检索结果-内蒙古大学图书馆

Interactive 3D Models and Animations for Cardiac Imaging Education

学校读者我要写书评

暂无评论

Journal of Medical Imaging and Radiation Sciences 2024年第3期55卷 101547-101547页

作者： Dr Nur Hayati Jasmin Dr Wan Mohd Rizhan Wan Idris Miss Nur Awfa Mohd Hilmi Mr Mohammad Izzat Zulkifli Miss Nurul Ashikin Roslan Miss Siti Nur Athirah Mohd Azhar School of Medical Imaging Faculty of Health Sciences Universiti Sultan Zainal Abidin Terengganu Malaysia Centre of Multimedia Studies Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Terengganu Malaysia Centre of Information Technology Faculty of Informatics and Computing Terengganu Malaysia

Background Cardiac imaging is a specialized branch of medical imaging that focuses on capturing detailed images of the heart. The coronary angiography procedure is one of the cardiac imaging techniques where radiographers use different angles and projections to get a comprehensive view of the coronary arteries in the heart and assess any potential blockages or abnormalities. Radiography student needs to grasp the theoretical and practical knowledge of these procedures before attending their clinical attachments and working in the field. However, the current teaching relies on static visualization (eg. still illustrations and photographs) which is insufficient to deliver the complex concepts in cardiac imaging. Practical sessions are challenging due to the limited access to the facility and involve ionizing radiation. Integrating 3D models and animations into e-learning for teaching cardiac imaging can significantly enhance the learning experience and provide an immersive and interactive environment. Methods 3D models and animations were developed using Autodesk Maya software from creating 3D models to animations and rendering of coronary angiography procedures demonstrating different angles and projections. Results 3D models and animations provide a dynamic visualization of the complex imaging procedure. All animations also provide a short description of each angulation, projection, and image, as well as other important notes related to clinical applications and scenarios. This allows students to learn the real-life scenarios and situations they might encounter in imaging patients in the hospital. This study could be extended for visualization in augmented reality (AR) where students can turn the 3D models around and manipulate the model in their own hands to perform the coronary angiography procedure. Conclusion 3D models and animations in cardiac imaging education simplify abstract processes and enhance understanding, in line with the needs of the current generati

关键词：

SGUQ: Staged Graph Convolution Neural Network for Alzheimer’s Disease Diagnosis using Multi-Omics Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tao, Liang Xie, Yixin Deng, Jeffrey D. Shen, Hui Deng, Hong-Wen Zhou, Weihua Zhao, Chen Department of Computer Science Kennesaw State University MariettaGA30060 United States Department of Information Technology Kennesaw State University MariettaGA30060 United States Geisel School of Medicine Dartmouth College Hamover NH03755 United States Division of Biomedical Informatics and Genomics Tulane Center of Biomedical Informatics and Genomics Deming Department of Medicine Tulane University New OrleansLA70112 United States Department of Applied Computing Michigan Technological University HoughtonMI49931 United States Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States

Alzheimer’s disease (AD) is a chronic neurodegenerative disorder and the leading cause of dementia, significantly impacting cost, mortality, and burden worldwide. The advent of high-throughput omics technologies, such as genomics, transcriptomics, proteomics, and epigenomics, has revolutionized the molecular understanding of AD. Conventional AI approaches typically require the completion of all omics data at the outset to achieve optimal AD diagnosis, which are inefficient and may be unnecessary. To reduce the clinical cost and improve the accuracy of AD diagnosis using multi-omics data, we propose a novel staged graph convolutional network with uncertainty quantification (SGUQ). SGUQ begins with mRNA and progressively incorporates DNA methylation and miRNA data only when necessary, reducing overall costs and exposure to harmful tests. Experimental results indicate that 46.23% of the samples can be reliably predicted using only single-modal omics data (mRNA), while an additional 16.04% of the samples can achieve reliable predictions when combining two omics data types (mRNA + DNA methylation). In addition, the proposed staged SGUQ achieved an accuracy of 0.858 on ROSMAP dataset, which outperformed existing methods significantly. The proposed SGUQ can not only be applied to AD diagnosis using multi-omics data, but also has the potential for clinical decision making using multi-viewed data. Our implementation is publicly available at https://***/chenzhao2023/multiomicsuncertainty. © 2024, CC BY.

