Abstract:Community-acquired pneumonia (CAP) poses a global public health challenge, and in the current environment of the pneumonia pandemic, timely and accurate diagnosis of different types of pneumonia is particularly crucial. Computed Tomography (CT) is an effective means of diagnosing pneumonia, and the use of artificial intelligence (AI) for diagnostic assistance can enhance clinical diagnostic efficiency. Therefore, this paper introduces a 3D multitask deep learning model called TransFuseNet to achieve real-time and accurate segmentation and classification of CAP.Specifically, the proposed network consists of two sub-networks: a 3D scSEU-Net sub-network for pneumonia lesion segmentation and a classification sub-network based on a fully convolutional Transformer. Both sub-networks share the same encoder, where the segmentation branch captures local features and spatial relationships, while the classification branch performs long-range modeling to capture global context information. Simultaneously, a loss function is introduced to enhance the interaction between the two sub-networks, balancing the importance of the two tasks.The retrospective dataset includes 180 patients who underwent thin-slice chest CT scans at a medical center in China. Numerous experiments demonstrate that the model achieved AUC: 0.989, DSC: 0.723, average accuracy: 0.927, precision: 0.889, sensitivity: 0.866, and specificity: 0.835 on the test set. The model shows no significant difference in pneumonia detection accuracy compared to radiologists.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. TransFuseNet: A Novel Multi-task Model for Community-Acquired Pneumonia Segmentation and Classification
	CHE PeiShuai,YIN Si-Xing,LI Shu-Fang
	Computer Science and Technology 13 March 2024
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Community-acquired pneumonia (CAP) poses a global public health challenge, and in the current environment of the pneumonia pandemic, timely and accurate diagnosis of different types of pneumonia is particularly crucial. Computed Tomography (CT) is an effective means of diagnosing pneumonia, and the use of artificial intelligence (AI) for diagnostic assistance can enhance clinical diagnostic efficiency. Therefore, this paper introduces a 3D multitask deep learning model called TransFuseNet to achieve real-time and accurate segmentation and classification of CAP.Specifically, the proposed network consists of two sub-networks: a 3D scSEU-Net sub-network for pneumonia lesion segmentation and a classification sub-network based on a fully convolutional Transformer. Both sub-networks share the same encoder, where the segmentation branch captures local features and spatial relationships, while the classification branch performs long-range modeling to capture global context information. Simultaneously, a loss function is introduced to enhance the interaction between the two sub-networks, balancing the importance of the two tasks.The retrospective dataset includes 180 patients who underwent thin-slice chest CT scans at a medical center in China. Numerous experiments demonstrate that the model achieved AUC: 0.989, DSC: 0.723, average accuracy: 0.927, precision: 0.889, sensitivity: 0.866, and specificity: 0.835 on the test set. The model shows no significant difference in pneumonia detection accuracy compared to radiologists.
	TO cite this article:CHE PeiShuai,YIN Si-Xing,LI Shu-Fang. TransFuseNet: A Novel Multi-task Model for Community-Acquired Pneumonia Segmentation and Classification[OL].[13 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762404


	2. DrivCapsNet: A Driving Style Detection Algorithm Based on Capsule Network
	Yueyue Wang,Chenxing Wang,Haiyong Luo
	Computer Science and Technology 26 May 2023
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Driver behavior plays a fundamental role in the driver-vehicle-environment system, where the driving style can significantly impact vehicle emissions, fuel consumption, insurance expenses, road safety, and advanced driver assistance systems (ADAS). Nonetheless, detecting driver behavior is a complex and challenging task, traditional methods require a lot of data pre-processing and there is still no research on discriminative driving behavior with capsule networks which can capture the spatial relationships of data. However, it has not been fully studied and applied for driver behavior detection. To tackle these challenges, we propose an methodology for detecting driving style using a capsule network, named DrivCapsNet, which is capable of detecting various driving styles using either inertial measurement unit (IMU) data or camera data. A crucial advantage of this method is that its dynamic routing mechanism can extract the relationships between the parts and the entity, thereby improving detection accuracy. We performed comprehensive experiments on two realistic driving datasets to substantiate the efficacy of our proposed DrivCapsNet approach. The outcomes validate that our approach performs well and achieves accurate driving style detection, highlighting its potential to contribute significantly to the field of driver behavior analysis.
	TO cite this article:Yueyue Wang,Chenxing Wang,Haiyong Luo. DrivCapsNet: A Driving Style Detection Algorithm Based on Capsule Network[OL].[26 May 2023] http://en.paper.edu.cn/en_releasepaper/content/4760841

