检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Koleilat, Taha Asgariandehkordi, Hojat Rivaz, Hassan Xiao, Yiming Department of Electrical and Computer Engineering Concordia University Montreal Canada Department of Computer Science and Software Engineering Concordia University Montreal Canada

Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most methods still lack data efficiency, generalizability, and interactability. Consequently, the development of new, precise segmentation methods that demand fewer labeled datasets is of utmost importance in medical image analysis. Recently, the emergence of foundation models, such as CLIP and Segment-Anything-Model (SAM), with comprehensive cross-domain representation opened the door for interactive and universal image segmentation. However, exploration of these models for data-efficient medical image segmentation is still limited, but is highly necessary. In this paper, we propose a novel framework, called MedCLIP-SAM that combines CLIP and SAM models to generate segmentation of clinical scans using text prompts in both zero-shot and weakly supervised settings. To achieve this, we employed a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss to fine-tune the BiomedCLIP model and the recent gScoreCAM to generate prompts to obtain segmentation masks from SAM in a zero-shot setting. Additionally, we explored the use of zero-shot segmentation labels in a weakly supervised paradigm to improve the segmentation quality further. By extensively testing three diverse segmentation tasks and medical image modalities (breast tumor ultrasound, brain tumor MRI, and lung X-ray), our proposed framework has demonstrated excellent accuracy. Code is available at https://***/HealthX-Lab/MedCLIP-SAM. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Joint enhancement of automatic chest X-ray diagnosis and radiological gaze prediction with multi-stage cooperative learning

arXiv

引用

arXiv 2024年

作者： Qiu, Zirui Rivaz, Hassan Xiao, Yiming Department of Computer Science and Software Engineering Concordia University Montreal Canada Department of Electrical and Computer Engineering Concordia University Montreal Canada

Background: As visual inspection is an inherent process during radiological screening, the associated eye gaze data can provide valuable insights into relevant clinical decision processes and facilitate computer-assisted diagnosis. However, the relevant techniques are still under-explored. Purpose: With deep learning becoming the state-of-the-art for computer-assisted diagnosis, integrating human behavior, such as eye gaze data, into these systems is instrumental to help guide machine predictions with clinical diagnostic criteria, thus enhancing the quality of automatic radiological diagnosis. In addition, the ability to predict a radiologist’s gaze saliency from a clinical scan along with the automatic diagnostic result could be instrumental for the end users. Methods: We propose a novel deep learning framework for joint disease diagnosis and prediction of corresponding radiological gaze saliency maps for chest X-ray scans. Specifically, we introduce a new dual-encoder multi-task UNet, which leverages both a DenseNet201 backbone and a Residual and Squeeze-and-Excitation block-based encoder to extract diverse features for visual saliency map prediction, and a multi-scale feature-fusion classifier to perform disease classification. To tackle the issue of asynchronous training schedules of individual tasks in multi-task learning, we propose a multi-stage cooperative learning strategy, with contrastive learning for feature encoder pretraining to boost performance. Results: Our proposed method is shown to significantly outperform existing techniques for chest radiography diagnosis (AUC = 0.93) and the quality of visual saliency map prediction (correlation coefficient = 0.58). Conclusion: Benefiting from the proposed multi-task multi-stage cooperative learning, our technique demonstrates the benefit of integrating clinicians’ eye gaze into radiological AI systems to boost performance and potentially explainability. © 2024, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Threat Intelligence Coalitions for Improved Cyber Defense Capabilities

Dynamic Threat Intelligence Coalitions for Improved Cyber De...

引用

IEEE International Conference on Cloud Networking (CLOUDNET)

作者： Omar Abdel Wahab Department of Computer and Software Engineering Polytechnique Montréal Montréal Canada

ISBN: (数字)9798350376562

ISBN: (纸本)9798350376579

In the dynamic landscape of cybersecu-rity and cyber warfares, Cyber Threat Intelligence (CTI) is increasingly relied on for gathering and sharing the latest information about threats and their trends. Current CTI sharing methods (e.g., ISACs, automated STIX/TAXII platforms), face challenges in terms of scalability, trust, and data quality issues. This is because they often lack systematic metrics for evaluating the quality and relevance of the threat data that are being shared. Moreover, they do not offer any mechanism to enable participating organizations to autonomously make decisions as to what Threat Intelligence providers to request and share data from/to. To address these limitations, we propose a novel Threat Intelligence sharing approach based on coalitional game theory. We first propose a set of metrics that enable organizations to assess the effectiveness of the shared Threat Intelligence data. Based on these metrics, we propose a preference function and a coalition formation algorithm that enable organizations to autonomously join and leave Threat Intelligence coalitions until reaching a Nash-Stable situation wherein no organization has incentive to leave its current coalition and join another one. Experiments suggest that our solution significantly improves the Mean Time to Detect (MTTD), Mean Time to Respond (MTTR) and Containment Rate.