关键词： Convolutional neural networks

Community detection in networks using graph embeddings

学校读者我要写书评

暂无评论

Physical Review E 2021年第2期103卷 022316-022316页

作者： Aditya Tandon Aiiad Albeshri Vijey Thayananthan Wadee Alhalabi Filippo Radicchi Santo Fortunato Luddy School of Informatics Computing and Engineering Indiana University Bloomington Indiana 47408 USA Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Kingdom of Saudi Arabia Indiana University Network Science Institute (IUNI) Bloomington Indiana 47408 USA

Graph embedding methods are becoming increasingly popular in the machine learning community, where they are widely used for tasks such as node classification and link prediction. Embedding graphs in geometric spaces should aid the identification of network communities as well because nodes in the same community should be projected close to each other in the geometric space, where they can be detected via standard data clustering algorithms. In this paper, we test the ability of several graph embedding techniques to detect communities on benchmark graphs. We compare their performance against that of traditional community detection algorithms. We find that the performance is comparable, if the parameters of the embedding techniques are suitably chosen. However, the optimal parameter set varies with the specific features of the benchmark graphs, like their size, whereas popular community detection algorithms do not require any parameter. So, it is not possible to indicate beforehand good parameter sets for the analysis of real networks. This finding, along with the high computational cost of embedding a network and grouping the points, suggests that, for community detection, current embedding techniques do not represent an improvement over network clustering algorithms.

关键词： Community structure Complex systems

Optimized efficient attention-based network for facial expressions analysis in neurological health care

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2024年 179卷 108822-108822页

作者： Munsif, Muhammad Sajjad, Muhammad Ullah, Mohib Tarekegn, Adane Nega Cheikh, Faouzi Alaya Tsakanikas, Panagiotis Muhammad, Khan Sejong University Seoul143-747 Korea Republic of Digital Image Processing Lab Department of Computer Science Islamia College Peshawar25000 Pakistan Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Department of Computer Science Norwegian University for Science and Technology Gjøvik2815 Norway Institute of Communication and Computer Systems National Technical University of Athens Athens15773 Greece Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

Facial Expression Analysis (FEA) plays a vital role in diagnosing and treating early-stage neurological disorders (NDs) like Alzheimer's and Parkinson's. Manual FEA is hindered by expertise, time, and training requirements, while automatic methods confront difficulties with real patient data unavailability, high computations, and irrelevant feature extraction. To address these challenges, this paper proposes a novel approach: an efficient, lightweight convolutional block attention module (CBAM) based deep learning network (DLN) to aid doctors in diagnosing ND patients. The method comprises two stages: data collection of real ND patients, and pre-processing, involving face detection and an attention-enhanced DLN for feature extraction and refinement. Extensive experiments with validation on real patient data showcase compelling performance, achieving an accuracy of up to 73.2%. Despite its efficacy, the proposed model is lightweight, occupying only 3MB, making it suitable for deployment on resource-constrained mobile healthcare devices. Moreover, the method exhibits significant advancements over existing FEA approaches, holding tremendous promise in effectively diagnosing and treating ND patients. By accurately recognizing emotions and extracting relevant features, this approach empowers medical professionals in early ND detection and management, overcoming the challenges of manual analysis and heavy models. In conclusion, this research presents a significant leap in FEA, promising to enhance ND diagnosis and *** code and data used in this work are available at: https://***/munsif200/Neurological-Health-Care. © 2024 Elsevier Ltd

关键词： Feature extraction

Sguq: Staged Graph Convolution Neural Network for Alzheimer's Disease Diagnosis Using Multi-Omics Data