Saved Papers

Saved Papers


	3. Automated Left Ventricular Myocardium Segmentation of Coronary Computed Tomography Angiography Based on Improved 2.5D U-Net
	CHU Dong-Heng, LI Shu-Fang
	Computer Science and Technology 24 April 2023
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Cardiovascular disease has become one of the major health hazards and non-invasive diagnostic methods are of great clinical importance for early intervention and treatment of cardiovascular disease. The widespread use of computed tomography (CT) and the rapid development of deep learning technologies have made it possible to perform non-invasive cardiac flow functional assessment based on coronary CTA images. Among them, the accurate segmentation of the left ventricular myocardium (LVM) region in coronary CTA images is the basis for effective quantification of functional pathological differences, which is essential to assist in the treatment and management of coronary artery disease. In this paper, a 2.5D segmentation algorithm based on improved U-Net is proposed for the purpose of segmenting LVM based on coronary CTA images. Unlike other deep learning-based segmentation methods, firstly, this paper implements a 2.5D segmentation model by thickening the samples. Secondly, this study proposes Dilated Slice and introduces an information correction module and a multi-stage multi-scale pooling module into the network model, which enables it to better focus on the features of the LVM region, thus improving the segmentation accuracy. In this paper, the algorithm is trained and tested based on a coronary CTA image dataset. Experiments demonstrate that the use of the newly proposed sampling method and the improved segmentation model can achieve optimal results in the task of implementing LVM region segmentation based on coronary CTA images.
	TO cite this article:CHU Dong-Heng, LI Shu-Fang. Automated Left Ventricular Myocardium Segmentation of Coronary Computed Tomography Angiography Based on Improved 2.5D U-Net[OL].[24 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4760523


	4. Dynamic Embedding Networks with Contrastive Learning for Session-based Recommendation
	Xukai Bao,Yulong Wang
	Computer Science and Technology 06 February 2023
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Most recent studies on session-based recommendation (SBR) utilize RNNs or GNNs to capture complex transitions among items and employ an attention mechanism to generate session embedding. However, they fail to pay sufficient attention to the relevance of items within the session, as they simply use a fixed embedding, such as the last clicked item, the average item within the session, or a special fixed item as the user’s current interest to generate session embedding, which would allow unrelated items to influence the recommendation results. In this study, to overcome these problems, a novel \textbf{D}ynamic \textbf{E}mbedding \textbf{N}etworks (DEN), is proposed by which user preferences are dynamically and accurately captured by integrating an affinity matrix and self-attention mechanism. In addition, to avoid the overfitting problem caused by data sparsity, a self-supervised contrastive learning task is incorporated into the DEN model to enhance the representations of embeddings using only the dropout masks as noise. Extensive experimental results on three real public datasets demonstrate that the proposed method outperforms the state-of-the-art session-based recommendation methods.
	TO cite this article:Xukai Bao,Yulong Wang. Dynamic Embedding Networks with Contrastive Learning for Session-based Recommendation[OL].[ 6 February 2023] http://en.paper.edu.cn/en_releasepaper/content/4758949


