scholarly journals VTG-Net: A CNN Based Vessel Topology Graph Network for Retinal Artery/Vein Classification

2021 ◽  
Vol 8 ◽  
Author(s):  
Suraj Mishra ◽  
Ya Xing Wang ◽  
Chuan Chuan Wei ◽  
Danny Z. Chen ◽  
X. Sharon Hu
Keyword(s):  
High Performance ◽  
Retinal Vessel ◽  
Graph Representation ◽  
Convolutional Network ◽  
Image Domain ◽  
Topological Features ◽  
Retinal Artery ◽  
Topology Information ◽  
Hierarchical Features ◽  
Topology Graph

From diagnosing cardiovascular diseases to analyzing the progression of diabetic retinopathy, accurate retinal artery/vein (A/V) classification is critical. Promising approaches for A/V classification, ranging from conventional graph based methods to recent convolutional neural network (CNN) based models, have been known. However, the inability of traditional graph based methods to utilize deep hierarchical features extracted by CNNs and the limitations of current CNN based methods to incorporate vessel topology information hinder their effectiveness. In this paper, we propose a new CNN based framework, VTG-Net (vessel topology graph network), for retinal A/V classification by incorporating vessel topology information. VTG-Net exploits retinal vessel topology along with CNN features to improve A/V classification accuracy. Specifically, we transform vessel features extracted by CNN in the image domain into a graph representation preserving the vessel topology. Then by exploiting a graph convolutional network (GCN), we enable our model to learn both CNN features and vessel topological features simultaneously. The final predication is attained by fusing the CNN and GCN outputs. Using a publicly available AV-DRIVE dataset and an in-house dataset, we verify the high performance of our VTG-Net for retinal A/V classification over state-of-the-art methods (with ~2% improvement in accuracy on the AV-DRIVE dataset).

scholarly journals A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2111
Author(s):  
Bo-Wei Zhao ◽  
Zhu-Hong You ◽  
Lun Hu ◽  
Zhen-Hao Guo ◽  
Lei Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Computational Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Representation Learning ◽  
Graph Representation ◽  
Convolutional Network ◽  
Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

Indocyanine green angiography imaging findings in artery occlusions

2021 ◽  
pp. 112067212110378
Author(s):  
Ramesh Venkatesh ◽  
Nikitha Gurram Reddy ◽  
Vishma Prabhu ◽  
Pukhraj Rishi ◽  
Arpitha Pereira ◽  
...  
Keyword(s):  
Indocyanine Green ◽  
Multimodal Imaging ◽  
Indocyanine Green Angiography ◽  
Retinal Vessel ◽  
Retinal Artery Occlusion ◽  
Artery Occlusion ◽  
Imaging Features ◽  
Retinal Artery ◽  
Choroidal Perfusion ◽  
Rouleaux Formation

Purpose: To describe the multimodal imaging features including indocyanine green angiography (ICGA) in cases diagnosed clinically as central retinal artery occlusion (CRAO) at its different disease stages. Methods: In this retrospective observational study, patients diagnosed clinically as CRAO or hemi-CRAO were included. All patients underwent multimodal imaging with optical coherence tomography (OCT), fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA) were studied. Analysis of ICGA images in different stages of artery occlusions and its correlation with accompanying FFA and OCT images was done. Results: Eight such studies in five patients were available for analysis. The most important observation noted on ICGA was the presence of hypercyanescent spots seen during the acute stages of the disease in four of the five cases. The spots were accompanied by retinal vessel staining on FFA in the corresponding region. As the disease showed signs of resolution, the hypercyanescent spots on ICGA and retinal vessel staining on FFA disappeared. The hypercyanescent spots seen on the ICGA were noted due to the red blood cell aggregation or ‘rouleaux’ formation. In addition, choroidal perfusion abnormalities were noted on ICGA in all five cases in the acute stage. Conclusion: Choroidal perfusion changes can be identified in acute phase of retinal artery occlusion. Rouleaux formation in the retinal circulation occurs due to the slowing of the blood flow following artery occlusion. These are seen as hypercyanescent spots in the late phase on ICGA.

scholarly journals Multi-Label Patent Categorization with Non-Local Attention-Based Graph Convolutional Network

