检索结果-内蒙古大学图书馆

MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chatterjee, Soumick Bajaj, Himanshi Siddiquee, Istiyak H. Subbarayappa, Nandish Bandi Simon, Steve Shashidhar, Suraj Bangalore Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany Genomics Research Centre Human Technopole Milan Italy German Centre for Neurodegenerative Disease Magdeburg Germany Centre for Behavioural Brain Sciences Magdeburg Germany

Image registration is the process of bringing different images into a common coordinate system - a technique widely used in various applications of computer vision, such as remote sensing, image retrieval, and, most commonly, medical imaging. Deep learning based techniques have been applied successfully to tackle various complex medical image processing problems, including medical image registration. Over the years, several image registration techniques have been proposed using deep learning. Deformable image registration techniques such as Voxelmorph have been successful in capturing finer changes and providing smoother deformations. However, Voxelmorph, as well as ICNet and FIRE, do not explicitly encode global dependencies (i.e. the overall anatomical view of the supplied image) and, therefore, can not track large deformations. In order to tackle the aforementioned problems, this paper extends the Voxelmorph approach in three different ways. To improve the performance in case of small as well as large deformations, supervision of the model at different resolutions has been integrated using a multi-scale UNet. To support the network to learn and encode the minute structural co-relations of the given image-pairs, a self-constructing graph network (SCGNet) has been used as the latent of the multi-scale UNet - which can improve the learning process of the model and help the model to generalise better. And finally, to make the deformations inverse-consistent, cycle consistency loss has been employed. On the task of registration of brain MRIs, the proposed method achieved significant improvements over ANTs and VoxelMorph, obtaining a Dice score of 0.8013±0.0243 for intramodal and 0.6211±0.0309 for intermodal, while VoxelMorph achieved 0.7747±0.0260 and 0.6071±0.0510, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Medical imaging

Micdir: Multi-Scale Inverse-Consistent Deformable Image Registration Using Unetmss with Self-Constructing Graph Latent

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Chatterjee, Soumick Bajaj, Himanshi Siddiquee, Istiyak H. Subbarayappa, Nandish Bandi Simon, Steve Shashidhar, Suraj Bangalore Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Department of Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany German Center for Neurodegenerative Disease Magdeburg Germany Center for Behavioral Brain Sciences Magdeburg Germany Leibniz Institute for Neurobiology Magdeburg Germany

Image registration is the process of bringing different images into a common coordinate system - a technique widely used in various applications of computer vision, such as remote sensing, image retrieval, and most commonly in medical imaging. Deep Learning based techniques have been applied successfully to tackle various complex medical image processing problems, including medical image registration. Over the years, several image registration techniques have been proposed using deep learning. Deformable image registration techniques such as Voxelmorph have been successful in capturing finer changes and providing smoother deformations. However, Voxelmorph, as well as ICNet and FIRE, do not explicitly encode global dependencies (i.e. the overall anatomical view of the supplied image) and therefore can not track large deformations. In order to tackle the aforementioned problems, this paper extends the Voxelmorph approach in three different ways. To improve the performance in case of small as well as large deformations, supervision of the model at different resolutions have been integrated using a multi-scale UNet. To support the network to learn and encode the minute structural co-relations of the given image-pairs, a self-constructing graph network (SCGNet) has been used as the latent of the multi-scale UNet - which can improve the learning process of the model and help the model to generalise better. And finally, to make the deformations inverse-consistent, cycle consistency loss has been employed. On the task of registration of brain MRIs, the proposed method achieved significant improvements over ANTs and VoxelMorph, obtaining a Dice score of 0.8013±0.0243 for intramodal and 0.6211±0.0309 for intermodal, while VoxelMorph achieved 0.7747±0.0260 and0.6071±0.0510, respectively. © 2022, The Authors. All rights reserved.

