检索结果-内蒙古大学图书馆

An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jun Aguirre, Aaron Moura, Junior Liu, Che Zhong, Lanhai Sun, Chenxi Clifford, Gari Westover, Brandon Hong, Shenda National Institute of Health Data Science Peking University Beijing China Department of Cardiology Massachusetts General Hospital BostonMA United States Department of Biomedical Informatics School of Medicine Emory University AtlantaGA United States Department of Biomedical Engineering Georgia Institute of Technology AtlantaGA United States Harvard Medical School BostonMA United States Department of Neurology Beth Israel Deaconess Medical Center BostonMA United States Department of Computing Data Science Institute Imperial College London London United Kingdom Zhongshan School of Medicine Sun Yat-sen University Guangzhou China Institute of Medical Technology Peking University Health Science Center Beijing China Institute for Artificial Intelligence Peking University Beijing China

BACKGROUND. Artificial intelligence (AI) has demonstrated significant potential in ECG analysis and cardiovascular disease assessment. Recently, foundation models have played a remarkable role in advancing medical AI, bringing benefits such as efficient disease diagnosis and cross-domain knowledge transfer. The development of an ECG foundation model holds the promise of elevating AI-ECG research to new heights. However, building such a model faces several challenges, including insufficient database sample sizes and inadequate generalization across multiple domains. Additionally, there is a notable performance gap between single-lead and multi-lead ECG analyses. METHODS. We introduced an ECG Foundation Model (ECGFounder), a general-purpose model that leverages real-world ECG annotations from cardiology experts to broaden the diagnostic capabilities of ECG analysis. ECGFounder was trained on over 10 million ECGs with 150 label categories from the Harvard-Emory ECG Database, enabling comprehensive cardiovascular disease diagnosis through ECG analysis. The model is designed to be both an effective out-of-the-box solution, and a to be fine-tunable for downstream tasks, maximizing usability. Importantly, we extended its application to lower rank ECGs, and arbitrary single-lead ECGs in particular. ECGFounder is therefore applicable to supporting various downstream tasks in mobile and remote monitoring scenarios. RESULTS. Experimental results demonstrate that ECGFounder achieves expert-level performance on internal validation sets, with AUROC exceeding 0.95 for eighty diagnoses. It also shows strong classification performance and generalization across various diagnoses on external validation sets. When fine-tuned, ECGFounder outperforms baseline models in demographic analysis, clinical event detection, and cross-modality cardiac rhythm diagnosis, surpassing baseline methods by 3 to 5 points in AUROC. CONCLUSIONS. The ECG foundation model offers an effective solution, allowi

关键词： Electrocardiography

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mao, Xudong Cao, Liujuan Gnanha, Aurele T. Yang, Zhenguo Li, Qing Ji, Rongrong Guangdong Key Laboratory of Big Data Analysis and Processing Sun Yat-Sen University China School of Informatics Xiamen University China Department of Computer Science City University of Hong Kong China Department of Computer Science Guangdong University of Technology China Department of Computing Hong Kong Polytechnic University China

GAN inversion aims to invert an input image into the latent space of a pre-trained GAN. Despite the recent advances in GAN inversion, there remain challenges to mitigate the tradeoff between distortion and editability, i.e. reconstructing the input image accurately and editing the inverted image with a small visual quality drop. The recently proposed pivotal tuning model makes significant progress towards reconstruction and editability, by using a two-step approach that first inverts the input image into a latent code, called pivot code, and then alters the generator so that the input image can be accurately mapped into the pivot code. Here, we show that both reconstruction and editability can be improved by a proper design of the pivot code. We present a simple yet effective method, named cycle encoding, for a high-quality pivot code. The key idea of our method is to progressively train an encoder in varying spaces according to a cycle scheme: W→W+→W. This training methodology preserves the properties of both W and W+ spaces, i.e. high editability of W and low distortion of W+. To further decrease the distortion, we also propose to refine the pivot code with an optimization-based method, where a regularization term is introduced to reduce the degradation in editability. Qualitative and quantitative comparisons to several state-of-the-art methods demonstrate the superiority of our approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

