Search

Throughout its history the strategy and tactics of contextual behavioral science (CBS) research have had distinctive features as compared to traditional behavioral science approaches. Continued progress in CBS research can be facilitated by greater clarity about how its strategy and tactics can be brought to bear on current challenges. The present white paper is the result of a 2 1/2-year long process designed to foster consensus among representative producers and consumers of CBS research about the best strategic pathway forward. The Task Force agreed that CBS research should be multilevel, process-based, multidimensional, prosocial, and pragmatic, and provided 33 recommendations to the CBS community arranged across these characteristics. In effect, this report provides a detailed research agenda designed to maximize the impact of CBS as a field. Scientists and practitioners are encouraged to mount this ambitious agenda.

Differences in cardiac and aortic structure and function are associated with cardiovascular diseases and a wide range of other types of disease. Here we analyzed cardiovascular magnetic resonance images from a population-based study, the UK Biobank, using an automated machine-learning-based analysis pipeline. We report a comprehensive range of structural and functional phenotypes for the heart and aorta across 26,893 participants, and explore how these phenotypes vary according to sex, age and major cardiovascular risk factors. We extended this analysis with a phenome-wide association study, in which we tested for correlations of a wide range of non-imaging phenotypes of the participants with imaging phenotypes. We further explored the associations of imaging phenotypes with early-life factors, mental health and cognitive function using both observational analysis and Mendelian randomization. Our study illustrates how population-based cardiac and aortic imaging phenotypes can be used to better define cardiovascular disease risks as well as heart–brain health interactions, highlighting new opportunities for studying disease mechanisms and developing image-based biomarkers. © 2020, The Author(s), under exclusive licence to Springer Nature America, Inc.

Purpose: To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac magnetic resonance tagged images. Methods and Materials: In this retrospective cross-sectional study, 4508 cases from the UK Biobank were split randomly into 3244 training and 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of 1) a convolutional neural network (CNN) for localization, and 2) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis. Results: Within the test set, myocardial end-systolic circumferential Green strain errors were -0.001 +/- 0.025, -0.001 +/- 0.021, and 0.004 +/- 0.035 in basal, mid, and apical slices respectively (mean +/- std. dev. of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in diabetics, hypertensives, and participants with previous heart attack. Typical processing time was ~260 frames (~13 slices) per second on an NVIDIA Tesla K40 with 12GB RAM, compared with 6-8 minutes per slice for the manual analysis. Conclusions: The fully automated RNNCNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack., Comment: accepted in Radiology Cardiothoracic Imaging

Convolutional neural network (CNN) based segmentation methods provide an efficient and automated way for clinicians to assess the structure and function of the heart in cardiac MR images. While CNNs can generally perform the segmentation tasks with high accuracy when training and test images come from the same domain (e.g. same scanner or site), their performance often degrades dramatically on images from different scanners or clinical sites. We propose a simple yet effective way for improving the network generalization ability by carefully designing data normalization and augmentation strategies to accommodate common scenarios in multi-site, multi-scanner clinical imaging data sets. We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy. Specifically, the method was trained on a large set of 3,975 subjects from the UK Biobank. It was then directly tested on 600 different subjects from the UK Biobank for intra-domain testing and two other sets for cross-domain testing: the ACDC dataset (100 subjects, 1 site, 2 scanners) and the BSCMR-AS dataset (599 subjects, 6 sites, 9 scanners). The proposed method produces promising segmentation results on the UK Biobank test set which are comparable to previously reported values in the literature, while also performing well on cross-domain test sets, achieving a mean Dice metric of 0.90 for the left ventricle, 0.81 for the myocardium and 0.82 for the right ventricle on the ACDC dataset; and 0.89 for the left ventricle, 0.83 for the myocardium on the BSCMR-AS dataset. The proposed method offers a potential solution to improve CNN-based model generalizability for the cross-scanner and cross-site cardiac MR image segmentation task., Comment: 15 pages, 8 figures

We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 feature values characterizing both the cardiac shape and motion. Second, a feature selection is performed to remove highly correlated feature pairs. Third, clustering is carried out using a Gaussian mixture model on the selected features. After analysis, we identify two small clusters which probably correspond to two pathological categories. Further confirmation using a trained classification model and dimensionality reduction tools is carried out to support this discovery. Moreover, we examine the differences between the other large clusters and compare our measures with the ground-truth.