2020 ◽  
Vol 34 (05) ◽  
pp. 9024-9031
Author(s):  
Pingjie Tang ◽  
Meng Jiang ◽  
Bryan (Ning) Xia ◽  
Jed W. Pitera ◽  
Jeffrey Welser ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
High Performance ◽  
State Of The Art ◽  
Convolutional Network ◽  
Attention Model ◽  
Patent Classification ◽  
International Patent ◽  
Non Local ◽  
Text Content ◽  
Document Representations

Patent categorization, which is to assign multiple International Patent Classification (IPC) codes to a patent document, relies heavily on expert efforts, as it requires substantial domain knowledge. When formulated as a multi-label text classification (MTC) problem, it draws two challenges to existing models: one is to learn effective document representations from text content; the other is to model the cross-section behavior of label set. In this work, we propose a label attention model based on graph convolutional network. It jointly learns the document-word associations and word-word co-occurrences to generate rich semantic embeddings of documents. It employs a non-local attention mechanism to learn label representations in the same space of document representations for multi-label classification. On a large CIRCA patent database, we evaluate the performance of our model and as many as seven competitive baselines. We find that our model outperforms all those prior state of the art by a large margin and achieves high performance on P@k and nDCG@k.

scholarly journals Relative depth estimation from single monocular images with deep convolutional network

2017 ◽  
Author(s):  
◽  
Alex Yang
Keyword(s):  
High Performance ◽  
Depth Estimation ◽  
Fine Tuning ◽  
Test Accuracy ◽  
Relative Depth ◽  
Optimized Design ◽  
Convolutional Network ◽  
Real Time Processing ◽  
Deep Convolutional Network ◽  
Depth Inference

Depth estimation from single monocular images is a theoretical challenge in computer vision as well as a computational challenge in practice. This thesis addresses the problem of depth estimation from single monocular images using a deep convolutional neural fields framework; which consists of convolutional feature extraction, superpixel dimensionality reduction, and depth inference. Data were collected using a stereo vision camera, which generated depth maps though triangulation that are paired with visual images. The visual image (input) and computed depth map (desired output) are used to train the model, which has achieved 83 percent test accuracy at the standard 25 percent tolerance. The problem has been formulated as depth regression for superpixels and our technique is superior to existing state-of-the-art approaches based on its demonstrated its generalization ability, high prediction accuracy, and real-time processing capability. We utilize the VGG-16 deep convolutional network as feature extractor and conditional random fields depth inference. We have leveraged a multi-phase training protocol that includes transfer learning and network fine-tuning lead to high performance accuracy. Our framework has a robust modular nature with capability of replacing each component with different implementations for maximum extensibility. Additionally, our GPU-accelerated implementation of superpixel pooling has further facilitated this extensibility by allowing incorporation of feature tensors with exible shapes and has provided both space and time optimization. Based on our novel contributions and high-performance computing methodologies, the model achieves a minimal and optimized design. It is capable of operating at 30 fps; which is a critical step towards empowering real-world applications such as autonomous vehicle with passive relative depth perception using single camera vision-based obstacle avoidance, environment mapping, etc.

scholarly journals An effective drug-disease associations prediction model based on graphic representation learning over multi-biomolecular network

2022 ◽  
Vol 23 (1) ◽  
Author(s):  
Hanjing Jiang ◽  
Yabing Huang
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Representation Learning ◽  
Biological Data ◽  
Graph Representation ◽  
Data Set ◽  
Validation Experiment ◽  
Biomolecular Network ◽  
Disease Associations ◽  
Drug Reposition

Abstract Background Drug-disease associations (DDAs) can provide important information for exploring the potential efficacy of drugs. However, up to now, there are still few DDAs verified by experiments. Previous evidence indicates that the combination of information would be conducive to the discovery of new DDAs. How to integrate different biological data sources and identify the most effective drugs for a certain disease based on drug-disease coupled mechanisms is still a challenging problem. Results In this paper, we proposed a novel computation model for DDA predictions based on graph representation learning over multi-biomolecular network (GRLMN). More specifically, we firstly constructed a large-scale molecular association network (MAN) by integrating the associations among drugs, diseases, proteins, miRNAs, and lncRNAs. Then, a graph embedding model was used to learn vector representations for all drugs and diseases in MAN. Finally, the combined features were fed to a random forest (RF) model to predict new DDAs. The proposed model was evaluated on the SCMFDD-S data set using five-fold cross-validation. Experiment results showed that GRLMN model was very accurate with the area under the ROC curve (AUC) of 87.9%, which outperformed all previous works in terms of both accuracy and AUC in benchmark dataset. To further verify the high performance of GRLMN, we carried out two case studies for two common diseases. As a result, in the ranking of drugs that were predicted to be related to certain diseases (such as kidney disease and fever), 15 of the top 20 drugs have been experimentally confirmed. Conclusions The experimental results show that our model has good performance in the prediction of DDA. GRLMN is an effective prioritization tool for screening the reliable DDAs for follow-up studies concerning their participation in drug reposition.

