检索结果-内蒙古大学图书馆

Asymmetric cascade networks for focal bone lesion prediction in multiple myeloma

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Licandro, Roxane Hofmanninger, Johannes Perkonigg, Matthias Roehrich, Sebastian Weber, Marc-Andr Wennmann, Markus Kintzele, Laurent Piraud, Marie Menze, Bjoern Langs, Georg Computer Vision Lab Department of Visual Computing and Human-centered Technologies TU Wien Austria Computational Imaging Research Lab Department of Biomedical Imaging and Image-guided Therapy Medical University of Vienna Austria Institute f. Diagn. u. Intervent. Radiologie Medizinische Universität Rostock Germany Department of Interventional and Diagnostic Radiology Section Musco-Skelatal Imaging Heidelberg University Germany Institute of Biomedical Engineering - Image-based biomedical modelling Technische Universitt Mnchen Germany

The reliable and timely stratification of bone lesion evolution risk in smoldering Multiple Myeloma plays an important role in identifying prime markers of the disease's advance and in improving the patients' outcome. In this work we provide an asymmetric cascade network for the longitudinal prediction of future bone lesions for T1 weighted whole body MR images. The proposed cascaded architecture, consisting of two distinct configured U-Nets, first detects the bone regions and subsequently predicts lesions within bones in a patch based way. The algorithm provides a full volumetric risk score map for the identification of early signatures of emerging lesions and for visualising high risk locations. The prediction accuracy is evaluated on a longitudinal dataset of 63 multiple myeloma patients. Keywords: Longitudinal prediction, asymmetric cascade U-Net, Multiple Myeloma, bone lesion assessment. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

Disability in space - What ESA should have aimed for

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Heinicke, Christiane Kaczmarzyk, Marcin Tannert, Benjamin Wasniowski, Aleksander Perycz, Malgorzata Schöning, Johannes Am Fallturm 2 Bremen28359 Germany Rzeszow University of Technology The Faculty of Civil and Environmental Engineering and Architecture Department of Building Engineering Poznańska Street 2 Rzeszow35-084 Poland Hochschule Bremen - City University of Applied Science Applied Media Informatics Flughafenallee 10 Bremen28199 Germany Space Is More ul. Mikulskiego 17 Wroclaw52-420 Poland Institute of Computer Science Polish Academy of Sciences Department of Artificial Intelligence Lab of Computational Biology Jana Kazimierza 5 st. Warsaw01-248 Poland University of Bremen Human-Computer Interaction Bibliothekstraße 5 Bremen28359 Germany

With announcing their "Parastronaut Feasibility Project", the European Space Agency ESA promises to make every reasonable effort to send astronauts with disability to space. This could spark hope in the 15% of all people who live with some form of disability. However, the fine-print of the announcement sets overly tight boundaries to "acceptable" disabilities, allowing only malformations that are expected to have a positive impact on the parastronaut's performance in space. By doing so, ESA is following decade-old traditions in space flight, with some inclusion for the sake of inclusion and public opinion. Instead of accommodating people with disabilities, ESA should send a strong signal for inclusion and truly challenge people with disabilities so they can and will tease out the best of their qualities. © 2021, CC BY.

关键词： Manned space flight

An Explainable Deep Neural Network Model Based on Multi-Granularity Co-Attention to Improve Prediction of Drug-Target Binding Affinity

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Lin, Yanmei Cao, Aiqing Deng, Lei Liao, Mingzhi Zhang, Ru Zhang, Hao Peng, Yuzhong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530001 China Guangxi Academy of Sciences Nanning530007 China School of Computer Science and Engineering Central South University Changsha410083 China Center of Bioinformatics College of Life Sciences Northwest A&F University Shaanxi Yangling712100 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518000 China Center for Applied Mathematics of Guangxi Nanning Normal University Nanning530100 China

The prediction of drug-target interactions is pivotal in modern new drug development and drug repositioning. Nonetheless, current methods for predicting drug-target interactions often lose essential molecular structure information during the modeling process, leading to low prediction accuracy. This work proposes rMolGIN, a novel graph neural network with residual connectivity for molecular feature learning. rMolGIN not only takes into account the differences in chemical bonding properties and atomic neighborhood interactions, but also captures global and local structural information of drug molecules. Furthermore, we propose a novel drug-target affinity model based on rMolGIN and deep neural networks, coupled with a multi-granularity co-attention mechanism called HMCoDTA to capture comprehensive structural insights from both drugs and proteins. The proposed innovative model allows for comprehensive insight into the structural relationships between drugs and proteins, facilitating a more accurate prediction of binding affinities. To validate the effectiveness of our proposed methods, we conducted extensive experiments on three benchmark datasets of drug-target binding affinity, comparing HMCoDTA against 19 state-of-the-art models. Notably, the results show that HMCoDTA outperforms existing methods, demonstrating the effectiveness and advantages of our model in predicting drug-target binding affinity. © 2024, The Authors. All rights reserved.