	5. Patch Refinement Network for Portrait Matting
	Zhen Cheng, Qi Qi
	Computer Science and Technology 25 December 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Portrait matting is a challenging task in the field of computer vision, which has important applications in meeting background replacement, image editing and other scenarios. However, how to obtain high precision alpha matte, especially for the part of the edge transition area, has been a difficult problem in this field. Focusing on the post processing part of the encoder-decoder, this paper designs a new efficient patch refinement network(PRN). It first recieves a coarse alpha matte and repair the selected patches under the guidance of flaw map, these patches will be reassembled to origin alpha matte to obtain high precision results. At the same time, this paper introduces ConvGRU into the refinement layer, which can improve the temporal consistency when migrating the refinement network to the task of video portrait matting. Experiments show that the PRN allows the original image to be sent to the network after down-sampling, which can improve the performance of the network inference while recovering the high-resolution details of the alpha matte as much as possible.
	TO cite this article:Zhen Cheng, Qi Qi. Patch Refinement Network for Portrait Matting[OL].[25 December 2022] http://en.paper.edu.cn/en_releasepaper/content/4758745


	6. Affinity and Uniqueness Learning with Adaptive Data Augmentation for Recommendations
	ZhaoXi,WangYulong
	Computer Science and Technology 23 November 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:The negative item sampling strategies adopted in current recommendation models with implicit feedback have difficulty discriminating real negative examples from false negative ones (i.e., potentially positive ones). As a result, significant amounts of misleading information are used in the representation learning of users and items, resulting in slow convergence speeds and unsatisfactory recommendation results. To avoid the drawbacks of these approaches, we propose a novel model-agnostic framework, called the Affinity and Uniqueness Learning with Adaptive Data Augmentation (AUL-AD) framework, which does not require sampling negative user-item pairs from unobserved interactions. Specifically, we design an affinity and uniqueness learning objective in AUL-AD, which aims to encourage the similarity between positive-related users and items and the discrimination of each user (or item). Because there is a lack of supervised signals from inactive users and long-tailed items for affinity-uniqueness learning, we further designed a self-supervised task with an adaptive augmentation scheme based on user activity and item popularity. Extensive experiments on three real-world datasets demonstrate the superiority of our proposed framework, which can significantly improve the recommendation accuracy and efficiency.
	TO cite this article:ZhaoXi,WangYulong. Affinity and Uniqueness Learning with Adaptive Data Augmentation for Recommendations[J].


	7. Bidirectional Group Random Walk Based Network Embedding for Asymmetric Proximity
	Shen Jia-Wei,Shu Xin-Cheng,Yang Hu,Yang Hu
	Computer Science and Technology 28 March 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Network embedding aims to represent a network into a low dimensional space where the network structural information and inherent properties are maximumly preserved. Random walk based network embedding methods such as DeepWalk and node2vec have shown outstanding performance in the aspect of preserving the network topological structure. However, these approaches either predict the distribution of a node's neighbors in both direction together, which makes them unable to capture any asymmetric relationship in a network; or preserve asymmetric relationship in only one direction and hence lose the one in another direction. To address these limitations, this paper proposes bidirectional group random walk based network embedding method (BiGRW), which treats the distributions of a node's neighbors in the forward and backward direction in random walks as two different asymmetric network structural information. The basic idea of BiGRW is to learn a representation for each node that is useful to predict its distribution of neighbors in the forward and backward direction separately. Apart from that, a novel random walk sampling strategy is proposed with a parameter $\alpha$ to flexibly control the trade-off between breadth-first sampling (BFS) and depth-first sampling (DFS). To learn representations from node attributes, we design an attributed version of BiGRW (BiGRW-AT). Experimental results on several benchmark datasets demonstrate that the proposed methods significantly outperform the state-of-the-art plain and attributed network embedding methods on tasks of node classification and clustering.
	TO cite this article:Shen Jia-Wei,Shu Xin-Cheng,Yang Hu, et al. Bidirectional Group Random Walk Based Network Embedding for Asymmetric Proximity[OL].[28 March 2022] http://en.paper.edu.cn/en_releasepaper/content/4756843


