Contrast Reactions and Approaches to Staffing the Contrast Reaction Management Team.

RATIONALE AND OBJECTIVES: Managing contrast reactions is critical as contrast reactions can be life-threatening and unpredictable. Institutions need an effective system to handle these events. Currently, there is no standard practice for assigning trainees, radiologists, non-radiologist physicians, or other non-physician providers for management of contrast reaction. MATERIALS AND METHODS: The Association of Academic Radiologists (AAR) created a task force to address this gap. The AAR task force reviewed existing practices, studied available literature, and consulted experts related to contrast reaction management. The Society of Chairs of Academic Radiology Departments (SCARD) members were surveyed using a questionnaire focused on staffing strategies for contrast reaction management. RESULTS: The task force found disparities in contrast reactions management across institutions and healthcare providers. There is a lack of standardized protocols for assigning personnel for contrast reaction management. CONCLUSION: The AAR task force suggests developing standardized protocols for contrast reaction management. The protocols should outline clear roles for different healthcare providers involved in these events.

ChatGPT in radiology: A systematic review of performance, pitfalls, and future perspectives.

PURPOSE: The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its integration, optimization, and ethical considerations in radiology applications. MATERIALS AND METHODS: After a comprehensive review of PubMed, Web of Science, Embase, and Google Scholar databases, a cohort of published studies was identified up to January 1, 2024, utilizing ChatGPT for clinical radiology applications. RESULTS: Out of 861 studies derived, 44 studies evaluated the performance of ChatGPT; among these, 37 (37/44; 84.1%) demonstrated high performance, and seven (7/44; 15.9%) indicated it had a lower performance in providing information on diagnosis and clinical decision support (6/44; 13.6%) and patient communication and educational content (1/44; 2.3%). Twenty-four (24/44; 54.5%) studies reported the proportion of ChatGPT's performance. Among these, 19 (19/24; 79.2%) studies recorded a median accuracy of 70.5%, and in five (5/24; 20.8%) studies, there was a median agreement of 83.6% between ChatGPT outcomes and reference standards [radiologists' decision or guidelines], generally confirming ChatGPT's high accuracy in these studies. Eleven studies compared two recent ChatGPT versions, and in ten (10/11; 90.9%), ChatGPTv4 outperformed v3.5, showing notable enhancements in addressing higher-order thinking questions, better comprehension of radiology terms, and improved accuracy in describing images. Risks and concerns about using ChatGPT included biased responses, limited originality, and the potential for inaccurate information leading to misinformation, hallucinations, improper citations and fake references, cybersecurity vulnerabilities, and patient privacy risks. CONCLUSION: Although ChatGPT's effectiveness has been shown in 84.1% of radiology studies, there are still multiple pitfalls and limitations to address. It is too soon to confirm its complete proficiency and accuracy, and more extensive multicenter studies utilizing diverse datasets and pre-training techniques are required to verify ChatGPT's role in radiology.

Computed Tomography-Based Coronary Artery Calcium Score Calculation at a Reduced Tube Voltage Utilizing Iterative Reconstruction and Threshold Modification Techniques: A Feasibility Study.

BACKGROUND: The coronary artery calcium score (CACS) indicates cardiovascular health. A concern in this regard is the ionizing radiation from computed tomography (CT). Recent studies have tried to introduce low-dose CT techniques to assess CACS. We aimed to investigate the accuracy of iterative reconstruction (IR) and threshold modification while applying low tube voltage in coronary artery calcium imaging. METHODS: The study population consisted of 107 patients. Each subject underwent an electrocardiogram-gated CT twice, once with a standard voltage of 120 kVp and then a reduced voltage of 80 kVp. The standard filtered back projection (FBP) reconstruction was applied in both voltages. Considering Hounsfield unit (HU) thresholds other than 130 (150, 170, and 190), CACS was calculated using the FBP-reconstructed 80 kVp images. Moreover, the 80 kVp images were reconstructed utilizing IR at different strength levels. CACS was measured in each set of images. The intraclass correlation coefficient (ICC) was used to compare the CACSs. RESULTS: A 64% reduction in the effective dose was observed in the 80 kVp protocol compared to the 120 kVp protocol. Excellent agreement existed between CACS at high-level (strength level = 5) IR in low-kVp images and the standard CACS protocol in scores ≥ 11 (ICC > 0.9 and p < 0.05). Increasing the threshold density to 190 HU in FBP-reconstructed low-kVp images yielded excellent agreement with the standard protocol in scores ≥ 11 (ICC > 0.9 and p < 0.05) and good agreement in score zero (ICC = 0.84 and p = 0.02). CONCLUSIONS: The modification of the density threshold and IR provides an accurate calculation of CACS in low-voltage CT with the potential to decrease patient radiation exposure.

