Explore the vast range of titles available.

ObjectivesTo evaluate the performance of an AI-powered algorithm for the automatic detection of pulmonary embolism (PE) on chest computed tomography pulmonary angiograms (CTPAs) on a large dataset.MethodsWe retrospectively identified all CTPAs conducted at our institution in 2017 (n = 1499). Exams with clinical questions other than PE were excluded from the analysis (n = 34). The remaining exams were classified into positive (n = 232) and negative (n = 1233) for PE based on the final written reports, which defined the reference standard. The fully anonymized 1-mm series in soft tissue reconstruction served as input for the PE detection prototype algorithm that was based on a deep convolutional neural network comprising a Resnet architecture. It was trained and validated on 28,000 CTPAs acquired at other institutions. The result series were reviewed using a web-based feedback platform. Measures of diagnostic performance were calculated on a per patient and a per finding level.ResultsThe algorithm correctly identified 215 of 232 exams positive for pulmonary embolism (sensitivity 92.7%; 95% confidence interval [CI] 88.3–95.5%) and 1178 of 1233 exams negative for pulmonary embolism (specificity 95.5%; 95% CI 94.2–96.6%). On a per finding level, 1174 of 1352 findings marked as embolus by the algorithm were true emboli. Most of the false positive findings were due to contrast agent–related flow artifacts, pulmonary veins, and lymph nodes.ConclusionThe AI prototype algorithm we tested has a high degree of diagnostic accuracy for the detection of PE on CTPAs. Sensitivity and specificity are balanced, which is a prerequisite for its clinical usefulness.Key Points• An AI-based prototype algorithm showed a high degree of diagnostic accuracy for the detection of pulmonary embolism on CTPAs.• It can therefore help clinicians to automatically prioritize exams with a high suspection of pulmonary embolism and serve as secondary reading tool.• By complementing traditional ways of worklist prioritization in radiology departments, this can speed up the diagnostic and therapeutic workup of patients with pulmonary embolism and help to avoid false negative calls.

Transcatheter aortic valve replacement (TAVR) is a minimally invasive alternative to conventional aortic valve replacement in symptomatic patients with severe aortic stenosis and contraindications to surgery. The procedure has shown to improve patient’s quality of life and prolong short- and mid-term survival in high-risk individuals, becoming a widely accepted therapeutic option which has been integrated into current clinical guidelines for the management of valvular heart disease. Nevertheless, not every patient at high-risk for surgery is a good candidate for TAVR. Besides clinical selection, which is usually established by the Heart Team, certain technical and anatomic criteria must be met as, unlike in surgical valve replacement, annular sizing is not performed under direct surgical evaluation but on the basis of non-invasive imaging findings. Present consensus document was outlined by a working group of researchers from the European Society of Cardiovascular Radiology (ESCR) and aims to provide guidance on the utilisation of CT and MR imaging prior to TAVR. Particular relevance is given to the technical requirements and standardisation of the scanning protocols which have to be tailored to the remarkable variability of the scanners currently utilised in clinical practice; recommendations regarding all required pre-procedural measurements and medical reporting standardisation have been also outlined, in order to ensure quality and consistency of reported data and terminology.Key Points• To provide a reference document for CT and MR acquisition techniques, taking into account the significant technological variation of available scanners.• To review all relevant measurements that are required and define a step-by-step guided approach for the measurements of different structures implicated in the procedure.• To propose a CT/MR reporting template to assist in consistent communication between various sites and specialists involved in the procedural planning.

To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

With mounting data on its accuracy and prognostic value, cardiovascular magnetic resonance (CMR) is becoming an increasingly important diagnostic tool with growing utility in clinical routine. Given its versatility and wide range of quantitative parameters, however, agreement on specific standards for the interpretation and post-processing of CMR studies is required to ensure consistent quality and reproducibility of CMR reports. This document addresses this need by providing consensus recommendations developed by the Task Force for Post Processing of the Society for Cardiovascular MR (SCMR). The aim of the task force is to recommend requirements and standards for image interpretation and post processing enabling qualitative and quantitative evaluation of CMR images. Furthermore, pitfalls of CMR image analysis are discussed where appropriate.

