Faculty Bibliography

Pulmonary nodules are the most common incidental finding in the chest, particularly on computed tomographs that include a portion or all of the chest, and may be encountered more frequently with increasing utilization of cross-sectional imaging. Established guidelines address the reporting and management of incidental pulmonary nodules, both solid and subsolid, synthesizing nodule and patient features to distinguish benign nodules from those of potential clinical consequence. Standard nodule assessment is essential for the accurate reporting of nodule size, attenuation, and morphology, all features with varying risk implications and thus management recommendations.

During the coronavirus disease 2019 (COVID-19) pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3661 patients, achieves an area under the receiver operating characteristic curve (AUC) of 0.786 (95% CI: 0.745-0.830) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at New York University Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

Chest CT angiography (CTA) is essential in the diagnosis of acute aortic syndromes. Chest CTA quality can be optimized with attention to technical parameters pertaining to noncontrast imaging, timing of contrast-enhanced imaging, contrast material volume, kilovolt potential, tube-current modulation, and decisions regarding electrocardiographic-gating and ultra-fast imaging, which may affect the accurate diagnosis of acute aortic syndromes. An understanding of methods to apply to address suboptimal image quality is useful, as the accurate identification of acute aortic syndromes is essential for appropriate patient management. Acute aortic syndromes have high morbidity and mortality, particularly when involving the ascending aorta, and include classic aortic dissection, penetrating atherosclerotic ulcer, and acute intramural hematoma. An understanding of the pathogenesis and distinguishing imaging features of acute aortic syndromes and aortic rupture and some less common manifestations is helpful when interpreting imaging examinations. Related entities, such as ulcerated plaque, ulcerlike projections, and intramural blood pools, and mimics, such as vasculitis and aortic thrombus, are important to recognize; knowledge of these is important to avoid interpretive pitfalls. In addition, an awareness of postsurgical aortic changes can be useful when interpreting CTA examinations when patient history is incomplete. The authors review technical considerations when performing CTA, discuss acute aortic syndromes, and highlight diagnostic challenges encountered when interpreting aortic CTA examinations. ^©RSNA, 2021.

The rapid spread of COVID-19 cases in recent months has strained hospital resources, making rapid and accurate triage of patients presenting to emergency departments a necessity. Machine learning techniques using clinical data such as chest X-rays have been used to predict which patients are most at risk of deterioration. We consider the task of predicting two types of patient deterioration based on chest X-rays: adverse event deterioration (i.e., transfer to the intensive care unit, intubation, or mortality) and increased oxygen requirements beyond 6 L per day. Due to the relative scarcity of COVID-19 patient data, existing solutions leverage supervised pretraining on related non-COVID images, but this is limited by the differences between the pretraining data and the target COVID-19 patient data. In this paper, we use self-supervised learning based on the momentum contrast (MoCo) method in the pretraining phase to learn more general image representations to use for downstream tasks. We present three results. The first is deterioration prediction from a single image, where our model achieves an area under receiver operating characteristic curve (AUC) of 0.742 for predicting an adverse event within 96 hours (compared to 0.703 with supervised pretraining) and an AUC of 0.765 for predicting oxygen requirements greater than 6 L a day at 24 hours (compared to 0.749 with supervised pretraining). We then propose a new transformer-based architecture that can process sequences of multiple images for prediction and show that this model can achieve an improved AUC of 0.786 for predicting an adverse event at 96 hours and an AUC of 0.848 for predicting mortalities at 96 hours. A small pilot clinical study suggested that the prediction accuracy of our model is comparable to that of experienced radiologists analyzing the same information.

OBJECTIVE:To evaluate diaphragmatic excursion as a quantitative metric for change in lung volume between inspiratory and expiratory chest computed tomography (CT) images. METHODS:A 12-month retrospective review identified 226 chest CT exams with inspiratory and expiratory phase imaging, 63 in individuals referred with diagnosis of asthma by ICD9/10 code. Exams acquired in the supine position at 1.25 mm slice thickness in each phase were included (n = 30, mean age = 62, M = 15, F = 15). Diaphragmatic excursion was calculated as the difference between axial slices through the lungs on inspiration and expiration, using the lung apex as the cranial bound, and the hemidiaphragm caudally. Inspiratory and expiratory lung and tracheal volumes were calculated through volumetric segmentation. Tracheal morphology was assessed at 1 cm above the level of the aortic arch, and 1 cm above the carina. RESULTS:Inspiratory and expiratory lung volumes were higher in men (mean I = 5 + 1.6 L, E = 3.1 + 1.2 L) than women (mean I = 3.6 + 0.8 L, E = 2.4 + 0.7 L), p = .005 and p = .047, respectively. Average inspiratory and expiratory tracheal volumes were higher in men (I = 61 + 17 mL, E = 43 + 14) than women (I = 44 + 14, E = 30 + 8), p = .006 and p = .005. Average change in lung and tracheal volume between inspiratory and expiratory scans did not significantly differ between men and women. Average diaphragmatic excursion was 2.5 cm between inspiratory and expiratory scans (2.7 cm in men, 2.3 cm in women; p = .5). There was a strong positive correlation between diaphragmatic excursion and change in lung (r = .84) and tracheal volume (r = .79). A moderate correlation was also found between change in tracheal volume and change in lung volume (r = 0.67). Change in tracheal morphology between inspiratory and expiratory imaging was associated with change in tracheal volume at both 1 cm above the aortic arch (p = .04) and 1 cm above the carina (p = .008); there was no association with diaphragmatic excursion or lung volume. CONCLUSIONS:Diaphragmatic excursion is a quantitative measure of expiratory effort as validated by both lung and tracheal volumes in asthma patients, and may be more accurate than qualitative assessment based on tracheal morphology.

