Graph representation learning nowadays becomes fundamental in analyzing graphstructured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by leveraging a contrastive objective at the node level. Specifically, we generate two graph views by corruption and learn node representations by maximizing the agreement of node representations in these two views. To provide diverse node contexts for the contrastive objective, we propose a hybrid scheme for generating graph views on both structure and attribute levels. Besides, we provide theoretical justification behind our motivation from two perspectives, mutual information and the classical triplet loss. We perform empirical experiments on both transductive and inductive learning tasks using a variety of real-world datasets. Experimental experiments demonstrate that despite its simplicity, our proposed method consistently outperforms existing state-of-the-art methods by large margins. Notably, our method gains about 10% absolute improvements on protein function prediction. Our unsupervised method even surpasses its supervised counterparts on transductive tasks, demonstrating its great potential in real-world applications.Recently, graph representation learning using Graph Neural Networks (GNN) has received considerable attention. Along with its prosperous development, however, there is an increasing concern over the label availability when training the model. Nevertheless, existing GNN models are mostly established in a supervised manner [6][7][8], which require abundant labeled nodes for training. Albeit with some attempts connecting previous unsupervised objectives (i.e., matrix reconstruction) to GNN models [9, 10], these methods still heavily rely on the preset graph proximity matrix.
A model-based approach was used to integrate data from a phase II study in order to provide a quantitative rationale for selecting the apixaban dosage regimen for a phase III trial. The exposure-response models demonstrated that an increase in daily steady-state area under the plasma concentration-vs.-time curve (AUC(ss)) of 1 microg x h/ml would increase the odds ratio for major bleeding by 0.118 and decrease the odds ratio for venous thromboembolism (VTE) by 0.0499. The therapeutic utility index (TUI) was used to integrate the efficacy and safety predictions to quantify apixaban's efficacy/safety balance as a function of AUC(ss). Of the apixaban dosage regimens tested in phase II, the 2.5 mg twice-daily (b.i.d.) dosage regimen had the highest TUI (86.2%). This was also higher than the TUI for either 30 mg b.i.d. enoxaparin (82.5%) or for warfarin (71.8%). Subjects with moderate renal impairment are expected to have a 43% increase in apixaban exposure; however, apixaban's TUI suggests that dose adjustment is not needed in these subjects with renal impairment.
Purpose: In diffusion-weighted magnetic resonance imaging (DW-MRI), the fiber orientation distribution function (fODF) is of great importance for solving complex fiber configurations to achieve reliable tractography throughout the brain, which ultimately facilitates the understanding of brain connectivity and exploration of neurological dysfunction. Recently, multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD) method has been explored for reconstructing full fODFs. To achieve a reliable fitting, similar to other model-based approaches, a large number of diffusion measurements is typically required for MSMT-CSD method. The prolonged acquisition is, however, not feasible in practical clinical routine and is prone to motion artifacts. To accelerate the acquisition, we proposed a method to reconstruct the fODF from downsampled diffusion-weighted images (DWIs) by leveraging the strong inference ability of the deep convolutional neural network (CNN). Methods: The method treats spherical harmonics (SH)-represented DWI signals and fODF coefficients as inputs and outputs, respectively. To compensate for the reduced gradient directions with reduced number of DWIs in acquisition in each voxel, its surrounding voxels are incorporated by the network for exploiting their spatial continuity. The resulting fODF coefficients are fitted with applying the CNN in a multi-target regression model. The network is composed of two convolutional layers and three fully connected layers. To obtain an initial evaluation of the method, we quantitatively measured its performance on a simulated dataset. Then, for in vivo tests, we employed data from 24 subjects from the Human Connectome Project (HCP) as training set and six subjects as test set. The performance of the proposed method was primarily compared to the super-resolved MSMT-CSD with the decreasing number of DWIs. The fODFs reconstructed by MSMT-CSD from all available 288 DWIs were used as training labels and the reference standard. The performance was quantitatively measured by the angular correlation coefficient (ACC) and the mean angular error (MAE). Results: For the simulated dataset, the proposed method exhibited the potential advantage over the model reconstruction. For the in vivo dataset, it achieved superior results over the MSMT-CSD in all the investigated cases, with its advantage more obvious when a limited number of DWIs were used. As the number of DWIs was reduced from 95 to 25, the median ACC ranged from 0.96 to 0.91 for the CNN, but 0.93 to 0.77 for the MSMT-CSD (with perfect score of 1). The angular error in the typical regions of interest (ROIs) was also much lower, especially in multi-fiber regions. The average MAE for the CNN method in regions containing one, two, three fibers was, respectively, 1.09°, 2.75°, and 8.35°smaller than the MSMT-CSD method. The visual inception of the fODF further 3101 confirmed this superiority. Moreover, the tractography results validated the effectiveness of the learned fODF, in preserving known major branching fiber...