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Tao, Liang Xie, Yixin Deng, Jeffrey D. Shen, Hui Deng, Hong-Wen Zhou, Weihua Zhao, Chen Department of Computer Science Kennesaw State University MariettaGA30060 United States Department of Information Technology Kennesaw State University MariettaGA30060 United States Geisel School of Medicine Dartmouth College HanoverNH03755 United States Division of Biomedical Informatics and Genomics Tulane Center of Biomedical Informatics and Genomics Deming Department of Medicine Tulane University New OrleansLA70112 United States Department of Applied Computing Michigan Technological University HoughtonMI49931 United States Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States

Background and Objective: Alzheimer’s disease (AD) is a chronic neurodegenerative disorder and the leading cause of dementia, significantly impacting cost, mortality, and burden worldwide. The advent of high-throughput omics technologies, such as genomics, transcriptomics, proteomics, and epigenomics, has revolutionized the molecular understanding of AD. Conventional AI approaches typically require the completion of all omics data at the outset to achieve optimal AD diagnosis, which are inefficient and may be unnecessary. We aim to propose a cost-effective method for AD ***: To reduce the clinical cost and improve the accuracy of AD diagnosis using multi-omics data, we propose a novel staged graph convolutional network with uncertainty quantification (SGUQ) model. SGUQ begins with mRNA and progressively incorporates miRNA and DNA methylation data only when necessary, reducing overall costs and exposure to harmful ***: Experimental results indicate that 0.94% of the samples can be reliably predicted using only single-modal omics data (mRNA), while an additional 33.96% of the samples can achieve reliable predictions when combining two omics data types (mRNA + miRNA). In addition, the proposed staged SGUQ achieved an accuracy of 0.878 on ROSMAP dataset, which outperformed existing methods ***: The proposed SGUQ can not only be applied to AD diagnosis using multi-omics data, but also has the potential for clinical decision making using multi-viewed data. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

Asym-Unet: An Asymmetric U-Shape Network for Lesion Segmentation of Breast Cancer

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Jia Shao, Jun Xu, Sen Tang, Zhiyong Liu, Weiquan Li, Zeshuai Wang, Tao Bian, Xuesheng Department of Information Engineering Yancheng Institute of Technology Jiangsu Yancheng224007 China Fujian Key Lab of Sensing and Computing for Smart Cities School of Informatics Xiamen University Fujian Xiamen361000 China Department of Ultrasound The First People’s Hospital of Yancheng Jiangsu Yancheng224007 China Department of Electrical Engineering Shanxi Electric Power Technical College Shanxi Taiyuan030020 China

Precise segmentation of breast ultrasound images is crucial in early breast cancer screening. However, the diverse tumor morphology, blurred boundaries, and the similar grey intensity distribution between lesions and normal tissues in breast ultrasound images make it challenging to segment lesions accurately. To tackle these issues, we propose the Asym-Unet, an asymmetric U-shaped network, to segment the breast lesion in ultrasound images accurately and reliably. In detail, our Asym-Unet consists of a multi-branch residual encoder, an external attention module, and a boundary detection module. The multi-branch residual encoder effectively captures the discriminative representation of breast lesions for subsequent segmentation tasks. The external attention module further guides the network to focus on the lesion areas while filtering out interference information for diagnosis. Additionally, to further improve the network's performance, we introduce the boundary detection module for refining the boundary of the predicted masks. The boundary detection module offers extra supervision and guidance through a multi-level prediction layer. We compared our Asym-Unet with ten other segmentation methods on two publicly available datasets. The results demonstrate that the network performs state-of-the-art in the breast tumor segmentation task. © 2024, The Authors. All rights reserved.