The predictive value of cardiac MRI strain parameters in hypertrophic cardiomyopathy patients with preserved left ventricular ejection fraction and a low fibrosis burden: a retrospective cohort study.

Background: Prompt interventions prevent adverse events (AE) in hypertrophic cardiomyopathy (HCM). We evaluated the pattern and the predictive role of feature tracking (FT)-cardiac magnetic resonance (CMR) imaging parameters in an HCM population with a normal left ventricular ejection fraction (LVEF) and a low fibrosis burden. Methods: The CMR and clinical data of 170 patients, consisting of 142 HCM (45 ± 15.7 years, 62.7% male) and 28 healthy (42.2 ± 11.26 years, 50% male) subjects, who were enrolled from 2015 to 2020, were evaluated. HCM patients had a normal LVEF with a late gadolinium enhancement (LGE) percentage below 15%. Between-group differences were described, and the potent predictors of AE were determined. A P-value below 0.05 was considered significant. Results: LV global longitudinal, circumferential, and radial strains (GLS, GCS, and GRS, respectively) and the LV myocardial mass index (MMI) were different between the healthy and HCM cases (all Ps < 0.05). Strains were significantly impaired in the HCM patients with a normal MMI. A progressive decrease in LVGLS and a distinct fall in LVGCS were noted with a rise in MMI. AE were predicted by LVGLS, LVGCS, and the LGE percentage, and LVGCS was the single robust predictor (HR, 1.144; 95% CI, 1.080-1.212; P = 0.001). An LVGCS below 16.2% predicted AE with 77% specificity and 58% sensitivity. Conclusions: LV strains were impaired in HCM patients with a normal EF and a low fibrosis burden, even in the presence of a normal MMI. CMR parameters, especially FT-CMR values, predicted AE in our HCM patients.

Machine Learning in Cardiovascular Imaging: A Scoping Review of Published Literature.

Purpose of Review: In this study, we planned and carried out a scoping review of the literature to learn how machine learning (ML) has been investigated in cardiovascular imaging (CVI). Recent Findings: During our search, we found numerous studies that developed or utilized existing ML models for segmentation, classification, object detection, generation, and regression applications involving cardiovascular imaging data. We first quantitatively investigated the different aspects of study characteristics, data handling, model development, and performance evaluation in all studies that were included in our review. We then supplemented these findings with a qualitative synthesis to highlight the common themes in the studied literature and provided recommendations to pave the way for upcoming research. Summary: ML is a subfield of artificial intelligence (AI) that enables computers to learn human-like decision-making from data. Due to its novel applications, ML is gaining more and more attention from researchers in the healthcare industry. Cardiovascular imaging is an active area of research in medical imaging with lots of room for incorporating new technologies, like ML. Supplementary Information: The online version contains supplementary material available at 10.1007/s40134-022-00407-8.

Comparison of conventional scoring systems to machine learning models for the prediction of major adverse cardiovascular events in patients undergoing coronary computed tomography angiography.