关键词： Prediction models

Deep Multi-Model Fusion for Single-Image Dehazing

学校读者我要写书评

暂无评论

Deep Multi-Model Fusion for Single-Image Dehazing

International Conference on computer vision (ICCV)

作者： Zijun Deng Lei Zhu Xiaowei Hu Chi-Wing Fu Xuemiao Xu Qing Zhang Jing Qin Pheng-Ann Heng South China University of Technology Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology CAS The Chinese University of Hong Kong State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Sun Yat-sen University The Hong Kong Polytechnic University CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology CAS

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

This paper presents a deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing. To do so, we first formulate the attentional feature integration module to maximize the integration of the convolutional neural network (CNN) features at different CNN layers and generate the attentional multi-level integrated features (AMLIF). Then, from the AMLIF, we further predict a haze-free result for an atmospheric scattering model, as well as for four haze-layer separation models, and then fuse the results together to produce the final haze-free image. To evaluate the effectiveness of our method, we compare our network with several state-of-the-art methods on two widely-used dehazing benchmark datasets, as well as on two sets of real-world hazy images. Experimental results demonstrate clear quantitative and qualitative improvements of our method over the state-of-the-arts.

关键词： Atmospheric modeling Predictive models Scattering Computational modeling Neural networks computer vision Solid modeling

Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kossen, Tabea Subramaniam, Pooja Madai, Vince I. Hennemuth, Anja Hildebrand, Kristian Hilbert, Adam Sobesky, Jan Livne, Michelle Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar CLAIM - Charité Lab for AI in Medicine Charité Universitätsmedizin Berlin Germany Department of Computer Engineering and Microelectronics Computer Vision & Remote Sensing Technical University Berlin Berlin Germany Department of Electrical Engineering and Computer Science Technical University of Berlin Berlin Germany School of Computing and Digital Technology Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine Charité Universitätsmedizin Berlin Berlin Germany Fraunhofer MEVIS Bremen Germany Department VI Computer Science and Media Beuth University of Applied Sciences Berlin Germany Johanna-Etienne-Hospital Neuss Germany Centre for Stroke Research Berlin Charité Universitätsmedizin Berlin Berlin Germany Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Mind Brain Body Institute Berlin School of Mind and Brain Humboldt University Berlin Berlin Germany Berlin Institute of Health Berlin Germany

Anonymization and data sharing are crucial for privacy protection and acquisition of large datasets for robust medical image analysis. This represents a major challenge, especially for brain imaging research. Here, the unique structure of brain images allows for potential re-identification and thus requires anonymization beyond conventional methods. Generative adversarial networks (GANs) have the potential to provide anonymous images while maintaining their predictive properties. Analyzing brain vessel segmentation as a use case, we trained 3 GAN architectures on time-of-flight (TOF) magnetic resonance angiography (MRA) patches of patients with cerebrovascular disease for image-label pair generation: 1) Deep convolutional GAN, 2) Wasserstein-GAN with gradient penalty (WGAN-GP) and 3) WGAN-GP with spectral normalization (WGAN-GP-SN). First, the synthesized image-labels from each GAN architecture were used to train a U-net for vessel segmentation. The U-nets were then tested on real patient data. In total, 66 patients were used for this analysis. In a second step, we simulated the application of our synthetic patches in a transfer learning approach using a second, independent dataset. Here, for an increasing number of up to 15 patients we evaluated vessel segmentation model performance on real data with and without pre-training on generated patches. Finally, performance for all models was assessed by the Dice Similarity Coefficient (DSC) and the 95th percentile of the Hausdorff Distance (95HD). Comparing the 3 GAN architectures, the U-net model trained on synthetic data generated by the WGAN-GP-SN showed the highest performance to predict brain vessels (DSC/95HD 0.82/28.97) benchmarked by the U-net trained on real data (0.89/26.61). The transfer learning approach showed superior performance for the same GAN architecture compared to no pre-training, especially for one labeled patient only (DSC/95HD 0.91/25.68 compared to DSC/95HD 0.85/27.36). In a brain imaging segment