关键词： Diagnosis

A review of AI-enabled routing protocols for UAV networks: Trends, challenges, and future outlook

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rovira-Sugranes, Arnau Razi, Abolfazl Afghah, Fatemeh Chakareski, Jacob School of Informatics Computing and Cyber Systems Northern Arizona University Flagstaff United States School of Computing Clemson University Clemson United States Department of Electrical Engineering Clemson University Clemson United States College of Computing New Jersey Institute of Technology Newark United States

Unmanned Aerial Vehicles (UAVs), as a recently emerging technology, enabled a new breed of unprecedented applications in different domains. This technology’s ongoing trend is departing from large remotely-controlled drones to networks of small autonomous drones to collectively complete intricate tasks time and cost-effectively. An important challenge is developing efficient sensing, communication, and control algorithms that can accommodate the requirements of highly dynamic UAV networks with heterogeneous mobility levels. Recently, the use of Artificial Intelligence (AI) in learning-based networking has gained momentum to harness the learning power of cognizant nodes to make more intelligent networking decisions by integrating computational intelligence into UAV networks. An important example of this trend is developing learning-powered routing protocols, where machine learning methods are used to model and predict topology evolution, channel status, traffic mobility, and environmental factors for enhanced routing. This paper reviews AI-enabled routing protocols designed primarily for aerial networks, including topology-predictive and self-adaptive learning-based routing algorithms, with an emphasis on accommodating highly-dynamic network topology. To this end, we justify the importance and adaptation of AI into UAV network communications. We also address, with an AI emphasis, the closely related topics of mobility and networking models for UAV networks, simulation tools and public datasets, and relations to UAV swarming, which serve to choose the right algorithm for each scenario. We conclude by presenting future trends, and the remaining challenges in AI-based UAV networking, for different aspects of routing, connectivity, topology control, security and privacy, energy efficiency, and spectrum sharing. © 2021, CC BY.

关键词： Energy efficiency

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Youmi Mizuki, Sakae Fujii, Kazuki Nakamura, Taishi Ohi, Masanari Shimada, Hinari Shiotani, Taihei Saito, Koshiro Maeda, Koki Hattori, Kakeru Okamoto, Takumi Ishida, Shigeki Yokota, Rio Takamura, Hiroya Okazaki, Naoaki Department of Computer Science School of Computing Institute of Science Tokyo Japan National Institute of Advanced Industrial Science and Technology Japan National Institute of Informatics Japan

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction approach can be easily adapted to other languages;we build datasets for Japanese and confirm that LLMs tuned with our data reach state-of-the-art performance. Analyses suggest that instruction-tuning in a new language allows LLMs to follow instructions, while the tuned models exhibit a notable lack of culture-specific knowledge in that language. The datasets and fine-tuned models will be publicly available1. Our datasets, synthesized with open-weight LLMs, are openly distributed under permissive licenses, allowing for diverse use cases. © 2025, CC BY.

关键词：

What we should learn from pandemic publishing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sikdar, Satyaki Venturini, Sara Charpignon, Marie-Laure Kumar, Sagar Rinaldi, Francesco Tudisco, Francesco Fortunato, Santo Majumder, Maimuna S. Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN United States Department of Computer Science Loyola University Chicago ChicagoIL United States Senseable City Laboratory Massachusetts Institute of Technology CambridgeMA United States Department of Mathematics "Tullio Levi-Civita" University of Padova Padova Italy Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA United States Network Science Institute Northeastern University BostonMA United States School of Mathematics The University of Edinburgh Edinburgh United Kingdom School of Mathematics Gran Sasso Science Institute L’Aquila Italy Department of Pediatrics Harvard Medical School BostonMA United States Computational Health Informatics Program Boston Children’s Hospital BostonMA United States

Since the emergence of COVID-19, discussions of ongoing pandemic-related research have accounted for an unprecedented share of media coverage and debate in the public sphere1. The urgency of the pandemic forced researchers to operate on an accelerated timeline, as both policymakers and the public relied on the most current evidence to guide their decisions and behaviors. With high demand for rapid pandemic-related insights and lower barriers to entry via preprint servers, the volume of COVID-19 articles skyrocketed2. The pressing need for research triggered the participation of many researchers with expertise in the science of infectious disease outbreaks (‘outbreak scientists’), who were joined by researchers from other disciplines (‘bellwethers’) and more junior researchers still in training (‘newcomers’) with the common goal of advancing the frontiers of pandemic science and informing policy decisions3. Please see Box 1 for details of this taxonomy. © 2024, CC BY-NC-ND.

关键词： COVID-19