COVID-19 classification of X-ray images using deep neural networks.

OBJECTIVES: In the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model's results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals. METHODS: In this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image. RESULTS: Our model achieved accuracy of 90.3%, (95% CI: 86.3-93.7%) specificity of 90% (95% CI: 84.3-94%), and sensitivity of 90.5% (95% CI: 85-94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93-0.97). CONCLUSION: We provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19. KEY POINTS: • A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%. • A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model's image embeddings.

The management of cardiac implantable electronic device lead perforations: a multicentre study.

AIMS: Lead perforation is a rare, well-known complication of cardiac implantable electronic device (CIED) implants, whose management is mostly not evidence-based. Main management strategies include conservative approach based on clinical and lead function follow-up vs. routine invasive lead revision approach. This study compared the complications of both strategies by composite endpoint, including recurrent perforation-related symptoms, recurrent pericardial effusion (PEf), lead dysfunction, and device infection during 12 month follow-up. METHODS AND RESULTS: Multicentre retrospective analysis, inquiring data from imaging studies, device interrogation, pericardiocentesis, and clinical charts of patients with suspected perforating leads between 2007 and 2014 in five hospitals. All cases were reviewed by electrophysiologist and defined as definite perforations by suggestive symptoms along with lead perforation on imaging, bloody PEf on pericardiocentesis shortly after implant, or right ventricular (RV) lead non-capture along with diaphragmatic stimulation upon bipolar pacing. Clinical outcomes associated with both management approaches were compared, with respect to the composite endpoint. The study included 48 definitive perforation cases: 22 managed conservatively and 26 via lead revision. Conservative management was associated with an increased composite endpoint compared with lead revision (8/22 vs. 1/26; P = 0.007). The dominant complication among the conservative cohort was appearance of cardiac tamponade during follow-up; 5/6 occurring in cases which presented with no or only mild PEf and were treated by antiplatelets/coagulants during or shortly after CIED implantation. CONCLUSION: A conservative management of CIED lead perforation is associated with increased complications compared with early lead revision. Lead revision may be the preferred management particularly in patients receiving antiplatelets/coagulants.

Radiological artificial intelligence - predicting personalized immunotherapy outcomes in lung cancer.

Personalized medicine has revolutionized approaches to treatment in the field of lung cancer by enabling therapies to be specific to each patient. However, physicians encounter an immense number of challenges in providing the optimal treatment regimen for the individual given the sheer complexity of clinical aspects such as tumor molecular profile, tumor microenvironment, expected adverse events, acquired or inherent resistance mechanisms, the development of brain metastases, the limited availability of biomarkers and the choice of combination therapy. The integration of innovative next-generation technologies such as deep learning-a subset of machine learning-and radiomics has the potential to transform the field by supporting clinical decision making in cancer treatment and the delivery of precision therapies while integrating numerous clinical considerations. In this review, we present a brief explanation of the available technologies, the benefits of using these technologies in predicting immunotherapy response in lung cancer, and the expected future challenges in the context of precision medicine.

Distribution of Aeration and Pulmonary Blood Volume in Healthy, ARDS and COVID-19 Lungs: A Dual-Energy Computed Tomography Retrospective Cohort Study.