DeepAtomicCharge: a new graph convolutional network-based architecture for accurate prediction of atomic charges

2020 ◽  
Author(s):  
Jike Wang ◽  
Dongsheng Cao ◽  
Cunchen Tang ◽  
Lei Xu ◽  
Qiaojun He ◽  
...  
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Atomic Charge ◽  
High Accuracy ◽  
Substantial Improvement ◽  
Molecular Properties ◽  
Atomic Charges ◽  
Convolutional Network ◽  
Structure Based Drug Design ◽  
Molecular Fingerprints

Abstract Atomic charges play a very important role in drug-target recognition. However, computation of atomic charges with high-level quantum mechanics (QM) calculations is very time-consuming. A number of machine learning (ML)-based atomic charge prediction methods have been proposed to speed up the calculation of high-accuracy atomic charges in recent years. However, most of them used a set of predefined molecular properties, such as molecular fingerprints, for model construction, which is knowledge-dependent and may lead to biased predictions due to the representation preference of different molecular properties used for training. To solve the problem, we present a new architecture based on graph convolutional network (GCN) and develop a high-accuracy atomic charge prediction model named DeepAtomicCharge. The new GCN architecture is designed with only the atomic properties and the connection information between the atoms in molecules and can dynamically learn and convert molecules into appropriate atomic features without any prior knowledge of the molecules. Using the designed GCN architecture, substantial improvement is achieved for the prediction accuracy of atomic charges. The average root-mean-square error (RMSE) of DeepAtomicCharge is 0.0121 e, which is obviously more accurate than that (0.0180 e) reported by the previous benchmark study on the same two external test sets. Moreover, the new GCN architecture needs much lower storage space compared with other methods, and the predicted DDEC atomic charges can be efficiently used in large-scale structure-based drug design, thus opening a new avenue for high-performance atomic charge prediction and application.

scholarly journals EAC-Net: Efficient and Accurate Convolutional Network for Video Recognition

2020 ◽  
Vol 34 (07) ◽  
pp. 11149-11156
Author(s):  
Bowei Jin ◽  
Zhuo Xu
Keyword(s):  
High Performance ◽  
High Efficiency ◽  
Multiple Time Scales ◽  
Multiple Time ◽  
Temporal Relations ◽  
Convolutional Network ◽  
Temporal Modeling ◽  
Video Recognition ◽  
Non Local

Research for computation-efficient video understanding is of great importance to real-world deployment. However, most of high-performance approaches are too computationally expensive for practical application. Though several efficiency oriented works are proposed, they inevitably suffer degradation of performance in terms of accuracy. In this paper, we explore a new architecture EAC-Net, enjoying both high efficiency and high performance. Specifically, we propose Motion Guided Temporal Encode (MGTE) blocks for temporal modeling, which exploits motion information and temporal relations among neighbor frames. EAC-Net is then constructed by inserting multiple MGTE blocks to common 2D CNNs. Furthermore, we proposed Atrous Temporal Encode (ATE) block for capturing long-term temporal relations at multiple time scales for further enhancing representation power of EAC-Net. Through experiments on Kinetics, our EAC-Nets achieved better results than TSM models with fewer FLOPs. With same 2D backbones, EAC-Nets outperformed Non-Local I3D counterparts by achieving higher accuracy with only about 7× fewer FLOPs. On Something-Something-V1 dataset, EAC-Net achieved 47% top-1 accuracy with 70G FLOPs which is 0.9% more accurate and 8× less FLOPs than that of Non-Local I3D+GCN.

Sign in / Sign up

Export Citation Format

Share Document