FOUNDATIONAL MODELS IN MEDICAL IMAGING: A COMPREHENSIVE SURVEY AND FUTURE VISION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Azad, Bobby Azad, Reza Eskandari, Sania Bozorgpour, Afshin Kazerouni, Amirhossein Rekik, Islem Merhof, Dorit Electrical Engineering and Computer Science Department South Dakota State University Brookings United States Faculty of Electrical Engineering and Information Technology RWTH Aachen University Aachen Germany Department of Electrical Engineering University of Kentucky Lexington United States Faculty of Informatics and Data Science University of Regensburg Regensburg Germany BASIRA Lab Imperial-X and Computing Department Imperial College London London United Kingdom School of Electrical Engineering Iran University of Science and Technology Tehran Iran dorit.merhofur.de

Foundation models, large-scale, pre-trained deep-learning models adapted to a wide range of downstream tasks have gained significant interest lately in various deep-learning problems undergoing a paradigm shift with the rise of these models. Trained on large-scale dataset to bridge the gap between different modalities, foundation models facilitate contextual reasoning, generalization, and prompt capabilities at test time. The predictions of these models can be adjusted for new tasks by augmenting the model input with task-specific hints called prompts without requiring extensive labeled data and retraining. Capitalizing on the advances in computer vision, medical imaging has also marked a growing interest in these models. With the aim of assisting researchers in navigating this direction, this survey intends to provide a comprehensive overview of foundation models in the domain of medical imaging. Specifically, we initiate our exploration by providing an exposition of the fundamental concepts forming the basis of foundation models. Subsequently, we offer a methodical taxonomy of foundation models within the medical domain, proposing a classification system primarily structured around training strategies, while also incorporating additional facets such as application domains, imaging modalities, specific organs of interest, and the algorithms integral to these models. Furthermore, we emphasize the practical use case of some selected approaches and then discuss the opportunities, applications, and future directions of these large-scale pre-trained models, for analyzing medical images. In the same vein, we address the prevailing challenges and research pathways associated with foundational models in medical imaging. These encompass the areas of interpretability, data management, computational requirements, and the nuanced issue of contextual comprehension. Finally, we gather the over-viewed studies with their available open-source implementations at our GitHub. We aim

关键词： Medical applications

Assistive Technical Communication of Montenegrin eServices: a Case Study

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: ...

International Scientific-Professional Conference on Information technology (IT)

作者： Aniko Simon Luka Laković Pavle Kovačević Peter A. Kara Ivana Ognjanović Ramo Šendelj Christoph Reich Milovan Roganović John Mantas Laszlo Bokor Sigma Technology 1093 Budapest Hungary Faculty for Information Systems and Technologies University of Donja Gorica 81000 Podgorica Montenegro Budapest University of Technology and Economics 1111 Budapest Hungary Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics 1111 Budapest Hungary Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing Wireless Multimedia and Networking Research Group Kingston University London KT1 2EE UK Humanistic Studies University of Donja Gorica 81000 Podgorica Montenegro Institute of Data Science Cloud Computing and IT Security Furtwangen University 78120 Furtwangen Germany Clinic for Neurology Clinical Centre of Montenegro 81000 Podgorica Montenegro Faculty of Nursing School of Health Sciences National and Kapodistrian University of Athens 11527 Goudi Greece

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity.

关键词： Online banking Education Europe Medical services Complexity theory Information technology

Digital Innovations Development: Causal factors and relations - A Case Study of Montenegro

学校读者我要写书评

暂无评论

Digital Innovations Development: Causal factors and relation...