关键词： Image registration

Assortative and preferential attachment lead to core-periphery networks

学校读者我要写书评

暂无评论

Physical Review Research 2023年第4期5卷 043287-043287页

作者： Javier Ureña-Carrión Fariba Karimi Gerardo Íñiguez Mikko Kivelä Department of Computer Science Aalto University School of Science 00076 Espoo Finland Faculty of Computer Science and Biomedical Engineering Graz University of Technology 8010 Graz Austria Network Inequality Group Complexity Science Hub 1080 Vienna Austria Department of Network and Data Science Central European University 1100 Vienna Austria Faculty of Information Technology and Communication Sciences Tampere University 33720 Tampere Finland Centro de Ciencias de la Complejidad Universidad Nacional Autonóma de México 04510 Mexico City Mexico

Core-periphery is a key feature of large-scale networks underlying a wide range of social, biological, and transportation phenomena. Nodes in the core have an influential position in the network, and thus, the periphery can be under structural disadvantage if the groups are aligned with external attributes such as gender or economic status. Despite its prevalence in empirical data, it is unclear whether core-periphery is a consequence of fundamental network evolution processes. While preferential attachment can create degree heterogeneity indistinguishable from core-periphery, it does not explain why cores and peripheries are aligned with some external node attribute, i.e., why specific groups of nodes gain dominance and become cores. We show that even small amounts of assortative attachment, e.g., homophily in social networks, can break the symmetric effect of preferential attachment and that the interplay of the two mechanisms leads to one of the groups emerging as a prominent core. A systematic analysis of the phase space of the proposed model reveals the levels of assortative and preferential attachment necessary for a group to become either core or periphery. We find that relative group size is significant, with minority groups typically having a disadvantage on becoming the core for similar assortative attachment levels among groups. We also find that growing networks are less prone to develop core-periphery than dynamically evolving networks and that these two network evolution mechanisms lead to different types of core-periphery structures. Analyzing five empirical networks, our findings suggest that core nodes are highly assortative, illustrating the potential of our model as a tool for designing and analyzing interventions on evolving networks.

关键词： Network evolution Network formation & growth Preferential attachment Real world networks Social networks Transportation networks Block models Evolving network models Preferential attachment models

Complex-valued neural networks to speed-up MR Thermometry during Hyperthermia using Fourier PD and PDUNet

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Khatun, Rupali Chatterjee, Soumick Bert, Christoph Wadepohl, Martin Ott, Oliver J. Semrau, Sabine Fietkau, Rainer Nürnberger, Andreas Gaipl, Udo S. Frey, Benjamin Department of Radiation Oncology Universitätsklinikum Erlangen Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen Germany Department of Radiation Oncology Universitätsklinikum Erlangen Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen Germany Comprehensive Cancer Centre Erlangen-EMN Erlangen Germany Data and Knowledge Engineering Group Faculty of Computer Science Otto von Guericke University Magdeburg Germany Genomics Research Centre Human Technopole Milan Italy Dr Sennewald Medizintechnik GmbH Munich Germany

Hyperthermia (HT) in combination with radio- and/or chemotherapy has become an accepted cancer treatment for distinct solid tumour entities. In HT, tumour tissue is exogenously heated to temperatures between 39 and 43 °C for 60 minutes. Temperature monitoring can be performed non-invasively using dynamic magnetic resonance imaging (MRI). However, the slow nature of MRI leads to motion artefacts in the images due to the movements of patients during image acquisition. By discarding parts of the data, the speed of the acquisition can be increased - known as undersampling. However, due to the invalidation of the Nyquist criterion, the acquired images might be blurry and can also produce aliasing artefacts. The aim of this work was, therefore, to reconstruct highly undersampled MR thermometry acquisitions with better resolution and with fewer artefacts compared to conventional methods. The use of deep learning in the medical field has emerged in recent times, and various studies have shown that deep learning has the potential to solve inverse problems such as MR image reconstruction. However, most of the published work only focuses on the magnitude images, while the phase images are ignored, which are fundamental requirements for MR thermometry. This work, for the first time, presents deep learning-based solutions for reconstructing undersampled MR thermometry data. Two different deep learning models have been employed here, the Fourier Primal-Dual network and the Fourier Primal-Dual UNet, to reconstruct highly undersampled complex images of MR thermometry. MR images of 44 patients with different sarcoma types who received HT treatment in combination with radiotherapy and/or chemotherapy were used in this study. The method reduced the temperature difference between the undersampled MRIs and the fully sampled MRIs from 1.3 °C to 0.6 °C in full volume and 0.49 °C to 0.06 °C in the tumour region for an acceleration factor of 10. Copyright © 2023, The Authors. All rights res