In systemic lupus erythematosus (SLE), cardiac manifestations, e.g. coronary artery disease (CAD) and myocarditis are leading causes of morbidity and mortality. The prevalence of subclinical heart disease in SLE is unknown. We studied whether a comprehensive cardiovascular magnetic resonance (CMR) protocol may be useful for early diagnosis of heart disease in SLE patients without known CAD. In this prospective, observational, cross-sectional study CMR including cine, late gadolinium enhancement (LGE) and stress perfusion sequences, ECG, and blood sampling were performed in 30 consecutive SLE patients without known CAD. All patients fulfilled at least 4/11 American College of Rheumatology (ACR) Criteria for the classification of SLE. 30 patients (83% female) were enrolled, mean age was 45±14 years and mean SLE disease duration was 10±8 years. 80% had low to moderate disease activity. All had a low SLE damage index. CMR was abnormal in 13/30 (43%), showing LGE in 9/13, stress perfusion deficits in 5/13 and pericardial effusion (PE) in 7/13. Patients with non-ischemic LGE had more often microalbuminuria while patients with stress perfusion deficits a history of hypertension, renal disorder as ACR criterion, repolarisation abnormalities on ECG and larger LV enddiastolic volume index. There was no correlation between clinical symptoms and CMR results. Our study shows that cardiac involvement as observed by CMR is frequent in SLE and not necessarily associated with typical symptoms. CMR may thus help to detect subclinical cardiac involvement, which could lead to earlier treatment. Additionally we identify possible risk factors associated with cardiac involvement.

The severe acute respiratory syndrome coronavirus 2019 (SARS-CoV-2) pandemic currently constitutes a significant burden on worldwide health care systems, with important implications on many levels, including radiology departments. Given the established fundamental role of cardiovascular imaging in modern healthcare, and the specific value of cardiopulmonary radiology in COVID-19 patients, departmental organisation and imaging programs need to be restructured during the pandemic in order to provide access to modern cardiovascular services to both infected and non-infected patients while ensuring safety for healthcare professionals. The uninterrupted availability of cardiovascular radiology services remains, particularly during the current pandemic outbreak, crucial for the initial evaluation and further follow-up of patients with suspected or known cardiovascular diseases in order to avoid unnecessary complications. Suspected or established COVID-19 patients may also have concomitant cardiovascular symptoms and require further imaging investigations. This statement by the European Society of Cardiovascular Radiology (ESCR) provides information on measures for safety of healthcare professionals and recommendations for cardiovascular imaging during the pandemic in both non-infected and COVID-19 patients.

Machine learning offers great opportunities to streamline and improve clinical care from the perspective of cardiac imagers, patients, and the industry and is a very active scientific research field. In light of these advances, the European Society of Cardiovascular Radiology (ESCR), a non-profit medical society dedicated to advancing cardiovascular radiology, has assembled a position statement regarding the use of machine learning (ML) in cardiovascular imaging. The purpose of this statement is to provide guidance on requirements for successful development and implementation of ML applications in cardiovascular imaging. In particular, recommendations on how to adequately design ML studies and how to report and interpret their results are provided. Finally, we identify opportunities and challenges ahead. While the focus of this position statement is ML development in cardiovascular imaging, most considerations are relevant to ML in radiology in general. Key Points • Development and clinical implementation of machine learning in cardiovascular imaging is a multidisciplinary pursuit. • Based on existing study quality standard frameworks such as SPIRIT and STARD, we propose a list of quality criteria for ML studies in radiology. • The cardiovascular imaging research community should strive for the compilation of multicenter datasets for the development, evaluation, and benchmarking of ML algorithms.

