Background-VDD pacing can enhance systolic function in patients with dilated cardiomyopathy and discoordinate contraction; however, identification of patients likely to benefit is unclear. We tested predictors of systolic responsiveness on the basis of global parameters as well as directly assessed mechanical dyssynchrony. Methods and Results-Twenty-two DCM patients with conduction delay were studied by cardiac catheterization with a dual-sensor micromanometer to measure LV and aortic pressures during sinus rhythm and LV free-wall pacing. Pacing enhanced isovolumetric (dP/dt max ) and ejection-phase (pulse pressure, PP) systolic function by 35Ϯ21% and 16.4Ϯ11%, respectively, and these changes correlated directly (rϭ0.7, Pϭ0.001). %⌬dP/dt max was weakly predicted by baseline QRS (rϭ0.6, PϽ0.02), more strongly by baseline dP/dt max (rϭ0.7, Pϭ0.001), and best by bidiscriminate analysis combining baseline dP/dt max Յ700 mm Hg/s and QRS Ն155 ms to predict %⌬dP/dt max Ն25% and %⌬PP Ն10% (PϽ0.0005, 2 ), with no false-positives. Benefit could not be predicted by %⌬QRS. To test whether basal mechanical dyssynchrony predicted responsiveness to LV pacing, circumferential strains were determined at Ϸ80 sites throughout the LV by tagged MRI in 8 DCM patients and 7 additional control subjects. Strain variance at time of maximal shortening indexed dyssynchrony, averaging 28.0Ϯ7.1% in normal subjects versus 201.4Ϯ84.3% in DCM patients (Pϭ0.001). Mechanical dyssynchrony also correlated directly with %⌬dP/dt max (rϭ0.85, Pϭ0.008). Conclusions-These results show that although mechanical dyssynchrony is a key predictor for pacing efficacy in DCM patients with conduction delay, combining information about QRS and basal dP/dt max provides an excellent tool to identify maximal responders.

Objective To compare myocardial blood flow (MBF) and myocardial flow reserve (MFR) estimates from 82Rb PET data using ten software packages (SPs): Carimas, Corridor4DM, FlowQuant, HOQUTO, ImagenQ, MunichHeart, PMOD, QPET, syngo MBF, and UW-QPP. Background It is unknown how MBF and MFR values from existing SPs agree for 82Rb PET. Methods Rest and stress 82Rb PET scans of 48 patients with suspected or known coronary artery disease (CAD) were analyzed in 10 centers. Each center used one of the 10 SPs to analyze global and regional MBF using the different kinetic models implemented. Values were considered to agree if they simultaneously had an intraclass correlation coefficient (ICC) > 0.75 and a difference < 20% of the median across all programs. Results The most common model evaluated was the one-tissue compartment model (1TCM) by Lortie et al. (2007). MBF values from seven of the eight software packages implementing this model agreed best (Carimas, Corridor4DM, FlowQuant, PMOD, QPET, syngoMBF, and UW-QPP). Values from two other models (El Fakhri et al. in Corridor4DM and Alessio et al. in UW-QPP) also agreed well, with occasional differences. The MBF results from other models (Sitek et al. 1TCM in Corridor4DM, Katoh et al. 1TCM in HOQUTO, Herrero et al. 2TCM in PMOD, Yoshida et al. retention in ImagenQ, and Lautamäki et al. retention in MunichHeart) were less in agreement with Lortie 1TCM values. Conclusions SPs using the same kinetic model, as described in Lortie et al. (2007), provided consistent results in measuring global and regional MBF values, suggesting they may be used interchangeably to process data acquired with a common imaging protocol.

BackgroundEstimation of the risk of malignancy in pulmonary nodules detected by CT is central in clinical management. The use of artificial intelligence (AI) offers an opportunity to improve risk prediction. Here we compare the performance of an AI algorithm, the lung cancer prediction convolutional neural network (LCP-CNN), with that of the Brock University model, recommended in UK guidelines.MethodsA dataset of incidentally detected pulmonary nodules measuring 5–15 mm was collected retrospectively from three UK hospitals for use in a validation study. Ground truth diagnosis for each nodule was based on histology (required for any cancer), resolution, stability or (for pulmonary lymph nodes only) expert opinion. There were 1397 nodules in 1187 patients, of which 234 nodules in 229 (19.3%) patients were cancer. Model discrimination and performance statistics at predefined score thresholds were compared between the Brock model and the LCP-CNN.ResultsThe area under the curve for LCP-CNN was 89.6% (95% CI 87.6 to 91.5), compared with 86.8% (95% CI 84.3 to 89.1) for the Brock model (p≤0.005). Using the LCP-CNN, we found that 24.5% of nodules scored below the lowest cancer nodule score, compared with 10.9% using the Brock score. Using the predefined thresholds, we found that the LCP-CNN gave one false negative (0.4% of cancers), whereas the Brock model gave six (2.5%), while specificity statistics were similar between the two models.ConclusionThe LCP-CNN score has better discrimination and allows a larger proportion of benign nodules to be identified without missing cancers than the Brock model. This has the potential to substantially reduce the proportion of surveillance CT scans required and thus save significant resources.

Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed. Objectives: To develop and validate a deep learning method to improve the management of IPNs. Methods: A Lung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions. Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were 83.5% (95% confidence interval [CI], 75.4–90.7%) and 91.9% (95% CI, 88.7–94.7%), compared with 78.1% (95% CI, 68.7–86.4%) and 81.9 (95% CI, 76.1–87.1%), respectively, for a commonly used clinical risk model for incidental nodules. Using 5% and 65% malignancy thresholds defining low- and high-risk categories, the overall net reclassifications in the validation cohorts for cancers and benign nodules compared with the Mayo model were 0.34 (Vanderbilt) and 0.30 (Oxford) as a rule-in test, and 0.33 (Vanderbilt) and 0.58 (Oxford) as a rule-out test. Compared with traditional risk prediction models, the Lung Cancer Prediction Convolutional Neural Network was associated with improved accuracy in predicting the likelihood of disease at each threshold of management and in our external validation cohorts. Conclusions: This study demonstrates that this deep learning algorithm can correctly reclassify IPNs into low- or high-risk categories in more than a third of cancers and benign nodules when compared with conventional risk models, potentially reducing the number of unnecessary invasive procedures and delays in diagnosis.

Routine quantification of myocardial blood flow (MBF) requires robust and reproducible processing of dynamic image series. The goal of this study was to evaluate the reproducibility of 3 highly automated software programs commonly used for absolute MBF and flow reserve (stress/rest MBF) assessment with 82 Rb PET imaging. Methods: Dynamic rest and stress 82 Rb PET scans were selected in 30 sequential patient studies performed at 3 separate institutions using 3 different 3-dimensional PET/CT scanners. All 90 scans were processed with 3 different MBF quantifi-cation programs, using the same 1-tissue-compartment model. Global (left ventricle) and regional (left anterior descending, left circumflex, and right coronary arteries) MBF and flow reserve were compared among programs using correlation and Bland-Altman analyses. Results: All scans were processed successfully by the 3 programs, with minimal operator interactions. Global and regional correlations of MBF and flow reserve all had an R 2 of at least 0.92. There was no significant difference in flow values at rest (P 5 0.68), stress (P 5 0.14), or reserve (P 5 0.35) among the 3 programs. Bland-Altman coefficients of reproducibility (1.96 · SD) averaged 0.26 for MBF and 0.29 for flow reserve differences among programs. Average pairwise differences were all less than 10%, indicating good reproducibility for MBF quantification. Global and regional SD from the line of perfect agreement averaged 0.15 and 0.17 mL/min/g, respectively, for MBF, compared with 0.22 and 0.26, respectively, for flow reserve. Conclusion: The 1-tissue-compartment model of 82 Rb tracer kinetics is a reproducible method for quantification of MBF and flow reserve with 3-dimensional PET/CT imaging. Absol ute quantification of myocardial blood flow (MBF) at stress and rest with dynamic PET imaging is an important tool for clinicians and provides information complementary to relative myocardial perfusion imaging (1-3). With standard list-mode acquisition and fast image reconstruction , dynamic, gated, and standard static perfusion images can be obtained with a single injection of the radiopharmaceutical and without additional imaging time. Automated image analysis tools are required for reliable and robust clinical use of dynamic data for MBF quantification (4). The performance of several such software programs for MBF quan-tification has been reported recently (5-9), each of which uses different tracers and methods of segmenting and sampling the left ventricular myocardium and blood-pool activity to obtain input curves. Although each of these tools greatly simplifies MBF quantification, uses the same tracer kinetic model for 82 Rb-rubidium (10), and has been validated individually , the effect of different model implementations has not been characterized. Previous studies have compared different tracer kinetic models and implementations for 13 N-ammonia (11,12) but not for 82 Rb-rubidium and in particular not for 3-dimensional (3D)-mode PET, which is the current standard technology. We aimed to comp...