	8. Mobility Prediction with Label Noise Based on Calibration Network
	Qing Miao,Yuanyuan Qiao
	Computer Science and Technology 15 March 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Predicting citywide human mobility is of great importance to several related fields, such as urban planning and traffic engineering. However, mobility data collected in a whole metropolis always faces challenges of label noise and few ground truth annotation. Blindly training with these noisy trajectories could certainly introduce inappropriate bias to model parameters, and reduce the performance of mobility prediction. This paperproposes a prediction with calibration framework, to quantify the quality and importance of each trajectory. The main module of proposed approach is a pre-trained calibration network, which is designed to be model-independent and can be trained in an unsupervised manner. It takes trajectories of a mobile user as input, evaluates the quality of them by learning intrinsic regularity and periodicity, and finally returns a numerical score. In this way, trajectories with strong regularity and periodicity for prediction could get higher scores, while the irregular movements with weak predictability score lower. Finally, a neural prediction model is trained with instance weighting strategy, which integrates the results of calibration network into the parameter updating process of mobility prediction model. Experiments conducted on citywide mobility dataset demonstrate the effectiveness of proposed approach, when dealing with massive noisy trajectories in real world.
	TO cite this article:Qing Miao,Yuanyuan Qiao. Mobility Prediction with Label Noise Based on Calibration Network[OL].[15 March 2022] http://en.paper.edu.cn/en_releasepaper/content/4756745


	9. Hard Posture-aware Graph Embedding for Human-Object Interaction Detection
	FAN Hongwei,邓伟洪
	Computer Science and Technology 14 March 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:Detecting Human-object Interaction~(HOI) is foundamental for deeper visual understanding. Recent work has focused on the input of human pose and the design of graph neural network, and progress has been made in performance. However, these methods cannot adapt to the difficult pose input, which restricts the further development on them. To tackle this problem, this paper proposes a Hard Pose-aware Graph Embedding (HPGE) pipeline, which first encodes the pose features with a Pose Aggregation Network (PAN), and then models the difficult pose input with the proposed Feature Gate (FG) and Pose Component Augmentation (PCAug). FG designs a switch gate controlling the connection with human feature and pose feature, and closes the connection with pose features when the pose input cannot be relied; PCAug further exploits the potential of pose component features basing on the variance of pose component boxes with Gaussian distribution. The paper evaluates the proposed method on two recent datasets V-COCO and HICO-DET, and the experimental results show that the proposed FG and PCAug method improve the performance compared to the vanilla baseline, and with these methods HPGE can achieve the level of mainstream human-object interaction detection methods. Moreover, the paper also conducts ablation study, parameter analysis and model visualization of the HPGE pipeline.
	TO cite this article:FAN Hongwei,邓伟洪. Hard Posture-aware Graph Embedding for Human-Object Interaction Detection[OL].[14 March 2022] http://en.paper.edu.cn/en_releasepaper/content/4756656


	10. OSnet:One-Shot Network for Video Inpainting
	Tan Rujian,Wang Jing
	Computer Science and Technology 28 February 2022
	Show/Hide Abstract \| Cite this paper︱Full-text: PDF (0 B)

	Abstract:video inpainting is a challenging task in the field of computer vision. Current methods are usually flow based methods in order to improve temporal coherence, and get better inpainting result. However, these networks are usually complex, and have less use value. In this paper, wo propose a quick video inpainting network based on endoder-decoder architecture, which optimizes network running time by enhance the ability of network feature extraction.We validate our approach on our video inpainting dataset based on DAVIS and Septuplet dataset. Experment results show that our method compares favorably against the mainstream algorithms, and has good inpainting capability.
	TO cite this article:Tan Rujian,Wang Jing. OSnet:One-Shot Network for Video Inpainting[OL].[28 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756327

	Check out RSS, or use RSS reader to subscribe this item