Embedding high-dimensional data onto a low-dimensional manifold is of both theoretical and practical value. In this article, we propose to combine deep neural networks (DNN) with mathematics-guided... Show moreEmbedding high-dimensional data onto a low-dimensional manifold is of both theoretical and practical value. In this article, we propose to combine deep neural networks (DNN) with mathematics-guided embedding rules for high-dimensional data embedding. We introduce a generic deep embedding network (DEN) framework, which is able to learn a parametric mapping from high-dimensional space to low-dimensional space, guided by well-established objectives such as Kullback-Leibler (KL) divergence minimization. We further propose a recursive strategy, called deep recursive embedding (DRE), to make use of the latent data representations for boosted embedding performance. We exemplify the flexibility of DRE by different architectures and loss functions, and benchmarked our method against the two most popular embedding methods, namely, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP). The proposed DRE method can map out-of-sample data and scale to extremely large datasets. Experiments on a range of public datasets demonstrated improved embedding performance in terms of local and global structure preservation, compared with other state-of-the-art embedding methods. Code is available at https://github.com/tao-aimi/DeepRecursiveEmbedding. Show less
Background: Although antibiotic treatment is recommended for acute exacerbations of chronic obstructive pulmonary disease (AECOPD), its value in real-world settings is still controversial.... Show moreBackground: Although antibiotic treatment is recommended for acute exacerbations of chronic obstructive pulmonary disease (AECOPD), its value in real-world settings is still controversial. Objectives: This study aimed to evaluate the short- and long-term effects of antibiotic treatment on AECOPD outpatients. Methods: A cohort study was conducted under the PharmLines Initiative. We included participants with a first recorded diagnosis of COPD who received systemic glucocorticoid treatment for an AECOPD episode. The exposed and reference groups were defined based on any antibiotic prescription during the AECOPD treatment. The short-term outcome was AECOPD treatment failure within 14-30 days after the index date. The long-term outcome was time to the next exacerbation. Adjustment for confounding was made using propensity scores. Results: Of the 1,105 AECOPD patients, antibiotics were prescribed to 518 patients (46.9%) while 587 patients (53.1%) received no antibiotics. The overall antibiotic use was associated with a relative risk reduction of AECOPD treatment failure by 37% compared with the reference group (adjusted odds ratio [aOR] 0.63 [95% CI: 0.40-0.99]). Protective effects were similar for doxycycline, macrolides, and co-amoxiclav, although only the effect of doxycycline was statistically significant (aOR 0.53 [95% CI: 0.28-0.99]). No protective effect was seen for amoxicillin (aOR 1.49 [95% CI: 0.78-2.84]). The risk of and time to the next exacerbation was similar for both groups. Conclusion: Overall, antibiotic treatment, notably with doxycycline, supplementing systemic glucocorticoids reduces short-term AECOPD treatment failure in real-world outpatient settings. No long-term beneficial effects of antibiotic treatment on AECOPD were found for the prevention of subsequent exacerbations. Show less
Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation... Show moreSegmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community. (C) 2020 Elsevier B.V. All rights reserved. Show less
Purpose Cardiac motion tracking enables quantitative evaluation of myocardial strain, which is clinically interesting in cardiovascular disease research. However, motion tracking is difficult to... Show morePurpose Cardiac motion tracking enables quantitative evaluation of myocardial strain, which is clinically interesting in cardiovascular disease research. However, motion tracking is difficult to perform manually. In this paper, we aim to develop and compare two fully automated motion tracking methods for the steady state free precession (SSFP) cine magnetic resonance imaging (MRI), and explore their use in real clinical scenario with different patient groups. Methods We proposed two automated cardiac motion tracking method: (a) a traditional registration-based method, named full cardiac cycle registration, which simultaneously tracks all cine frames within a full cardiac cycle by joint registration of all frames; and (b) a modern convolutional neural network (CNN)-based method, named Groupwise MotionNet, which enhances the temporal coherence by fusing motion along a continuous time scale. Both methods were evaluated on the healthy volunteer data from the MICCAI 2011 STACOM Challenge, as well as on patient data including hypertrophic cardiomyopathy (HCM) and myocardial infarction (MI). Results The full cardiac cycle registration method achieved an average end-point error (EPE) 2.89 +/- 1.57 mm for cardiac motion tracking, with computation time of around 9 min per short-axis cine MRI (size 128 x 128, 30 cardiac phases). In comparison, the Groupwise MotionNet achieved an average EPE of 0.94 +/- 1.59 mm, taking < 1 s for a full cardiac phases. Further experiments showed that registration method had stable performance, independent of patient cohort and MRI machine, while the CNN-based method relied on the training data to deliver consistently accurate results. Conclusion Both registration-based and CNN-based method can track the cardiac motion from SSFP cine MRI in a fully automated manner, while taking temporal coherence into account. The registration method is generic, robust, but relatively slow; the CNN-based method trained with heterogeneous data was able to achieve high tracking accuracy with real-time performance. Show less
Supervised convolutional neural networks (CNNs) have demonstrated state-of-art performance in medical image segmentation tasks. However, the performance of a well-trained CNN on an independent... Show moreSupervised convolutional neural networks (CNNs) have demonstrated state-of-art performance in medical image segmentation tasks. However, the performance of a well-trained CNN on an independent dataset (e.g., different vendors, sequences) relies strongly on the distribution similarity, and may drop unexpectedly in case of distribution shift. To obtain a large amount of annotation from each new dataset for re-training the CNN is expensive and impractical. Adaptation algorithms to improve the CNN generaliza bility from source domain to target domain has significant practical value. In this work, we propose a highly efficient end-to-end domain adaptation approach, with left ventricle segmentation from cine MRI sequences as an example. We propose to perform domain adaptation in the output space where different domains share the strongest similarities. The core of this algorithm is a flexible and light output adaption module based on adversarial learning. Moreover, Canny edge detector is introduced to enhance model's attention to edges during adversarial learning. Comparative experiments were carried out using images from three major MR vendors (Philips, Siemens, and GE) as three domains. Our results demonstrated that the proposed method substantially improved the generalization of the trained CNN model from one vendor to other vendors without any additional annotation. Moreover, the ablation study proved that introducing Canny edge detector further refined the edge detection in segmentation. The proposed adaption is generic can be extended to other medical image segmentation problems. Show less