RATIONALE AND OBJECTIVES: Few reports have studied lung aeration and perfusion in normal lungs, COVID-19, and ARDS from other causes (NC-ARDS) using dual-energy computed tomography pulmonary angiograms (DE-CTPA). To describe lung aeration and blood-volume distribution using DE-CTPAs of patients with NC-ARDS, COVID-19, and controls with a normal DE-CTPA ("healthy lungs"). We hypothesized that each of these conditions has unique ranges of aeration and pulmonary blood volumes. MATERIALS AND METHODS: This retrospective, single-center study of DE-CTPAs included patients with COVID-19, NC-ARDS (Berlin criteria), and controls. Patients with macroscopic pulmonary embolisms were excluded. The outcomes studied were the (1) lung blood-volume in areas with different aeration levels (normal, ground glass opacities [GGO], consolidated lung) and (2) aeration/blood-volume ratios. RESULTS: Included were 20 patients with COVID-19 (10 milds, 10 moderate-severe), six with NC-ARDS, and 12 healthy-controls. Lung aeration was lowest in patients with severe COVID-19 24% (IQR13%-31%) followed by those with NC-ARDS 40%(IQR21%-46%). Blood-volume in GGO was lowest in patients with COVID-19 [moderate-severe:-28.6 (IQR-33.1-23.2); mild: -30.1 (IQR-33.3-23.4)] and highest in normally aerated areas in NC-ARDS -37.4 (IQR-52.5-30.2-) and moderate-severe COVID-19 -33.5(IQR-44.2-28.5). The median aeration/blood-volume ratio was lowest in severe COVID-19 but some values overlapped with those observed among patients with NC-ARDS. CONCLUSION: Severe COVID-19 disease is associated with low total aerated lung volume and blood-volume in areas with GGO and overall aeration/blood volume ratios, and with high blood volume in normal lung areas. In this hypothesis-generating study, these findings were most pronounced in severe COVID disease. Larger studies are needed to confirm these preliminary findings.

Image quality of low-energy pulmonary CT angiography: comparison with standard CT.

OBJECTIVE: The purpose of this article is to prospectively compare visualization of central and peripheral pulmonary arteries on simultaneously acquired low-energy and standard pulmonary CT angiography. SUBJECTS AND METHODS: Thirty-three consecutive patients (20 women and 13 men; mean age, 55.6 years; range, 21-92 years) with suspected pulmonary embolism (PE) were scanned (140 kVp; 250-300 mA) on a single-source dual-layer dual-energy MDCT scanner. Attenuation and image noise were measured at the main and segmental pulmonary arteries. Signal-to-noise ratios were calculated. Two blinded experienced radiologists assessed segmental and subsegmental artery visibility in consensus, using slab maximum-intensity-projection (MIP) reconstructions. Nonparametric sign test and kappa statistic were used for statistical analysis. RESULTS: PE was detected in three patients (9.1%); two segmental vessel and subsegmental emboli were seen in the low-energy images only. Higher attenuation was noted in low-energy versus standard images for all arteries evaluated, with a mean (± SD) increase of 66.6 ± 4.4 HU (p < 0.0001). Low-energy images improved visualization of segmental and subsegmental arteries from 97.0% to 99.2% and from 88.0% to 93.9%, respectively. A larger number of subsegmental vessels was seen on low-energy MIP reconstructions in 69.7% (95% CI, 36.5-71.89%) of studies compared with 9.1% on the standard images. Visualization of subsegmental vessels was superior in 55.5% of cases using low-energy imaging. The mean image noise increased by 9.7 ± 0.6 HU (p < 0.0001). The mean signal-to-noise ratio showed no significant difference in the low-energy (8.2) versus standard (8.1) CT images (p = 0.7759). CONCLUSION: Improved visualization of central and peripheral arteries can be obtained with low-energy pulmonary CT angiography, without a substantial decrease in image quality.

Severe influenza A (H1N1): the course of imaging findings.