International Scientific-Professional Conference on Information technology (IT)

作者： Ivana Ognjanović Luka Laković Ramo Šendelj Laszlo Bokor Peter A. Kara Christoph Reich Manav Madan Milovan Roganović Emmanouil Zouilas John Mantas Jevto Eraković Tanja Radusinović Nada Rakočević Faculty for Information Systems and Technologies University of Donja Gorica Podgorica Montenegro Humanistic Studies University of Donja Gorica Podgorica Montenegro Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary Institute of Data Science Cloud Computing and IT Security Furtwangen University Furtwangen Germany Clinic for Neurology Clinical Centre of Montenegro Podgorica Montenegro Faculty of Nursing School of Health Sciences National and Kapodistrian University of Athens Goudi Greece Chamber of Economy of Montenegro Podgorica Montenegro

In order for economies to expand and develop globally, innovation is essential. A popular statistic for evaluating innovation between countries is the Global Innovation Index (GII), which provides a thorough analysis of the state of innovation worldwide. In this context, this paper aims to contribute to the literature by examining the multi-factoral effects of the innovation ecosystem on innovation development (internal causal effects), and the impact of global trends and crises on the innovation ecosystem (external causal effects) in Montenegro. The resources provided in this paper offer valuable insights into the innovation landscape in Montenegro and the Western Balkans, as well as the impact of globalization, global trends, and crises on innovation in the region. The paper also discusses the function of innovation hubs such as the DigNest project, in promoting cooperation between academic institutions, government agencies and corporations, and supporting the exchange of knowledge and fresh concepts.

关键词：

Brain multigraph prediction using topology-aware adversarial graph neural network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bessadok, Alaa Mahjoub, Mohamed Ali Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Higher Institute of Informatics and Communication Technologies University of Sousse Tunisia National Engineering School of Sousse University of Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia School of Science and Engineering Computing University of Dundee United Kingdom

Brain graphs (i.e, connectomes) constructed from medical scans such as magnetic resonance imaging (MRI) have become increasingly important tools to characterize the abnormal changes in the human brain. Due to the high acquisition cost and processing time of multimodal MRI, existing deep learning frameworks based on Generative Adversarial Network (GAN) focused on predicting the missing multimodal medical images from a few existing modalities. While brain graphs help better understand how a particular disorder can change the connectional facets of the brain, synthesizing a target brain multigraph (i.e, multiple brain graphs) from a single source brain graph is strikingly lacking. Additionally, existing graph generation works mainly learn one model for each target domain which limits their scalability in jointly predicting multiple target domains. Besides, while they consider the global topological scale of a graph (i.e., graph connectivity structure), they overlook the local topology at the node scale (e.g., how central a node is in the graph). To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. Its three key innovations are: (i) designing a novel graph adversarial auto-encoder for predicting multiple brain graphs from a single one, (ii) clustering the encoded source graphs in order to handle the mode collapse issue of GAN and proposing a cluster-specific decoder, (iii) introducing a topological loss to force the prediction of topologically sound target brain graphs. The experimental results using five target domains demonstrated the outperformance of our method in brain multigraph prediction from a single graph in comparison with baseline approaches. © 2021, CC BY-NC-SA.

关键词： Graphic methods

Hybrid Metaheuristic and Artificial Neural Network Approach for Solving Inverse Kinematics of a SCARA Manipulator Robot

学校读者我要写书评

暂无评论

Hybrid Metaheuristic and Artificial Neural Network Approach ...

International Conference on Innovation and Intelligence for informatics, computing, and Technologies (3ICT)

作者： Rania Bouzid Jyotindra Narayan Hassène Gritli Polytechnic School of Tunisia University of Carthage La Marsa Tunisia RISC Lab (LR16ES07) ENIT University of Tunis El Manar Tunis Tunisia Department of Mechanical Engineering Thapar Institute of Engineering and Technology Patiala Punjab India Department of Computing Imperial College London UK Laboratory of Robotics Informatics and Complex Systems (RISC Lab - LR16ES07) ENIT University of Tunis El Manar Tunis Tunisia ISTIC University of Carthage Tunis Tunisia

ISBN: (数字)9798331533137

ISBN: (纸本)9798331533144

This paper presents a hybrid approach that inte-grates metaheuristic algorithms and Artificial Neural Networks (ANNs) to address the Inverse Kinematics (IK) problem of a SCARA (Selective Compliant Assembly Robot Arm) manipulator robot with four degrees of freedom. The method combines Particle Swarm Optimization (PSO) with ANNs and Genetic Algorithm (GA) with ANNs to optimize training key hyperpa-rameters, such as activation functions and hidden layer sizes using MATLAB's Neural Network Toolbox. Experimental results achieved on a random step size dataset obtained after training show that the PSO-ANN method achieves a Mean Squared Error (MSE) of 0.12846, with a hidden layer size of 90. The GA-ANN method results in an MSE of 0.13785, with a hidden layer size of 91. This hybrid approach significantly reduces MSE in computed joint configurations and demonstrates promise for real-time control applications.