关键词： Measurement Systematics Machine learning algorithms Scalability Data integrity Organizations Reliability theory Market research Real-time systems Cyber threat intelligence

来源：评论

学校读者我要写书评

暂无评论

Real-Time Simultaneous Localization and Mapping with LiDAR Intensity

arXiv

引用

arXiv 2023年

作者： Du, Wenqiang Beltrame, Giovanni The Department of Computer Engineering and Software Engineering Polytechnique Montreal University of Montreal MontrealQCH3T1J4 Canada

We propose a novel real-time LiDAR intensity image-based simultaneous localization and mapping method, which addresses the geometry degeneracy problem in unstructured environments. Traditional LiDAR-based front-end odometry mostly relies on geometric features such as points, lines and planes. A lack of these features in the environment can lead to the failure of the entire odometry system. To avoid this problem, we extract feature points from the LiDAR-generated point cloud that match features identified in LiDAR intensity images. We then use the extracted feature points to perform scan registration and estimate the robot ego-movement. For the back-end, we jointly optimize the distance between the corresponding feature points, and the point to plane distance for planes identified in the map. In addition, we use the features extracted from intensity images to detect loop closure candidates from previous scans and perform pose graph optimization. Our experiments show that our method can run in real time with high accuracy and works well with illumination changes, low-texture, and unstructured environments. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention

arXiv

引用

arXiv 2025年

作者： Manzari, Omid Nejati Asgariandehkordi, Hojat Koleilat, Taha Xiao, Yiming Rivaz, Hassan Tehran Iran Department of Electrical and Computer Engineering Concordia University Montreal Canada Department of Computer Science and Software Engineering Concordia University Montreal Canada

Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However, these methods were primarily designed to classify clean images using labeled data. In contrast, real-world clinical data often involve image corruptions that are unique to multi-center studies and stem from variations in imaging equipment across manufacturers. In this paper, we introduce the Medical Vision Transformer (MedViTV2), a novel architecture incorporating Kolmogorov-Arnold Network (KAN) layers into the transformer architecture for the first time, aiming for generalized medical image classification. We have developed an efficient KAN block to reduce computational load while enhancing the accuracy of the original MedViT. Additionally, to counteract the fragility of our MedViT when scaled up, we propose an enhanced Dilated Neighborhood Attention (DiNA), an adaptation of the efficient fused dot-product attention kernel capable of capturing global context and expanding receptive fields to scale the model effectively and addressing feature collapse issues. Moreover, a hierarchical hybrid strategy is introduced to stack our Local Feature Perception and Global Feature Perception blocks in an efficient manner, which balances local and global feature perceptions to boost performance. Extensive experiments on 17 medical image classification datasets and 12 corrupted medical image datasets demonstrate that MedViTV2 achieved state-of-the-art results in 27 out of 29 experiments with reduced computational complexity. MedViTV2 is 44% more computationally efficient than the previous version and significantly enhances accuracy, achieving improvements of 4.6% on MedMNIST, 5.8% on NonMNIST, and 13.4% on the MedMNIST-C benchmark. Our code is available at https://***/Omid-Nejati/*** © 2025, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Toponym Identification in Epidemiology Articles – A Deep Learning Approach 20th

Toponym Identification in Epidemiology Articles – A Deep L...

引用

20th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2019

作者： Davari, MohammadReza Kosseim, Leila Bui, Tien D. Department of Computer Science and Software Engineering Concordia University MontrealQCH3G 1M8 Canada

ISBN: (纸本)9783031243394

When analyzing the spread of viruses, epidemiologists often need to identify the location of infected hosts. This information can be found in public databases, such as GenBank [3], however, information provided in these databases are usually limited to the country or state level. More fine-grained localization information requires phylogeographers to manually read relevant scientific articles. In this work we propose an approach to automate the process of place name identification from medical (epidemiology) articles. The focus of this paper is to propose a deep learning based model for toponym detection and experiment with the use of external linguistic features and domain specific information. The model was evaluated using a collection of 105 epidemiology articles from PubMed Central [33] provided by the recent SemEval task 12 [28]. Our best detection model achieves an F1 score of 80.13 %, a significant improvement compared to the state of the art of 69.84 %. These results underline the importance of domain specific embedding as well as specific linguistic features in toponym detection in medical journals. © 2023, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Broadcasting in Split Graphs 13th