BACKGROUND: An outbreak of respiratory illness caused by a novel swine-origin influenza virus (influenza A/H1N1 2009) that began in Mexico was declared a global pandemic by the World Health Organization in June 2009. The pandemic affected many countries, including Israel. OBJECTIVES: To compare the course of chest radiographic and computed tomography findings in patients who survived and those who died following admission to the intensive care unit (ICU) or intubation due to severe laboratory-confirmed swine-origin influenza A/H1N1 2009. METHODS: We retrospectively reviewed the patient records (267 radiographs, 8 CTs) of 22 patients (10 males, 12 females) aged 3.5-66 years (median 34) with confirmed influenza A/ H1N1 2009, admitted to the ICU and/or intubated in five major Israeli medical centers during the period July-November 2009. We recorded demographic, clinical, and imaging findings--including pattern of opacification, extent, laterality, distribution, zone of findings, and presence/absence of nodular opacities--at initial radiography and during the course of disease, and compared the findings of survivors and non-survivors. Statistical significance was calculated using the Wilcoxon (continuous variables) and Fisher exact tests. RESULTS: The most common findings on the initial chest radiography were airspace opacities, which were multifocal in 17 patients (77%) and bilateral in 16 (73%), and located in the lower or lower and middle lung zones in 19 patients (86%). Large airspace nodules with indistinct margins were seen in 8 patients (36%). Twelve patients survived, 10 died. Patients who died had multiple background illnesses and were significantly older than survivors (P = 0.006). Radiologic findings for the two groups were not significantly different. CONCLUSION: Airspace opacities, often with nodular appearance, were the most common findings among patients with severe influenza A/H1N1 2009. The course of radiologic findings was similar in patients with severe influenza A/ H1N1 2009 who survived and those who died.

Bilateral Adrenal Hemorrhage in Coronavirus Disease 2019 Patient: A Case Report.

CONTEXT: Bilateral adrenal hemorrhage is a rare condition with potentially life-threatening consequences such as acute adrenal insufficiency. Early adrenal axis testing, as well as directed imaging, is crucial for immediate diagnosis and treatment. Coronavirus disease 2019 (COVID-19) has been associated with coagulopathy and thromboembolic events. CASE DESCRIPTION: A 66-year-old woman presented with acute COVID-19 infection and primary adrenal insufficiency due to bilateral adrenal hemorrhage (BAH). She also had a renal vein thrombosis. Her past medical history revealed primary antiphospholipid syndrome (APLS). Four weeks after discharge she had no signs of COVID-19 infection and her polymerase chain reaction test for COVID-19 was negative, but she still needed glucocorticoid and mineralocorticoid replacement therapy. The combination of APLS and COVID-19 was probably responsible of the adrenal event as a "two-hit" mechanism. CONCLUSIONS: COVID-19 infection is associated with coagulopathy and thromboembolic events, including BAH. Adrenal insufficiency is life threatening; therefore, we suggest that early adrenal axis testing for COVID-19 patients with clinical suspicion of adrenal insufficiency should be carried out.

The radiological myometrial appearance after cesarean section: is it associated with postpartum complications and subsequent delivery outcome?

PURPOSE: To evaluate whether the characteristics of the radiological uterine myometrial discontinuity (RMD) is associated with maternal-neonatal outcomes and post-cesarean section (CS) complications. A secondary aim was to describe the evolution of the CT uterine surgical incision and the related outcome of a subsequent trial of labor after cesarean (TOLAC). METHODS: Single center retrospective cohort study of CT scans was performed within 6 weeks from cesarean delivery. Demographic characteristics of patients were recorded (age, intrapartum fever, CS data, and hospital stay length). Abdominopelvic CT scans were performed using a multidetector CT (16 or 256 slice) with intravenous contrast material. CT analysis was performed by two radiologists in consensus. The RMD seen as low attenuation gap in expected incision site was assessed for: visualization, thickness, and presence of gas. Logistic regression analysis was fitted to assess the relationship of the delivery-CT time interval with the presence of RMD and gas. RESULTS: Of a total of 75,791 births during the study period there were 8775 CS (11.6%). The study group consisted of 101 CTs in 84 woman after CS. RMD defined in 73 (72.2%) of all CT exams; the mean RMD thickness was 7 mm ± 3.9, "RMD gas" observed in 15 (17.9%) of CT exams. RMD thickness or gas presence were strongly associated with a CS-1st CT exam time interval of less than 7 days, OR 5.8 [CI 1.5-22.6], p = 0.010, but not with maternal, delivery, or neonatal characteristics. A subsequent successful vaginal birth was achieved in 75% of the patients with no uterine rupture, regardless of the RMD gas presence. CONCLUSION: RMD gas visualization on CT is not associated with febrile morbidity, cesarean characteristics, and subsequent TOLAC results. RMD gas is a normal post-operative finding and should not lead to changes in the postpartum delivery complication management or recommendations for the future mode of delivery.