关键词： Training Robotic assembly Technological innovation Metaheuristics Kinematics Artificial neural networks Manipulators Real-time systems Particle swarm optimization Genetic algorithms

A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Wei Du, Jinglong Zhang, Zhao Zhuang, Fuzhen He, Zhongshi College of Computer Science Chongqing University Chongqing China Institute of Artificial Intelligence Beihang University Beijing100191 China College of Medical Informatics Chongqing Medical University Chongqing China Institute of Computing Technology Chinese Academy of Sciences Beijing China SKLSDE School of Computer Science Beihang University Beijing100191 China

Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification). However, most existing approaches either sequentially extract task-specific features, leading to insufficient feature interactions, or they encode aspect features and sentiment features in a parallel manner, implying that feature representation in each task is largely independent of each other except for input sharing. Both of them ignore the internal correlations between the aspect extraction and sentiment classification. To solve this problem, we novelly propose a hierarchical interactive network (HI-ASA) to model two-way interactions between two tasks appropriately, where the hierarchical interactions involve two steps: shallow-level interaction and deep-level interaction. First, we utilize cross-stitch mechanism to combine the different task-specific features selectively as the input to ensure proper two-way interactions. Second, the mutual information technique is applied to mutually constrain learning between two tasks in the output layer, thus the aspect input and the sentiment input are capable of encoding features of the other task via backpropagation. Extensive experiments on three real-world datasets demonstrate HI-ASA’s superiority over baselines1 © 2022, CC BY.

关键词： Sentiment analysis

Dermoscopic Image Classification Using Attention Mechanism and Ensemble Learning Approaches

学校读者我要写书评

暂无评论

Dermoscopic Image Classification Using Attention Mechanism a...

IEEE International Conference on Big Data

作者： Shanchuan Huang Hongwei Lei Liuhan Jin Jinzhu Yang Tao Jiang Yudong Yao Marcin Grzegorzek Chen Li Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang Liaoning China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China Department of Electrical and Computer Engineering Stevens Institute of Technology USA Institute of Medical Informatics University of Luebeck Luebeck Germany

Background and purpose: Skin tumours have become one of the most common diseases worldwide. While benign ones are not usually a threat to human health, malignant ones can develop into skin cancer and become life-threatening if left untreated. Early detection of the disease is important for the treatment of patients with skin tumours and dermoscopy is the most effective means of diagnosing skin tumours. However, the complexity of skin tumour cells makes the diagnosis somewhat erroneous for doctors. Therefore, a dermoscopic classification network based on deep learning and computer-aided diagnostic techniques is needed to obtain a high diagnostic accuracy rate for skin tumours. Methods: In this paper, Deep-skin, a model for dermoscopic image classification is proposed, which is based on both attention mechanism and ensemble learning. Considering the characteristics of dermoscopic images, embedding different attention mechanisms on top of Inception-V3 has been suggested to obtain more potential features. We then improve the classification performance by late fusion of the different models. To demonstrate the effectiveness of Deep-skin, experiments and evaluations are performed on the publicly available dataset Skin Cancer: Malignant vs. Benign and compare the performance of Deep-skin with other classification models. Results: The experimental results indicate that Deep-skin performs well on the dataset in comparison to other models, achieving a maximum accuracy of 87.8%.Conclusion: In this paper, the Deep-skin model is proposed for the classification of dermoscopic images and has shown better performance. In the future, we intend to investigate better classification models for automatic diagnosis of skin tumours. Such models can potentially assist physicians and patients in clinical settings.

关键词：