be aware of the many conditions which affect the pulmonary arteries, as some may require urgent treatment. This article will review normal pulmonary artery anatomy and physiology, as well as the various imaging findings of pulmonary vascular pathologies.

Early-stage COVID-19 pandemic observations on pulmonary embolism using nationwide multi-institutional data harvesting.

We introduce a multi-institutional data harvesting (MIDH) method for longitudinal observation of medical imaging utilization and reporting. By tracking both large-scale utilization and clinical imaging results data, the MIDH approach is targeted at measuring surrogates for important disease-related observational quantities over time. To quantitatively investigate its clinical applicability, we performed a retrospective multi-institutional study encompassing 13 healthcare systems throughout the United States before and after the 2020 COVID-19 pandemic. Using repurposed software infrastructure of a commercial AI-based image analysis service, we harvested data on medical imaging service requests and radiology reports for 40,037 computed tomography pulmonary angiograms (CTPA) to evaluate for pulmonary embolism (PE). Specifically, we compared two 70-day observational periods, namely (i) a pre-pandemic control period from 11/25/2019 through 2/2/2020, and (ii) a period during the early COVID-19 pandemic from 3/8/2020 through 5/16/2020. Natural language processing (NLP) on final radiology reports served as the ground truth for identifying positive PE cases, where we found an NLP accuracy of 98% for classifying radiology reports as positive or negative for PE based on a manual review of 2,400 radiology reports. Fewer CTPA exams were performed during the early COVID-19 pandemic than during the pre-pandemic period (9806 vs. 12,106). However, the PE positivity rate was significantly higher (11.6 vs. 9.9%, p < 10-4) with an excess of 92 PE cases during the early COVID-19 outbreak, i.e., ~1.3 daily PE cases more than statistically expected. Our results suggest that MIDH can contribute value as an exploratory tool, aiming at a better understanding of pandemic-related effects on healthcare.

Imaging in the Evaluation of Chest Pain in the Primary Care Setting, Part 1: Cardiovascular Etiologies.

Chest pain is a common presenting complaint in the primary care setting. Imaging plays a key role in the evaluation of the multiple organ systems that can be responsible for chest pain. With numerous imaging modalities available, determination of the most appropriate test and interpretation of the findings can be a challenge for the clinician. In this 2-part series, we offer resources to guide primary care physicians in the selection of imaging studies and present the imaging findings of various causes of nonemergent chest pain. In Part 1, we focus on a discussion of the basic concepts of each imaging technique and the appearance of common cardiovascular etiologies of chest pain.

Imaging in the Evaluation of Chest Pain in the Primary Care Setting, Part 2: Sources of Noncardiac Chest Pain.

Chest pain is a common presenting complaint in the primary care setting. Imaging plays a key role in the evaluation of the multiple organ systems that can be responsible for chest pain. With numerous imaging modalities available, determination of the most appropriate test and interpretation of the findings can be a challenge for the clinician. In this 2-part series, we offer resources to guide primary care physicians in the selection of imaging studies and present the imaging findings of various causes of nonemergent chest pain. In Part 2, we focus on the radiologic appearance of common noncardiac sources of chest pain, including gastrointestinal, pulmonary, and musculoskeletal etiologies.