Cardiac CT of the transplanted heart: indications, technique, appearance, and complications.

Effective antirejection therapy and infection control have significantly improved the long-term survival of heart transplant recipients, but coronary allograft vasculopathy remains an important limiting factor. Most heart transplant recipients undergo annual coronary angiography for the detection of allograft vasculopathy, which is often clinically silent. Angiography allows detection of vasculopathy only indirectly, with depiction of the lumen, and does not depict the wall thickening and intimal hyperplasia that typify this disease; the procedure also is invasive and is associated with a 1%-2% risk of complication. In contrast, electrocardiographically gated multidetector computed tomography (CT) can provide a comprehensive and noninvasive evaluation of the transplanted heart in a single study. Cardiac CT enables evaluation of the coronary artery lumen and wall and thus may be used for screening, diagnosis, grading, and follow-up of coronary allograft vasculopathy. It also may be used to detect other posttransplantation complications, such as malignancy and infection, and to assess cardiac and vascular anastomoses and cardiac function. However, special strategies may be needed to reduce the transplant heart rate so as to obtain images of diagnostic quality.

CT pulmonary angiography for the detection of pulmonary embolism: interobserver agreement between on-call radiology residents and specialists (CTPA interobserver agreement).

PURPOSE: The aim of this study was to prospectively determine interobserver agreement between on-call radiology residents and specialists in the interpretation of computed tomographic pulmonary angiography (CTPA). METHODS: CTPA examinations obtained between January 2002 and March 2003 were interpreted by a radiology resident on call and by two radiology specialists. Agreement was assessed using percentage of agreement between interpreters and by the kappa coefficient. Sensitivity of residents' interpretations was calculated by relating them to the interpretation of Specialist 1, which served as the gold standard. RESULTS: Of the 81 CTPA examinations evaluated, there was agreement of 93% and 91% for the diagnosis of pulmonary embolism (PE) and of 97% and 85% for the exclusion of PE with Specialist 1 and 2, respectively. The concordance between residents' interpretations and those of Specialist 1 was very high (kappa=.8), and with those of Specialist 2 was high (kappa=.7). In all cases of agreement between the two specialists, there was complete agreement between the specialists' and the residents' intepretations. CONCLUSIONS: Our study showed good to very good agreement of residents' interpretations with each of the radiology specialists. Therefore, relying on the residents' preliminary interpretations during after-hour calls is reasonable.

Interobserver and intraobserver variability in the assessment of pulmonary nodule size on CT using film and computer display methods.

RATIONALE AND OBJECTIVES: A critical element in determining biologic behavior of pulmonary nodules is volume and temporal volume change. We evaluate variability in nodule volume among readers and measuring methods. MATERIALS AND METHODS: 55 small (<2 cm) lung nodules were measured in long- and short-axis dimensions independently by 4 radiologists, using 3 methods: 1) hard copy, 2) GE Advantage Windows workstation (GE Healthcare, Milwaukee, WI), 3) Siemens IMACS workstation (Siemens Medical Systems, Iselan, NJ). Nodule margin was recorded as smooth, lobulated, or spiculated. Volume was calculated from diameter measurements. Variability in nodule volume was evaluated within each reader, between readers, and across measurement tools. RESULTS: Mean nodule short-axis diameter was 5.3 mm; mean long-axis diameter 7.2 mm. There was statistically significant variation among readers and measurement method for nodule volume. Volume was significantly larger using hard-copy measurements (51.9%-54.1% variation; P < .0001) than either workstation, and not different between workstations. There was greater intraobserver variability in volume using the hard-copy method, and no difference between workstation methods. Volumes based on measurements from one reader were consistently lower than those from other readers (P = < .001, .003, and .02); volume was consistently larger for another reader (P < .0001, .03, and .12). Reader agreement for nodule margin was good to excellent. CONCLUSION: Considerable interobserver and intraobserver variability in measuring nodules exists using hard-copy and computer tools. Since a small change in diameter indicates a much larger change in volume, this may be significant when using early repeat CT to follow small pulmonary nodules. Computer-aided diagnostic tools that reproducibly measure nodule volume are strongly needed.