Background: The trend towards large-scale studies including population imaging poses new challenges in terms of quality control (QC). This is a particular issue when automatic processing tools, e.g. image segmentation methods, are employed to derive quantitative measures or biomarkers for later analyses. Manual inspection and visual QC of each segmentation isn't feasible at large scale. However, it's important to be able to automatically detect when a segmentation method fails so as to avoid inclusion of wrong measurements into subsequent analyses which could lead to incorrect conclusions. Methods: To overcome this challenge, we explore an approach for predicting segmentation quality based on Reverse Classification Accuracy, which enables us to discriminate between successful and failed segmentations on a per-cases basis. We validate this approach on a new, large-scale manually-annotated set of 4,800 cardiac magnetic resonance scans. We then apply our method to a large cohort of 7,250 cardiac MRI on which we have performed manual QC. Results: We report results used for predicting segmentation quality metrics including Dice Similarity Coefficient (DSC) and surface-distance measures. As initial validation, we present data for 400 scans demonstrating 99% accuracy for classifying low and high quality segmentations using predicted DSC scores. As further validation we show high correlation between real and predicted scores and 95% classification accuracy on 4,800 scans for which manual segmentations were available. We mimic real-world application of the method on 7,250 cardiac MRI where we show good agreement between predicted quality metrics and manual visual QC scores. Conclusions: We show that RCA has the potential for accurate and fully automatic segmentation QC on a per-case basis in the context of large-scale population imaging as in the UK Biobank Imaging Study., Comment: 14 pages, 7 figures, Journal of Cardiovascular Magnetic Resonance

Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy. However, occasionally even the best method fails due to low image quality, artifacts or unexpected behaviour of black box algorithms. Being able to predict segmentation quality in the absence of ground truth is of paramount importance in clinical practice, but also in large-scale studies to avoid the inclusion of invalid data in subsequent analysis. In this work, we propose two approaches of real-time automated quality control for cardiovascular MR segmentations using deep learning. First, we train a neural network on 12,880 samples to predict Dice Similarity Coefficients (DSC) on a per-case basis. We report a mean average error (MAE) of 0.03 on 1,610 test samples and 97% binary classification accuracy for separating low and high quality segmentations. Secondly, in the scenario where no manually annotated data is available, we train a network to predict DSC scores from estimated quality obtained via a reverse testing strategy. We report an MAE=0.14 and 91% binary classification accuracy for this case. Predictions are obtained in real-time which, when combined with real-time segmentation methods, enables instant feedback on whether an acquired scan is analysable while the patient is still in the scanner. This further enables new applications of optimising image acquisition towards best possible analysis results., Comment: Accepted at MICCAI 2018

A vast wealth of literature exists on the topic of rocket trajectory optimisation, particularly in the area of interplanetary trajectories due to its relevance today. Studies on optimising interstellar and intergalactic trajectories are usually performed in flat spacetime using an analytical approach, with very little focus on optimising interstellar trajectories in a general relativistic framework. This paper examines the use of low-acceleration rockets to reach galactic destinations in the least possible time, with a genetic algorithm being employed for the optimisation process. The fuel required for each journey was calculated for various types of propulsion systems to determine the viability of low-acceleration rockets to colonise the Milky Way. The results showed that to limit the amount of fuel carried on board, an antimatter propulsion system would likely be the minimum technological requirement to reach star systems tens of thousands of light years away. However, using a low-acceleration rocket would require several hundreds of thousands of years to reach these star systems, with minimal time dilation effects since maximum velocities only reached about 0.2c. Such transit times are clearly impractical, and thus, any kind of colonisation using low acceleration rockets would be difficult. High accelerations, on the order of 1g, are likely required to complete interstellar journeys within a reasonable time frame, though they may require prohibitively large amounts of fuel. So for now, it appears that humanity's ultimate goal of a galactic empire may only be possible at significantly higher accelerations, though the propulsion technology requirement for a journey that uses realistic amounts of fuel remains to be determined., Comment: 32 pages, 16 figures, Accepted for publication in Acta Astronautica