OBJECTIVES/OBJECTIVE:To describe the histologic features that are helpful in the diagnosis of the rare bronchiolar adenomas/ciliated muconodular papillary tumors (BAs/CMPTs) during intraoperative consultation. METHODS:Multi-institutional retrospective review of frozen sections of 18 BAs/CMPTs. RESULTS:In 14 of 18 cases, BA/CMPT was the primary reason for sublobar lung resection, and in 4 cases, BA/CMPT was an incidental finding intraoperatively for resections performed for carcinoma in other lobes. There were 11 proximal-type/classic BAs/CMPTs and 7 distal-type/nonclassic BAs/CMPTs. Only 3 (16.7%) of 18 were correctly diagnosed at the time of frozen section, all of which were proximal type/classic. The remainder were diagnosed as adenocarcinoma (n = 7); invasive mucinous adenocarcinoma (n = 1); non-small cell lung carcinoma (n = 1); cystic mucinous neoplasm, favor adenocarcinoma (either mucinous or colloid type) (n = 1); favor adenocarcinoma, cannot exclude CMPT (n = 1); atypical proliferation (n = 2); mucinous epithelial proliferation (n = 1); and mucous gland adenoma (n = 1). CONCLUSIONS:BA/CMPT can potentially be misdiagnosed as carcinoma during intraoperative consultation. On retrospective review of the frozen sections, the presence of the following may help to avoid misdiagnosis: a mixture of bland ciliated columnar cells, mucinous cells, and, most important, a basal cell layer, as well as a lack of necrosis, significant atypia, and mitoses.

Subsolid nodules are common on chest CT and may be either benign or malignant. Their varied features, and broad differential diagnoses present management challenges. While subsolid nodules often represent lung adenocarcinomas, other possibilities are common, and influence management. Practice guidelines exist for subsolid nodule management for both incidentally and screening-detected nodules, incorporating patient and nodule characteristics. This review will highlight similarities and differences amongst these algorithms, with the intent of providing a resource for comparison, and aid in choosing management options.

Anterior mediastinal lesions while rare, are heterogeneous in etiology, with broad differential considerations that may be narrowed by drawing on discriminating clinical, radiologic, and histopathologic features. This manuscript will review the radiographic and pathologic correlation of anterior mediastinal lesions of thymic, lymphomatous, and germ-cell origin.

During the COVID-19 pandemic, rapid and accurate triage of patients at the emergency department is critical to inform decision-making. We propose a data-driven approach for automatic prediction of deterioration risk using a deep neural network that learns from chest X-ray images, and a gradient boosting model that learns from routine clinical variables. Our AI prognosis system, trained using data from 3,661 patients, achieves an AUC of 0.786 (95% CI: 0.742-0.827) when predicting deterioration within 96 hours. The deep neural network extracts informative areas of chest X-ray images to assist clinicians in interpreting the predictions, and performs comparably to two radiologists in a reader study. In order to verify performance in a real clinical setting, we silently deployed a preliminary version of the deep neural network at NYU Langone Health during the first wave of the pandemic, which produced accurate predictions in real-time. In summary, our findings demonstrate the potential of the proposed system for assisting front-line physicians in the triage of COVID-19 patients.

Background We observed a high number of patients with COVID-19 pneumonia who had barotrauma related to invasive mechanical ventilation at our institution. Purpose To determine if the rate of barotrauma in patients with COVID-19 infection was greater than other patients requiring invasive mechanical ventilation at our institution. Methods In this retrospective study, clinical and imaging data of patients seen between 03/01/2020 and 04/06/2020 who tested positive for COVID-19 and experienced barotrauma associated with invasive mechanical ventilation were compared to patients without COVID-19 infection during the same period. Historical comparison was made to barotrauma rates of patients with acute respiratory distress syndrome (ARDS) from 02/01/2016 to 02/01/2020 at our institution. Comparison of patient groups was performed using categorical or continuous statistical testing as appropriate with multivariable regression analysis. Patient survival was assessed using Kaplan-Meier curves analysis. Results 601 patients with COVID-19 infection underwent invasive mechanical ventilation (63 ± 15 years, 71% men). There were 89/601 (15%) patients with one or more barotrauma events, for a total of 145 barotrauma events (24% overall events) (95% CI 21-28%). During the same period, 196 patients without COVID-19 infection (64 ± 19 years, 52% male) with invasive mechanical ventilation had 1 barotrauma event (.5% 95% CI, 0-3%, p<.001 vs. the group with COVID-19 infection). Of 285 patients with ARDS over the prior 4 years on invasive mechanical ventilation (68 ± 17 years, 60% men), 28 patients (10%) had 31 barotrauma events, with overall barotrauma rate of 11% (95% CI 8-15%, p<.001 vs. the group with COVID-19 infection). Barotrauma is an independent risk factor for death in COVID-19 (OR=2.2, p=.03), and is associated with longer hospital length of stay (OR=.92, p<.001). Conclusion Patients with COVID-19 infection and invasive mechanical ventilation had a higher rate of barotrauma than patients with ARDS and patients without COVID-19 infection.