Background: The study aims to compare the prognostic performance of conventional scoring systems to a machine learning (ML) model on coronary computed tomography angiography (CCTA) to discriminate between the patients with and without major adverse cardiovascular events (MACEs) and to find the most important contributing factor of MACE. Materials and methods: From November to December 2019, 500 of 1586 CCTA scans were included and analyzed, then six conventional scores were calculated for each participant, and seven ML models were designed. Our study endpoints were all-cause mortality, non-fatal myocardial infarction, late coronary revascularization, and hospitalization for unstable angina or heart failure. Score performance was assessed by area under the curve (AUC) analysis. Results: Of 500 patients (mean age: 60 ± 10; 53.8% male subjects) referred for CCTA, 416 patients have met inclusion criteria, 46 patients with early (<90 days) cardiac evaluation (due to the inability to clarify the reason for the assessment, deterioration of the symptoms vs. the CCTA result), and 38 patients because of missed follow-up were not enrolled in the final analysis. Forty-six patients (11.0%) developed MACE within 20.5 ± 7.9 months of follow-up. Compared to conventional scores, ML models showed better performance, except only one model which is eXtreme Gradient Boosting had lower performance than conventional scoring systems (AUC:0.824, 95% confidence interval (CI): 0.701-0.947). Between ML models, random forest, ensemble with generalized linear, and ensemble with naive Bayes were shown to have higher prognostic performance (AUC: 0.92, 95% CI: 0.85-0.99, AUC: 0.90, 95% CI: 0.81-0.98, and AUC: 0.89, 95% CI: 0.82-0.97), respectively. Coronary artery calcium score (CACS) had the highest correlation with MACE. Conclusion: Compared to the conventional scoring system, ML models using CCTA scans show improved prognostic prediction for MACE. Anatomical features were more important than clinical characteristics.

Hypersensitivity Pneumonitis: A Pictorial Review Based on the New ATS/JRS/ALAT Clinical Practice Guideline for Radiologists and Pulmonologists.

Hypersensitivity pneumonitis (HP) is a complicated and heterogeneous interstitial lung disease (ILD) caused by an excessive immune response to an inhaled antigen in susceptible individuals. Accurate diagnosis of HP is difficult and necessitates a detailed exposure history, as well as a multidisciplinary discussion of clinical, histopathologic, and radiologic data. We provide a pictorial review based on the latest American Thoracic Society (ATS)/Japanese Respiratory Society (JRS)/Asociación Latinoamericana del Tórax (ALAT) guidelines for diagnosing HP through demonstrating new radiologic terms, features, and a new classification of HP which will benefit radiologists and pulmonologists.

Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review.

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.

Articular Findings on Chest Computed Tomography: An Algorithmic Approach for Radiologists.

ABSTRACT: Chest computed tomography (CT) is one of the most frequently performed imaging studies. Incidental osseous and articular findings are commonly encountered in chest CTs in daily practice. The spectrum of findings is broad, varying from benign to malignant, and interpretation of these incidental musculoskeletal findings could be challenging for radiologists. In this review, we provide a systematic algorithmic approach for the diagnosis of common articular findings seen on chest CT with recommendations for appropriate follow-up evaluation.

Incidental osseous lesions on chest CT: an algorithmic approach for radiologists.

Numerous osseous findings are commonly discovered incidentally at chest CTs in daily practice. A broad spectrum of these findings ranges from benign and do not touch lesions to ominous conditions requiring further imaging evaluation and/or intervention. Interpretation of these incidental musculoskeletal findings may constitute a diagnostic challenge to radiologists. This review provides a systematic, algorithmic approach to common osseous lesions on chest CT based on imaging findings with recommendations for proper next step management.

A Review of Posteromedial Lesions of the Chest Wall: What Should a Chest Radiologist Know?