Cardiovascular magnetic resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images. Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV). By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance on par with human experts in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images., Comment: Accepted for publication by Journal of Cardiovascular Magnetic Resonance

by Choi Mo Fung Kenneth., Thesis (M.Phil.)--Chinese University of Hong Kong, 1998., Includes bibliographical references (leaves 105-112)., also in Chinese., Chapter 1 --- Introduction --- p.1, Chapter 1.1 --- Constraint Satisfaction Problems --- p.2, Chapter 1.2 --- Constraint Satisfaction Techniques --- p.2, Chapter 1.3 --- Motivation of the Research --- p.4, Chapter 1.4 --- Overview of the Thesis --- p.5, Chapter 2 --- Related Work --- p.7, Chapter 2.1 --- Min-conflicts Heuristic --- p.7, Chapter 2.2 --- GSAT --- p.8, Chapter 2.3 --- Breakout Method --- p.8, Chapter 2.4 --- GENET --- p.9, Chapter 2.5 --- E-GENET --- p.9, Chapter 2.6 --- DLM --- p.10, Chapter 2.7 --- Simulated Annealing --- p.11, Chapter 2.8 --- Genetic Algorithms --- p.12, Chapter 2.9 --- Tabu Search --- p.12, Chapter 2.10 --- Integer Programming --- p.13, Chapter 3 --- Background --- p.15, Chapter 3.1 --- GENET --- p.15, Chapter 3.1.1 --- Network Architecture --- p.15, Chapter 3.1.2 --- Convergence Procedure --- p.18, Chapter 3.2 --- Classical Optimization --- p.22, Chapter 3.2.1 --- Optimization Problems --- p.22, Chapter 3.2.2 --- The Lagrange Multiplier Method --- p.23, Chapter 3.2.3 --- Saddle Point of Lagrangian Function --- p.25, Chapter 4 --- Binary CSP's as Zero-One Integer Constrained Minimization Prob- lems --- p.27, Chapter 4.1 --- From CSP to SAT --- p.27, Chapter 4.2 --- From SAT to Zero-One Integer Constrained Minimization --- p.29, Chapter 5 --- A Continuous Lagrangian Approach for Solving Binary CSP's --- p.33, Chapter 5.1 --- From Integer Problems to Real Problems --- p.33, Chapter 5.2 --- The Lagrange Multiplier Method --- p.36, Chapter 5.3 --- Experiment --- p.37, Chapter 6 --- A Discrete Lagrangian Approach for Solving Binary CSP's --- p.39, Chapter 6.1 --- The Discrete Lagrange Multiplier Method --- p.39, Chapter 6.2 --- Parameters of CSVC --- p.43, Chapter 6.2.1 --- Objective Function --- p.43, Chapter 6.2.2 --- Discrete Gradient Operator --- p.44, Chapter 6.2.3 --- Integer Variables Initialization --- p.45, Chapter 6.2.4 --- Lagrange Multipliers Initialization --- p.46, Chapter 6.2.5 --- Condition for Updating Lagrange Multipliers --- p.46, Chapter 6.3 --- A Lagrangian Reconstruction of GENET --- p.46, Chapter 6.4 --- Experiments --- p.52, Chapter 6.4.1 --- Evaluation of LSDL(genet) --- p.53, Chapter 6.4.2 --- Evaluation of Various Parameters --- p.55, Chapter 6.4.3 --- Evaluation of LSDL(max) --- p.63, Chapter 6.5 --- Extension of LSDL --- p.66, Chapter 6.5.1 --- Arc Consistency --- p.66, Chapter 6.5.2 --- Lazy Arc Consistency --- p.67, Chapter 6.5.3 --- Experiments --- p.70, Chapter 7 --- Extending LSDL for General CSP's: Initial Results --- p.77, Chapter 7.1 --- General CSP's as Integer Constrained Minimization Problems --- p.77, Chapter 7.1.1 --- Formulation --- p.78, Chapter 7.1.2 --- Incompatibility Functions --- p.79, Chapter 7.2 --- The Discrete Lagrange Multiplier Method --- p.84, Chapter 7.3 --- A Comparison between the Binary and the General Formulation --- p.85, Chapter 7.4 --- Experiments --- p.87, Chapter 7.4.1 --- The N-queens Problems --- p.89, Chapter 7.4.2 --- The Graph-coloring Problems --- p.91, Chapter 7.4.3 --- The Car-Sequencing Problems --- p.92, Chapter 7.5 --- Inadequacy of the Formulation --- p.94, Chapter 7.5.1 --- Insufficiency of the Incompatibility Functions --- p.94, Chapter 7.5.2 --- Dynamic Illegal Constraint --- p.96, Chapter 7.5.3 --- Experiments --- p.97, Chapter 8 --- Concluding Remarks --- p.100, Chapter 8.1 --- Contributions --- p.100, Chapter 8.2 --- Discussions --- p.102, Chapter 8.3 --- Future Work --- p.103, Bibliography --- p.105, http://library.cuhk.edu.hk/record=b5889537, Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)