Leukocyte telomere length and coronary artery calcification in Palestinians.

OBJECTIVE: Shorter leukocyte telomere length (LTL) is associated with higher incidence of coronary heart disease (CHD) and increased mortality. We examined the association of LTL with coronary artery calcification (CAC), which reflects the cumulative burden of coronary atherosclerosis, in an urban Arab sample of Palestinians, a population at high risk of CHD. METHODS: Using a cross-sectional design, a random sample of East Jerusalem residents, comprising 250 men aged 45-77 and women aged 55-76 and free of CHD or past stroke, was drawn from the Israel national population register. LTL was measured by Southern blots. CAC was determined by 16-slice multidetector helical CT scanning using Agatston scoring. We applied multivariable logistic modeling to examine the association between sex-specific tertiles of LTL and CAC (comparing scores >100 vs. <100, and the upper third vs. the lower 2 thirds), controlling for age, sex, education and coronary risk factors. RESULTS: CAC, evident in 65% of men and 52% of women, was strongly associated with age (sex-adjusted Spearman's rho 0.495). The multivariable-adjusted odds ratios for CAC >100 (found in 30% of men and 29% of women) were 2.92 (95% CI 1.28-6.68) and 2.29 (0.99-5.30) for the lower and mid-tertiles of LTL vs. the upper tertile, respectively (Ptrend = 0.008). Findings were similar for CAC scores in the upper tertile (Ptrend = 0.006), and persisted after the exclusion of patients with diabetes or receiving statins. CONCLUSIONS: Shorter LTL was associated with a greater prevalence of asymptomatic coronary atherosclerosis in an urban Arab population-based sample. Mechanisms underlying this association should be sought.

CT features of intrapulmonary lymph nodes confirmed by cytology.

We retrospectively assessed the computed tomography features of intrapulmonary lymph nodes confirmed by cytology in 18 patients. The median size of the lymph nodes was 5.8 mm (range=3.3-8.5 mm). All were below the carina, and only one nodule, which was associated with an interlobar fissure, was over 20 mm from the chest wall. The nodules were oval, round, triangular, or trapezoidal; had sharply defined borders; were solid and homogenous; and were without calcification. Six nodules (33.3%) had a discrete thin tag extending to the pleura. Intrapulmonary lymph nodes can reliably be confirmed by fine needle aspiration with cytological diagnosis.

The effect of the cryosurgical cox-maze procedure on pulmonary veins diameter and left atrial size: computed tomography angiographic assessment.

OBJECTIVE: : The Cox-Maze procedure using cryoablation results in transmural lesions, which follow the lesion pattern of the cut-and-sew Cox-Maze procedure. The purpose of our study was to evaluate the effect of the Cox-Maze procedure on left atrial and pulmonary vein size using computed tomography angiogram (CTA). An additional aim was to evaluate pulmonary vein anatomic variability. METHODS: : Six patients (four women and two men; ages 39-63 years, mean age 54.3) underwent chest CTA 1 day before and 38 to 104 days (mean 62.6 days) after the cryosurgical Cox-Maze procedure. Measurements of pulmonary vein ostia and left atrial cranio-caudal, left-to-right and anterior-posterior diameters were derived by consensus. The change in diameters after therapy was compared using the Wilcoxon nonparametric test for paired measurements. Four patients (1 woman and 3 men; age 57-73 years; mean age 59) were evaluated with postoperative CTA alone 296-530 days (mean 447) after surgery, for the development of postoperative pulmonary vein stenosis. A single patient underwent preoperative CTA, but surgery was not performed. Pulmonary venous anatomy was recorded in all 11 patients. RESULTS: : Sinus rhythm was restored in all operated patients. No focal ostial stenosis of the pulmonary veins was observed. The quantitative assessment in the six patients with preoperative and postoperative studies disclosed only slight changes in pulmonary vein diameter with either reduction or dilatation of no more than 20% from baseline (P > 0.05). There was a consistent trend toward decrease in left atrial dimensions, which did not reach statistical significance. Six patients (55%) had standard pulmonary venous anatomy and five patients (45%) had at least one variation in their pulmonary vein anatomy. CONCLUSIONS: : In this study, we found that a very intensive cryoablation protocol around the pulmonary veins did not result in pulmonary vein stenosis. In addition, a relatively high incidence of anatomic variations of the pulmonary veins was documented.