A heterogeneous group of tumors can affect the posteromedial chest wall. They form diverse groups of benign and malignant (primary or secondary) pathologies that can arise from different chest wall structures, i.e., fat, muscular, vascular, osseous, or neurogenic tissues. Chest radiography is very nonspecific for the characterization of chest wall lesions. The modality of choice for the initial assessment of the chest wall lesions is computed tomography (CT). More advanced cross-sectional modalities such as magnetic resonance imaging (MRI) and positron emission tomography (PET) with fluorodeoxyglucose are usually used for further characterization, staging, treatment response, and assessment of recurrence. A systematic approach based on age, clinical history, and radiologic findings is required for correct diagnosis. It is essential for radiologists to be familiar with the spectrum of lesions that might affect the posteromedial chest wall and their characteristic imaging features. Although the imaging findings of these tumors can be nonspecific, cross-sectional imaging helps to limit the differential diagnosis and determine the further diagnostic investigation (e.g., image-guided biopsy). Specific imaging findings, e.g., location, mineralization, enhancement pattern, and local invasion, occasionally allow a particular diagnosis. This article reviews the posteromedial chest wall anatomy and different pathologies. We provide a combination of location and imaging features of each pathology. We will also explore the role of imaging and its strengths and limitations for diagnosing posteromedial chest wall lesions.

Mediastinal Lymphadenopathy in the National Lung Screening Trial (NLST) Is Associated with Interval Lung Cancer.

Background There are currently no evidence-based guidelines for the management of enlarged mediastinal lymph nodes found on lung cancer screening (LCS) CT scans. Purpose To assess the frequency and clinical significance of enlarged mediastinal lymph nodes on the initial LCS CT scans in National Lung Screening Trial (NLST) participants. Materials and Methods A retrospective review of the NLST database identified all CT trial participants with at least one enlarged (≥1.0 cm) mediastinal lymph node identified by site readers on initial CT scans. Each study was reviewed independently by two thoracic radiologists to measure the two largest nodes and to record morphologic characteristics. Scans with extensively calcified mediastinal lymph nodes or nodes measuring less than 1 cm were excluded. Frequency and time to lung cancer diagnosis, lung cancer stage, and histologic findings were compared between NLST participants with and without lymphadenopathy. Results Of the 26 722 NLST participants, 422 (1.6%) had enlarged noncalcified mediastinal lymph nodes on the initial LCS CT scan. Mediastinal lymphadenopathy was associated with an increase in lung cancer cases (72 of 422 participants [17.1%; 95% CI: 13.6, 21.0] vs 1017 of 26 300 [3.9%; 95% CI: 3.6, 4.1]; P < .001), earlier diagnosis (restricted mean survival time ± standard error, 2285 days ± 44 vs 2611 days ± 2; P < .001), the presence of lung nodules (P < .001), advanced stage at presentation (22 of 72 participants [31%] with cancer at stage IIIA vs 410 of 1017 [40.3%] at stage IA; P < .001), and increased mortality (P < .001). The majority of participants with lung cancers in the LCS group with mediastinal lymphadenopathy were detected at initial LCS CT (50 of 422 participants [11.8%; 95% CI: 8.9, 15.3] vs T1-T7, 22 of 422 [5.3%; 95% CI: 3.3, 7.8]; P < .001). There was no association between mediastinal lymphadenopathy and lung cancer histologic findings, CT appearance, or location of lung nodules (P > .05 based on unadjusted pairwise association analyses). Conclusion Noncalcified mediastinal lymphadenopathy in the low-dose lung cancer screening study sample was associated with an increase in lung cancer, an earlier diagnosis, more advanced-stage disease, and increased mortality. More aggressive treatment of these patients appears warranted. © RSNA, 2021 Online supplemental material is available for this article. See also the editorials by McLoud and by Mascalchi and Zompatori in this issue.

Deep learning classification of COVID-19 in chest radiographs: performance and influence of supplemental training.

