Search

Aims: Remote dielectric sensing (ReDS) enables quick estimation of lung fluid content. To examine if ReDS is superior to other methods in detecting acute heart failure. Methods and results: We included consecutive patients with dyspnoea from the emergency departments at Bispebjerg Hospital, Copenhagen, and performed ReDS, low-dose chest computed tomography (CT), echocardiogram, lung ultrasound, NT-Pro-brain natriuretic peptide (NT-proBNP), and a Boston score evaluation (chest X-ray and clinical signs). ReDS values >35% were used as a cut-off to diagnose pulmonary congestion. Acute heart failure was adjudicated by experts' review of health records but independently of ReDS values. Sub-analyses investigated ReDS in acute heart failure patients with congestion on CT. We included 97 patients within a median of 4.8 h from admittance: 25 patients (26%) were ReDS-positive and 39 (40%) had adjudicated acute heart failure (21 with and 18 without CT congestion). Heart failure patients had median ReDS 33%, left ventricular ejection fraction 48%, and NT-proBNP 2935 ng/L. A positive ReDS detected heart failure with 46% sensitivity, 88% specificity, and 71% accuracy. The AUC for ReDS was like the Boston score (P = 0.88) and the lung ultrasound score (P = 0.74). CT-congested heart failure patients had higher ReDS values than patients without heart failure (median 38 vs. 28%, P < 0.001). Heart failure patients without CT-congestion had ReDS values like patients without heart failure (mean 30 vs. 28%, P = 0.07). Conclusion: ReDS detects acute heart failure similarly to the Boston score and lung ultrasound score, and ReDS primarily identifies the acute heart failure patients who have congestion on a chest CT. Graphical Abstract [ABSTRACT FROM AUTHOR]

We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), for which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed for solid, subsolid, and large nodules. For each candidate, a set of 2-D patches from differently oriented planes is extracted. The proposed architecture comprises multiple streams of 2-D ConvNets, for which the outputs are combined using a dedicated fusion method to get the final classification. Data augmentation and dropout are applied to avoid overfitting. On 888 scans of the publicly available LIDC-IDRI dataset, our method reaches high detection sensitivities of 85.4% and 90.1% at 1 and 4 false positives per scan, respectively. An additional evaluation on independent datasets from the ANODE09 challenge and DLCST is performed. We showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system. [ABSTRACT FROM AUTHOR]

We present a fast and robust atlas-based algorithm for labeling airway trees, using geodesic distances in a geometric tree-space. Possible branch label configurations for an unlabeled airway tree are evaluated using distances to a training set of labeled airway trees. In tree-space, airway tree topology and geometry change continuously, giving a natural automatic handling of anatomical differences and noise. A hierarchical approach makes the algorithm efficient, assigning labels from the trachea and downwards. Only the airway centerline tree is used, which is relatively unaffected by pathology. The algorithm is evaluated on 80 segmented airway trees from 40 subjects at two time points, labeled by three medical experts each, testing accuracy, reproducibility and robustness in patients with chronic obstructive pulmonary disease (COPD). The accuracy of the algorithm is statistically similar to that of the experts and not significantly correlated with COPD severity. The reproducibility of the algorithm is significantly better than that of the experts, and negatively correlated with COPD severity. Evaluation of the algorithm on a longitudinal set of 8724 trees from a lung cancer screening trial shows that the algorithm can be used in large scale studies with high reproducibility, and that the negative correlation of reproducibility with COPD severity can be explained by missing branches, for instance due to segmentation problems in COPD patients. We conclude that the algorithm is robust to COPD severity given equally complete airway trees, and comparable in performance to that of experts in pulmonary medicine, emphasizing the suitability of the labeling algorithm for clinical use. [ABSTRACT FROM AUTHOR]

Objectives. It remains unknown whether non-electrocardiogram-gated coronary artery calcium (CAC) score in lung cancer screening provides incremental prognostic value. The aim of this study was to evaluate the prognostic value of CAC in the Danish Lung Cancer Screening Trial (DLCST), in addition to conducting a systematic review and meta-analysis including previously published studies regarding CAC in lung cancer screening. Design. In DLCST, we measured Agatston CAC scores in 1,945 current and former smokers. Causes of death were extracted from the Danish National Death Registry. We used Cox proportional hazards model to determine hazard ratios (HRs) of CAC scores. A weighted fixed-effects model was used for the meta-analysis. Results. Median follow-up in DLCST was 7.1 years, and 55% were men. Overall survival rates associated with CAC scores of 0, 1-400, and > 400 were 98%, 96%, and 92% ( p < 0.001), respectively. Adjusted HR of cardiovascular death associated with CAC >400 was 3.8 (1.0-15) ( p < 0.05). The meta-analysis included 28,045 asymptomatic participants. A high non-gated CAC score was associated with fatal or non-fatal cardiovascular events ( p < 0.0001). Conclusion. Assessment of non-electrocardiogram-gated CAC in lung cancer screening programs is a robust prognostic measure of fatal or non-fatal cardiovascular events in current and former smokers independent of traditional cardiovascular risk factors. [ABSTRACT FROM AUTHOR]