关键词： Chemotherapy

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Islam, Md Shofiqul Hasan, Khondokar Fida Sultana, Sunjida Uddin, Shahadat Lio', Pietro Quinn, Julian M.W. Moni, Mohammad Ali Faculty of Computing Universiti Malaysia Pahang Gambang Pahang Kuantan26300 Malaysia Lebuhraya Tun Razak Gambang Pahang Kuantan26300 Malaysia 2 George Street Brisbane4000 Australia Department of Computer Science and Engineering Islamic University Kushtia7600 Bangladesh School of Project Management Faculty of Engineering The University of Sydney Sydney Australia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Bone Research Group The Garvan Institute of Medical Research DarlinghurstNSW Australia Artificial Intelligence & Data Science School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St LuciaQLD4072 Australia

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach substantially reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise. © 2023, CC BY.

关键词： Electrocardiograms

Design of a Domain-Specific Metamodel for Industrial Business Process Management 8

学校读者我要写书评

暂无评论

Design of a Domain-Specific Metamodel for Industrial Busines...

8th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2019

作者： Utz, Wilfrid Research Group Knowledge Engineering University of Vienna Faculty of Computer Science Vienna Austria

ISBN: (纸本)9781728126272

Enterprises operate in fast-changing environments nowadays and experience the continuous need to adapt to changing circumstances and new strategical and technological developments. This observation impacts how enterprise information systems are analysed, designed, implemented and used. Focusing on the analysis and design phases, conceptual modelling methods in the field of enterprise architecture management experience a continuous evolution in research and practice. Existing methods are re-purposed for specific requirements, new methods are developed/evaluated in concrete industrial settings and coupling/integration techniques support holistic viewpoints. Nevertheless, current practices in the design and enactment of such methods, and more specifically their metamodels, are inefficient with respect to agile and iterative considerations. Within this paper, a novel design approach for modelling method engineering is discussed that builds on the notion of meta-models as conceptual structures. Syntactic and semantic operation on these structures aim to facilitate the design process following the design science research methodology. The approach is evaluated by introducing a case developed as part of the European research project GO0D MAN. In the context of the project an enterprise architecture metamodel has been designed, developed and deployed that supports an integrated viewpoint of conceptual model artefacts coupled with operational data visualisations to assess the effectiveness of design decisions. © 2019 IEEE.

关键词： Semantics

Automated Mobility Context Detection with Inertial Signals

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bevilacqua, Antonio Alcock, Lisa Caulfield, Brian Gazit, Eran Hansen, Clint Ireson, Neil Ifrim, Georgiana The Insight Centre for Data Analytics School of Computer Science University College Dublin Ireland The Insight Centre for Data Analytics School of Public Health Physiotherapy and Sports Science University College Dublin Ireland The Clinical Ageing Research Unit Faculty of Medical Sciences Newcastle University United Kingdom The Center for the Study of Movement Congnition and Mobility Department of Neurology Tel Aviv Sourasky Medical Center The Department of Neurology Kiel University Germany The Organisation Information and Knowledge Group Department of Computer Science University of Sheffield United Kingdom