Purpose: Accurate classification of COVID-19 in chest radiographs is invaluable to hard-hit pandemic hot spots. Transfer learning techniques for images using well-known convolutional neural networks show promise in addressing this problem. These methods can significantly benefit from supplemental training on similar conditions, considering that there currently exists no widely available chest x-ray dataset on COVID-19. We evaluate whether targeted pretraining for similar tasks in radiography labeling improves classification performance in a sample radiograph dataset containing COVID-19 cases. Approach: We train a DenseNet121 to classify chest radiographs through six training schemes. Each training scheme is designed to incorporate cases from established datasets for general findings in chest radiography (CXR) and pneumonia, with a control scheme with no pretraining. The resulting six permutations are then trained and evaluated on a dataset of 1060 radiographs collected from 475 patients after March 2020, containing 801 images of laboratory-confirmed COVID-19 cases. Results: Sequential training phases yielded substantial improvement in classification accuracy compared to a baseline of standard transfer learning with ImageNet parameters. The test set area under the receiver operating characteristic curve for COVID-19 classification improved from 0.757 in the control to 0.857 for the optimal training scheme in the available images. Conclusions: We achieve COVID-19 classification accuracies comparable to previous benchmarks of pneumonia classification. Deliberate sequential training, rather than pooling datasets, is critical in training effective COVID-19 classifiers within the limitations of early datasets. These findings bring clinical-grade classification through CXR within reach for more regions impacted by COVID-19.

Complications of Lung Transplantation: Update on Imaging Manifestations and Management.

As lung transplantation has become the most effective definitive treatment option for end-stage chronic respiratory diseases, yearly rates of this surgery have been steadily increasing. Despite improvement in surgical techniques and medical management of transplant recipients, complications from lung transplantation are a major cause of morbidity and mortality. Some of these complications can be classified on the basis of the time they typically occur after lung transplantation, while others may occur at any time. Imaging studies, in conjunction with clinical and laboratory evaluation, are key components in diagnosing and monitoring these conditions. Therefore, radiologists play a critical role in recognizing and communicating findings suggestive of lung transplantation complications. A description of imaging features of the most common lung transplantation complications, including surgical, medical, immunologic, and infectious complications, as well as an update on their management, will be reviewed here. Keywords: Pulmonary, Thorax, Surgery, Transplantation Supplemental material is available for this article. © RSNA, 2021.

CT evaluation of unrepaired/incidental congenital cardiovascular diseases in adults.

Congenital heart disease (CHD) affects approximately one million people in the USA with the number increasing by 5% each year. Patients are usually both diagnosed and treated in infancy, however many of them may have subclinical CHD that remains undiagnosed until late adulthood. Patients with complex CHD tend to be symptomatic and are diagnosed at a younger age than those with a single defect. CHDs can be divided into three categories, including cardiac, great vessels and coronary artery anomalies. Recent advances in computed tomography (CT) technology with faster acquisition time and improved spatial resolution allow for detailed evaluation of cardiac morphology and function. The concomitant increased utilization of CT has simultaneously led to more sensitive detection and more thorough diagnosis of CHD. Recognition of and understanding the imaging attributes specific to each anomaly is important for radiologists in order to make a correct and definite diagnosis. This article reviews the spectrum of CHDs, which persist into adulthood that may be encountered by radiologists on CT.

Ultrasound Training in Radiology Residency Programs: A National Survey.

OBJECTIVES: Comprehensive training in ultrasound (US) imaging during radiology residency is crucial if radiologists are expected to maintain a substantial role in this widely used imaging modality. This study aimed to evaluate the current curriculum of US training among radiology residency programs across the country via a nationwide survey. METHODS: A 28-question survey was distributed among all academic radiology departments in the United States and their radiology residents. The survey consisted of 4 sections: general demographic information, training information, clinical competency, and adequacy of training (perspective). The Student t test and 1-way analyses of variance were performed to assess statistical significance. RESULTS: Overall, 256 residents from 32 states completed the questionnaire. Only 114 (45%) residents reported having a dedicated rotation for performing US studies. Although 228 (89%) of trainees believed they received adequate experience for interpreting US studies, only 66 (26%) of them had the same belief about performing them. Only 116 (45%) of the residents were comfortable operating the US machines in their departments. Higher years of residency training, having a dedicated rotation for performing US studies, and having more than 10 hours per year of didactic lectures and/or more than 5 hours per year of case conferences dedicated to US had a positive impact on the residents' clinical competency and perspective (all P < .05). CONCLUSIONS: Most radiology residents do not feel confident in performing US examinations by themselves. However, higher clinical competency was reported in the residents who had dedicated rotations for performing US studies and received more hours of US lectures and case conferences throughout their residency.