Staging esophageal cancer.

Accurate staging of disease is necessary in patients with newly diagnosed esophageal cancer in order to prompt appropriate curative or palliative therapy. Computed tomography (CT) may be used to evaluate for local spread into adjacent structures (T4 disease) and to diagnose distant metastases (M1). Endoscopic ultrasonography (EUS) is the modality of choice for distinguishing T1 tumors from higher stage lesions and for detecting and sampling regional lymph nodes (N1 disease). Positron emission tomography (PET) scanning is most helpful for detecting previously occult distant metastases. Optimal staging generally requires a multimodality approach.

Positron emission tomography in interstitial lung disease.

BACKGROUND AND OBJECTIVES: A high rate of glycolysis may reflect the inflammatory activity of interstitial lung disease (ILD). This prospective study investigated whether PET can distinguish IPF, a primarily fibrotic process, from other entities of ILD that have a marked inflammatory component. METHODS: Twenty-one patients referred for surgical lung biopsy because of diffuse ILD underwent PET at the time of the lung biopsy. PET transmission scans were obtained after injecting (18)FDG intravenously. Regions of interest (ROI) were drawn on the lung images, and the standardized uptake value (SUV) was calculated for these ROI. RESULTS: Of the 21 patients studied, 14 had IPF, four had non-specific interstitial pneumonia, and the remaining three patients each had respiratory bronchiolitis-ILD, sarcoidosis and Langerhan's cell histiocytosis. There was no statistically significant difference in the SUV between IPF patients and non-IPF patients (P = 0.26), although patients with IPF tended to have higher SUV. Radiographic changes tended to be more prominent in the lung bases in patients with IPF compared with non-IPF patients; however, the median ratio of SUV measured in the upper fields to the whole lungs in IPF patients was not significantly different compared with the median ratio in non-IPF patients (P = 0.31). CONCLUSION: PET does not allow differentiation of IPF from a non-IPF diffuse interstitial pulmonary process.

Imaging of thymic disorders.

Evaluation of the thymus poses a challenge to the radiologist. In addition to age-related changes in thymic size, shape, and tissue composition, there is considerable variability in the normal adult thymic appearance within any age group. Many different types of disorders may affect the thymus, including hyperplasia, cysts, and benign and malignant neoplasms, both primary and secondary; clinical and imaging findings typical for each disease process are described in this article. Whereas computed tomography is the mainstay for imaging the thymus, other imaging modalities may occasionally provide additional structural or functional information.

Imaging of recurrent lung cancer.

Local, regional and distant tumor recurrence is common following surgical resection for non-small cell lung cancer. It is important to be familiar with the patterns of recurrence and to differentiate them from the normal post-operative appearance and post-radiation changes. The risks and types of recurrence are influenced by various factors including preoperative tumor stage, histological type and type of surgical resection. Treated patients are at risk for developing a second lung primary, reported to be 1-4% per year, and therefore follow-up must be aimed at detecting not only recurrent cancer, but also a new, primary lung cancer. Different follow-up imaging strategies have been suggested, including conventional radiography, CT and/or PET scanning.