Remote monitoring of motor functions is a powerful approach for health assessment, especially among the elderly population or among subjects affected by pathologies that negatively impact their walking capabilities. This is further supported by the continuous development of wearable sensor devices, which are getting progressively smaller, cheaper, and more energy efficient. The external environment and mobility context have an impact on walking performance, hence one of the biggest challenges when remotely analysing gait episodes is the ability to detect the context within which those episodes occurred. The primary goal of this paper is the investigation of context detection for remote monitoring of daily motor functions. We aim to understand whether inertial signals sampled with wearable accelerometers, provide reliable information to classify gait-related activities as either indoor or outdoor. We explore two different approaches to this task: (1) using gait descriptors and features extracted from the input inertial signals sampled during walking episodes, together with classic machine learning algorithms, and (2) treating the input inertial signals as time series data and leveraging end-to-end state-of-the-art time series classifiers. We directly compare the two approaches through a set of experiments based on data collected from 9 healthy individuals. Our results indicate that the indoor/outdoor context can be successfully derived from inertial data streams. We also observe that time series classification models achieve better accuracy than any other feature-based models, while preserving efficiency and ease of use. © 2022, CC BY-NC-SA.

关键词： Remote control

Computationally Efficient Approximations for Matrix-based Rényi's Entropy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gong, Tieliang Dong, Yuxin Yu, Shujian Dong, Bo The School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an710049 China The Machine Learning Group UiT - The Arctic University of Norway Department of Computer Science Vrije University Amsterdam Amsterdam Netherlands

The recently developed matrix-based Rényi's αorder entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi-definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution. This intriguing property makes this new information measurement widely adopted in multiple statistical inference and learning tasks. However, the computation of such quantity involves the trace operator on a PSD matrix G to power α (i.e., tr(Gα)), with a normal complexity of nearly O(n3), which severely hampers its practical usage when the number of samples (i.e., n) is large. In this work, we present computationally efficient approximations to this new entropy functional that can reduce its complexity to even significantly less than O(n2). To this end, we leverage the recent progress on Randomized Numerical Linear Algebra, developing Taylor, Chebyshev and Lanczos approximations to tr(Gα) for arbitrary values of α by converting it into a matrix-vector multiplication problem. We also establish the connection between the matrix-based Rényi's entropy and PSD matrix approximation, which enables exploiting both clustering and block low-rank structure of G to further reduce the computational cost. We theoretically provide approximation accuracy guarantees and illustrate the properties for different approximations. Large-scale experimental evaluations on both synthetic and real-world data corroborate our theoretical findings, showing promising speedup with negligible loss in accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chatterjee, Soumick Sciarra, Alessandro Dünnwald, Max Tummala, Pavan Agrawal, Shubham Kumar Jauhari, Aishwarya Kalra, Aman Oeltze-Jafra, Steffen Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany MedDigit Department of Neurology Medical Faculty University Hospital Magdeburg Germany German Center for Neurodegenerative Disease Magdeburg Germany Center for Behavioral Brain Sciences Magdeburg Germany Leibniz Institute for Neurobiology Magdeburg Germany

Expert interpretation of anatomical images of the human brain is the central part of neuro-radiology. Several machine learning-based techniques have been proposed to assist in the analysis process. However, the ML models typically need to be trained to perform a specific task, e.g., brain tumour segmentation or classification. Not only do the corresponding training data require laborious manual annotations, but a wide variety of abnormalities can be present in a human brain MRI - even more than one simultaneously, which renders a representation of all possible anomalies very challenging. Hence, a possible solution is an unsupervised anomaly detection (UAD) system that can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out-of-distribution samples. Such a technique can then be used to detect anomalies - lesions or abnormalities, for example, brain tumours, without explicitly training the model for that specific pathology. Several Variational Autoencoder (VAE) based techniques have been proposed in the past for this task. Even though they perform very well on controlled artificially simulated anomalies, many of them perform poorly while detecting anomalies in clinical data. This research proposes a compact version of the "context-encoding" VAE (ceVAE) model, combined with pre and post-processing steps, creating a UAD pipeline (StRegA), which is more robust on clinical data and shows its applicability in detecting anomalies such as tumours in brain MRIs. The proposed pipeline achieved a Dice score of 0.642±0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859±0.112 while detecting artificially induced anomalies, while the best performing baseline achieved 0.522 ±0.135 and 0.783 ±0.111, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Tumors