关键词： Image segmentation

Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chatterjee, Soumick Saad, Fatima Sarasaen, Chompunuch Ghosh, Suhita Krug, Valerie Khatun, Rupali Mishra, Rahul Desai, Nirja Radeva, Petia Rose, Georg Stober, Sebastian Speck, Oliver Nürnberger, Andreas Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Faculty of Computer Science Otto von Guericke University Magdeburg Germany Genomics Research Centre Human Technopole Italy Institute for Medical Engineering Otto von Guericke University Magdeburg Germany Research Campus STIMULATE Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany Artificial Intelligence Lab Otto von Guericke University Magdeburg Germany Department of Mathematics and Computer Science University of Barcelona Barcelona Spain Translational Radiobiology Department of Radiation Oncology Universitätsklinikum Erlangen Erlangen Germany Apollo Hospitals Bilaspur India HCG Cancer Centre Vadodara India Computer Vision Centre Cerdanyola Barcelona Spain Centre for Behavioural Brain Sciences Magdeburg Germany German Centre for Neurodegenerative Diseases Magdeburg Germany

The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing infected patients. Medical imaging, such as X-ray and Computed Tomography (CT), combined with the potential of Artificial Intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2 and DenseNet161) and their ensemble, using majority voting have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods - occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT, and using a global technique - neuron activation profiles. The mean Micro-F1 score of the models for COVID-19 classifications ranges from 0.66 to 0.875, and is 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model. Copyright © 2020, The Authors. All rights reserved.

关键词： COVID-19

Voxel-wise classification for porosity investigation of additive manufactured parts with 3D unsupervised and (deeply) supervised neural networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Iuso, Domenico Chatterjee, Soumick Cornelissen, Sven Verhees, Dries De Beenhouwer, Jan Sijbers, Jan Imec-Vision Lab Department of Physics University of Antwerp Antwerp2610 Belgium Faculty of Computer Science Otto von Guericke University Street Magdeburg39106 Germany Genomics Research Centre Human Technopole V.le Rita Levi-Montalcini 1 Milan20157 Italy Materialise NV. Technologielaan 15 Leuven3001 Belgium Flanders Make vzw. Oude Diestersebaan 133 Lommel3920 Belgium DynXlab Center for 4D Quantitative X-ray Imaging and Analysis Antwerp2610 Belgium

Additive Manufacturing (AM) has emerged as a manufacturing process that allows the direct production of samples from digital models. To ensure that quality standards are met in all manufactured samples of a batch, X-ray computed tomography (X-CT) is often used combined with automated anomaly detection. For the latter, deep learning (DL) anomaly detection techniques are increasingly, as they can be trained to be robust to the material being analysed and resilient towards poor image quality. Unfortunately, most recent and popular DL models have been developed for 2D image processing, thereby disregarding valuable volumetric information. This study revisits recent supervised (UNet, UNet++, UNet 3+, MSS-UNet) and unsupervised (VAE, ceVAE, gmVAE, vqVAE) DL models for porosity analysis of AM samples from X-CT images and extends them to accept 3D input data with a 3D-patch pipeline for lower computational requirements, improved efficiency and generalisability. The supervised models were trained using the Focal Tversky loss to address class imbalance that arises from the low porosity in the training datasets. The output of the unsupervised models is post-processed to reduce misclassifications caused by their inability to adequately represent the object surface. The findings were cross-validated in a 5-fold fashion and include: a performance benchmark of the DL models, an evaluation of the post-processing algorithm, an evaluation of the effect of training supervised models with the output of unsupervised models. In a final performance benchmark on a test set with poor image quality, the best performing supervised model was UNet++ with an average precision of 0.751 ± 0.030, while the best unsupervised model was the post-processed ceVAE with 0.830 ± 0.003. The VAE/ceVAE models demonstrated superior capabilities, particularly when leveraging post-processing techniques. © 2023, CC BY-NC-ND.

关键词： 3D printing

Response to Escobedo et al

学校读者我要写书评

暂无评论

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America 2018年第3期67卷 481页

作者： Karlyn D Beer Sarah A Collier Fan Du Julia W Gargano Division of Foodborne Waterborne and Environmental Diseases Centers for Disease Control and Prevention Atlanta Georgia. Human-Computer Interaction Lab University of Maryland College Park. Division of Viral Diseases Centers for Disease Control and Prevention Atlanta Georgia.

Erratum to: Presence and digital tourism

学校读者我要写书评

暂无评论

AI & SOCIETY 2014年第4期29卷 531-531页

作者： Benyon, David Quigley, Aaron O’Keefe, Brian Riva, Giuseppe Centre for Interaction Design Edinburgh Napier University Edinburgh Scotland UK SACHI St Andrews Computer Human Interaction University of St Andrews St Andrews Scotland UK GCCIS School of Informatics Rochester Institute of Technology Rochester USA Communication and Ergonomics of NEw Technologies Lab—ICE NET Lab Università Cattolica del Sacro Cuore Milan Italy Applied Technology for Neuro-Psychology Lab Istituto Auxologico Italiano Milan Italy