Broadcasting in Split Graphs

引用

13th International Symposium on Algorithms and Complexity, CIAC 2023

作者： Harutyunyan, Hovhannes A. Hovhannisyan, Narek Department of Computer Science and Software Engineering Concordia University MontrealQCH3G 1M8 Canada

ISBN: (纸本)9783031304477

Broadcasting is an information dissemination primitive where a message is passed from one node (called originator) to all other nodes in the network. With the increasing interest in interconnection networks, an extensive amount of research was dedicated to broadcasting. Two main research goals of this area are finding inexpensive network structures that maintain efficient broadcasting and finding the broadcast time for well-known and widely used network topologies. In the scope of this paper, we will mainly focus on determining the broadcast time and the optimal broadcasting scheme for graphs. Determination of the broadcast time of a node x in an arbitrary network G is known to be NP-hard. Polynomial time solutions are known only for a few classes of networks. There also exist various heuristic and approximation algorithms for different network topologies. In this paper, we will consider networks that can be represented as split graphs. We will present a polynomial time 2-approximation algorithm for the broadcast time problem and will introduce an algorithm for generating optimal or near-optimal broadcast schemes in split graphs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information dissemination

来源：评论

学校读者我要写书评

暂无评论

Broadcasting in chains of rings 14

Broadcasting in chains of rings

引用

14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

作者： Harutyunyan, Hovhannes A. Hovhannisyan, Narek Maraachlian, Edward Concordia University Department of Computer Science and Software Engineering MontrealQCH3G 1M8 Canada

ISBN: (纸本)9798350335385

Broadcasting is an information dissemination problem in an interconnection network where one node, called the originator, must distribute a message to all other nodes by placing a series of calls along the links of the network. Every time the informed nodes aid the originator in distributing the message. Finding the broadcast time of any node in an arbitrary network is NP-complete. Polynomial time solutions are known only for a few classes of networks. In this paper, we consider chains of rings. We present a linear algorithm to find the broadcast time of arbitrary chains of rings and closed chains of rings. © 2023 IEEE.

关键词： Broadcasting

来源：评论

学校读者我要写书评

暂无评论

Broadcasting in interconnection networks based on node partitioning 3

Broadcasting in interconnection networks based on node parti...

引用

3rd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2023

作者： Harutyunyan, Hovhannes A. Hovhannisyan, Narek Concordia University Department of Computer Science and Software Engineering MontrealQCH3G 1M8 Canada

ISBN: (纸本)9798350333732

Broadcasting is one of the information dissemination primitives where a message is passed from one node (called originator) to all other nodes in the network. With the increasing interest in interconnection networks, an extensive amount of research was dedicated to broadcasting. Two main research goals of this area are finding inexpensive network structures that maintain efficient broadcasting and finding the broadcast time for well-known and widely used network *** the scope of this paper, we will mainly focus on determining the broadcast time and near-optimal broadcasting schemes in networks. Determination of the broadcast time of any node in an arbitrary network is known to be NP-hard. Polynomial time solutions are known only for a few network topologies. There also exist various heuristic and approximation algorithms for different network topologies. In this paper, we will present an efficient heuristic for the broadcast time problem in networks, where the nodes can be partitioned into two groups. © 2023 IEEE.

关键词： Broadcasting

来源：评论

学校读者我要写书评

暂无评论

Efficient Heuristic for Broadcasting in Chordal Networks 37th

Efficient Heuristic for Broadcasting in Chordal Networks

引用

37th International Conference on Advanced Information Networking and Applications, AINA 2023

作者： Harutyunyan, Hovhannes A. Hovhannisyan, Narek Department of Computer Science and Software Engineering Concordia University MontrealQCH3G 1M8 Canada

ISBN: (纸本)9783031290558

Broadcasting is one of the information dissemination primitives where a message is passed from one node (called originator) to all other nodes in the network. With the increasing interest in interconnection networks, an extensive amount of research was dedicated to broadcasting. Two main research goals of this area are finding inexpensive network structures that maintain efficient broadcasting and finding the broadcast time for well-known and widely used network topologies. In the scope of this paper, we will mainly focus on determining the broadcast time and near-optimal broadcasting schemes in networks. Determination of the broadcast time of a node x in arbitrary network G is known to be NP-hard. Polynomial-time solutions are known only for a few network topologies. There also exist various heuristic and approximation algorithms for different network topologies. In this paper, we will consider a large subset of chordal networks. We will present an efficient heuristic for the broadcast time problem in these networks and will present some empirical results. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Broadcasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：