Atrial fibrillation (AF) has been linked to left atrial (LA) enlargement. Whereas most studies focused on 2D-based estimation of static LA volume (LAV), we used a fully-automatic convolutional neural network (CNN) for time-resolved (CINE) volumetry of the whole LA on cardiac MRI (cMRI). Aim was to investigate associations between functional parameters from fully-automated, 3D-based analysis of the LA and current classification schemes in AF. We retrospectively analyzed consecutive AF patients who underwent cMRI on 1.5T systems including a stack of oblique-axial CINE series covering the whole LA. The LA was automatically segmented by a validated CNN. In the resulting volume-time curves, maximum, minimum and LAV before atrial contraction were automatically identified. Active, passive and total LA emptying fractions (LAEF) were calculated and compared to clinical classifications (AF Burden score (AFBS), increased stroke risk (CHA.sub.2 DS.sub.2 VASc[greater than or equal to]2), AF type (paroxysmal/persistent), EHRA score, and AF risk factors). Moreover, multivariable linear regression models (mLRM) were used to identify associations with AF risk factors. Overall, 102 patients (age 61±9 years, 17% female) were analyzed. Active LAEF (LAEF_active) decreased significantly with an increase of AFBS (minimal: 44.0%, mild: 36.2%, moderate: 31.7%, severe: 20.8%, p<0.003) which was primarily caused by an increase of minimum LAV. Likewise, LAEF_active was lower in patients with increased stroke risk (30.7% vs. 38.9%, p = 0.002). AF type and EHRA score did not show significant differences between groups. In mLRM, a decrease of LAEF_active was associated with higher age (per year: -0.3%, p = 0.02), higher AFBS (per category: -4.2%, p<0.03) and heart failure (-12.1%, p<0.04). Fully-automatic morphometry of the whole LA derived from cMRI showed significant relationships between LAEF_active with increased stroke risk and severity of AFBS. Furthermore, higher age, higher AFBS and presence of heart failure were independent predictors of reduced LAEF_active, indicating its potential usefulness as an imaging biomarker.

Background Transbronchial cryobiopsy in the evaluation of patients with interstitial lung diseases (ILD) is expected to reduce the need for surgical lung biopsy (SLB). Objective To evaluate the diagnostic value of cryobiopsy in combination with bronchoalveolar lavage (BAL), radiologic and clinical data in patients with ILD. Methods Between 08/15 and 01/20 patients with ILD underwent cryobiopsy if they: did not have (i) an usual interstitial pneumonia (UIP)-pattern on CT, (ii) predominant ground-glass opacities suggesting alveolitis, (iii) findings suggestive of sarcoidosis on CT, or if they had (i) a CT showing UIP-pattern, but had findings suggesting alternative diagnosis than idiopathic pulmonary fibrosis (IPF), or (ii) had previous non-diagnostic conventional transbronchial forceps biopsy. Histological findings were integrated into the multidisciplinary team discussion (MDTD) and a diagnostic consensus was sought. Results One hundred patients underwent cryobiopsy. In 88/100 patients, cryobiopsy was representative with diagnostic findings in 45/88 and non-specific histological findings in 43/88 patients. In 25/43 with non-specific findings, a consensus diagnosis was reached after MDTD integrating BAL, radiologic and clinical data; eight of the remaining 18 patients with non-specific findings were referred to SLB. In 12/100 patients cryobiopsy was not representative and three of these patients were also referred to SLB. In 7/11 patients (64%) SLB was diagnostic. Complications of cryobiopsy included pneumothorax (14%) and locally controlled bleeding (24%). Conclusions The diagnostic yield of cryobiopsy was 70%:45% of cryobiopsies were diagnostic based on histology alone and an additional 25% provided non-specific, but valuable findings allowing a consensus diagnosis after MDTD. Our data demonstrate that the diagnostic value of cryobiopsy is high if combined with BAL, radiologic and clinical data.