Carboxymethyl chitosan (CM-chitosan), which is a water-soluble derivative of chitosan, has attracted much attention as a new biomedical material. The safety study of this material was persuasive for its potential application. The present study was conducted to assess the tissue distribution, pharmacokinetics, biodegradation mechanism, and excretion of CM-chitosan in rats. After the rats were intraperitoneally injected at the dose of 50 mg/kg, the fluorescein isothiocyanate (FITC)-labeled CM-chitosan was absorbed rapidly and distributed to different organs, including liver, spleen, and kidney. The highest level of CM-chitosan was found in liver. It was at the level of 1.6 +/- 0.6 mg/liver and made up approximately 10-22% of the total injected FTC-CM-chitosan. Urinary excretion was the predominant way of excretion of FITC-labeled CM-chitosan, and 85% of the dose was excreted in urine over the period of 11 days. The molecular weights of body distributed FTC-CM-chitosan and urinary excreted FTC-CM-chitosan were analyzed by gel chromatography. The results indicated that the FTC-CM-chitosan was degraded in abdominal dropsy. The absorbed CM-chitosan forms were found with a relatively high molecular weight (approximately 300 kDa), whereas the molecular weight of the urinary excreted FTC-CM-chitosan was less than 45 kDa. In vitro research revealed that the CM-Chi was also degradable in plasma and homogenate of liver. The CM-chitosan with a molecular weight of approximately 800k was thoroughly degraded to a small molecule after it was incubated in homogenate of liver at 37 degrees C for 24 h. The results suggested that the liver plays a central role in biodegradation of CM-chitosan. The excellent biodegradability of CM-chitosan could potentially contribute to the clinical applications. The results also provide important clues for further modification of CM-chitosan as the postsurgical and other biomedical materials.
Diffusion kurtosis imaging (DKI) is an advanced diffusion imaging method that captures complex brain microstructural properties; however, it often has a lengthy acquisition time compared to conventional diffusion tensor imaging (DTI). Recently, a deep learning-based method has shown the potential for reducing the number of diffusion-weighted images (DWIs) required to compute the rotationally invariant scalar measures to twelve. In this study, we propose a three-dimensional (3D) convolutional neural network (CNN) to estimate the scalar measures. This network further improves the performance of the deep learning-based method with a largely reduced number of required DWIs. In our approach, all the DTI and DKI measures were estimated using a single network, and a hierarchical structure was introduced to customize the outputs based on their computational complexities and to learn the commonalities of the measures. Moreover, 3 × 3 × 3 convolution kernels were introduced to extract features from the 3D input patches and utilize the spatial context from adjacent neighborhoods, which also strengthened the network's robustness against noise. The proposed method was evaluated with two datasets. The results showed that, compared with the previous method that used an artificial neural network, our proposed hierarchical CNN provided enhanced efficiency for estimating all eight diffusion measures. It also improved the robustness against noise and retained the fine structures with only a few DWIs (as few as eight). This result suggests that it is possible to achieve kurtosis mapping in most clinical scanners within one minute, which could significantly extend the clinical utility of the DKI.
Cartographic generalization is a problem, which poses interesting challenges to automation. Whereas plenty of algorithms have been developed for the different sub-problems of generalization (e.g., simplification, displacement, aggregation), there are still cases, which are not generalized adequately or in a satisfactory way. The main problem is the interplay between different operators. In those cases the human operator is the benchmark, who is able to design an aesthetic and correct representation of the physical reality. Deep learning methods have shown tremendous success for interpretation problems for which algorithmic methods have deficits. A prominent example is the classification and interpretation of images, where deep learning approaches outperform traditional computer vision methods. In both domains-computer vision and cartography-humans are able to produce good solutions. A prerequisite for the application of deep learning is the availability of many representative training examples for the situation to be learned. As this is given in cartography (there are many existing map series), the idea in this paper is to employ deep convolutional neural networks (DCNNs) for cartographic generalizations tasks, especially for the task of building generalization. Three network architectures, namely U-net, residual U-net and generative adversarial network (GAN), are evaluated both quantitatively and qualitatively in this paper. They are compared based on their performance on this task at target map scales 1:10,000, 1:15,000 and 1:25,000, respectively. The results indicate that deep learning models can successfully learn cartographic generalization operations in one single model in an implicit way. The residual U-net outperforms the others and achieved the best generalization performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.