Virtual Imaging Trials for Coronavirus Disease (COVID-19).

OBJECTIVE. The virtual imaging trial is a unique framework that can greatly facilitate the assessment and optimization of imaging methods by emulating the imaging experiment using representative computational models of patients and validated imaging simulators. The purpose of this study was to show how virtual imaging trials can be adapted for imaging studies of coronavirus disease (COVID-19), enabling effective assessment and optimization of CT and radiography acquisitions and analysis tools for reliable imaging and management of COVID-19. MATERIALS AND METHODS. We developed the first computational models of patients with COVID-19 and as a proof of principle showed how they can be combined with imaging simulators for COVID-19 imaging studies. For the body habitus of the models, we used the 4D extended cardiac-torso (XCAT) model that was developed at Duke University. The morphologic features of COVID-19 abnormalities were segmented from 20 CT images of patients who had been confirmed to have COVID-19 and incorporated into XCAT models. Within a given disease area, the texture and material of the lung parenchyma in the XCAT were modified to match the properties observed in the clinical images. To show the utility, three developed COVID-19 computational phantoms were virtually imaged using a scanner-specific CT and radiography simulator. RESULTS. Subjectively, the simulated abnormalities were realistic in terms of shape and texture. Results showed that the contrast-to-noise ratios in the abnormal regions were 1.6, 3.0, and 3.6 for 5-, 25-, and 50-mAs images, respectively. CONCLUSION. The developed toolsets in this study provide the foundation for use of virtual imaging trials in effective assessment and optimization of CT and radiography acquisitions and analysis tools to help manage the COVID-19 pandemic.

A comparison of COVID-19 and imaging radiation risk in clinical patient populations.

The outbreak of coronavirus SARS-COV2 affected more than 180 countries necessitating fast and accurate diagnostic tools. Reverse transcriptase polymerase chain reaction (RT-PCR) has been identified as a gold standard test with Chest CT and Chest Radiography showing promising results as well. However, radiological solutions have not been used extensively for the diagnosis of COVID-19 disease, partly due to radiation risk. This study aimed to provide quantitative comparison of imaging radiation risk versus COVID risk. The analysis was performed in terms of mortality rate per age group. COVID-19 mortality was extracted from epidemiological data across 299, 004 patients published by ISS-Integrated surveillance of COVID-19 in Italy. For radiological risk, the study considered 659 Chest CT performed in adult patients. Organ doses were estimated using a Monte Carlo method and then used to calculate Risk Index that was converted into an upper bound for related mortality rate following NCI-SEER data. COVID-19 mortality showed a rapid rise for ages >30 years old (min: 0.30%; max: 30.20%), whereas only four deaths were reported in the analysed patient cohort for ages <20 years old. The rates decreased for radiation risk across age groups. The median mortality rate across all ages for Chest-CT and Chest-Radiography were 0.007% (min: 0.005%; max: 0.011%) and 0.0003% (min: 0.0002%; max: 0.0004%), respectively. COVID-19, Chest Radiography, and Chest CT mortality rates showed different magnitudes and trends across age groups. In higher ages, the risk of COVID-19 far outweighs that of radiological exams. Based on risk comparison alone, Chest Radiography and CT for COVID-19 care is justified for patients older than 20 and 30 years old, respectively. Notwithstanding other aspects of diagnosis, the present results capture a component of risk consideration associated with the use of imaging for COVID. Once integrated with other diagnostic factors, they may help inform better management of the pandemic.

Chronic airspace disease: Review of the causes and key computed tomography findings.

Chronic airspace diseases are commonly encountered by chest, body or general radiologists in everyday practice. Even though there is significant overlap in the imaging findings of different causes of chronic airspace disease, some key clinical, laboratory and imaging findings can be used to guide the radiologist to the correct diagnosis. The goal of this article is to review and compare these features.