检索结果-内蒙古大学图书馆

Towards Fast and Light-Weight Restoration of Dark Images 31

学校读者我要写书评

暂无评论

Towards Fast and Light-Weight Restoration of Dark Images

31st British Machine Vision Conference, BMVC 2020

作者： Lamba, Mohit Balaji, Atul Mitra, Kaushik Computational Imaging Lab Dept. of Electrical Engineering Indian Institute of Technology Madras Chennai India

The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. State-of-the-art algorithms on dark image enhancement need to pre-amplify the image before processing it. However, they generally use ground truth information to find the amplification factor even during inference, restricting their applicability for unknown scenes. In contrast, we propose a simple yet effective light-weight mechanism for automatically determining the amplification factor from the input image. We show that we can enhance a full resolution, 2848 × 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 − 7× fewer model parameters, 2 − 3× lower memory utilization, 5 − 20× speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms. © 2020. The copyright of this document resides with its author

关键词： Image enhancement

Anomalous Hall optical conductivity in tilted topological nodal-line semimetals

学校读者我要写书评

暂无评论

Physical Review B 2021年第16期103卷 165104-165104页

作者： Chen Wang Wen-Hui Xu Chang-Yong Zhu Jin-Na Chen Yong-Long Zhou Ming-Xun Deng Hou-Jian Duan Rui-Qiang Wang Lab for Computational Imaging Technology and Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210023 China Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials School of Physics and Telecommunication Engineering South China Normal University Guangzhou 510006 China

Nodal-line semimetals are typically characterized by a nodal ring, a closed line of Dirac points in the Brillouin zone, whose topology is characterized by a quantized Berry phase. The nodal loop is protected by the combined inversion and time-reversal (PT) symmetry in the absence of spin-orbit coupling, exhibiting the parity anomaly. Introduction of the PT-break mass term can lead to the transverse Hall response at each point in the nodal ring, but the net Hall current vanishes due to the existence of inversion-symmetry points that contribute to the transverse current with opposite signs. We show that the combination of an inversion-broken tilt term and finite Fermi energy can cause the nonzero anomalous Hall effect. We explore the DC and AC anomalous Hall conductivity in tilted nodal-line semimetals using Kubo formula and focus on the contribution of the free carriers to the Hall conductivity. We find that the interband transition of free carriers dominates the nonvanishing dynamic Hall conductivity over the filled band contribution. The resulting anomalous Hall conductivity exhibits the parity anomaly for the DC case, and rich characteristic frequencies for the AC case which is closely related to the change of the geometry of the Fermi surface. These features may serve as a diagnostic tool to characterize the topological property, tilting parameter, or the radius of the nodal line.

关键词： Electrical conductivity Optical conductivity Topological materials Node-line semimetals

Physics-Informed DeepMRI: Bridging the Gap from Heat Diffusion to k-Space Interpolation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cui, Zhuo-Xu Liu, Congcong Fan, Xiaohong Cao, Chentao Cheng, Jing Zhu, Qingyong Liu, Yuanyuan Jia, Sen Zhou, Yihang Wang, Haifeng Zhu, Yanjie Zhang, Jianping Liu, Qiegen Liang, Dong Research Center for Medical AI Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China School of mathematics and computational science Xiangtan University Xiangtan China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China National Innovation Center for Advanced Medical Devices Shenzhen China Department of Electronic Information Engineering Nanchang University Nanchang China Pazhou Lab Guangzhou China

In the field of parallel imaging (PI), alongside image-domain regularization methods, substantial research has been dedicated to exploring k-space interpolation. However, the interpretability of these methods remains an unresolved issue. Furthermore, these approaches currently face acceleration limitations that are comparable to those experienced by image-domain methods. In order to enhance interpretability and overcome the acceleration limitations, this paper introduces an interpretable framework that unifies both k-space interpolation techniques and image-domain methods, grounded in the physical principles of heat diffusion equations. Building upon this foundational framework, a novel k-space interpolation method is proposed. Specifically, we model the process of high-frequency information attenuation in k-space as a heat diffusion equation, while the effort to reconstruct high-frequency information from low-frequency regions can be conceptualized as a reverse heat equation. However, solving the reverse heat equation poses a challenging inverse problem. To tackle this challenge, we modify the heat equation to align with the principles of magnetic resonance PI physics and employ the score-based generative method to precisely execute the modified reverse heat diffusion. Finally, experimental validation conducted on publicly available datasets demonstrates the superiority of the proposed approach over traditional k-space interpolation methods, deep learning-based k-space interpolation methods, and conventional diffusion models in terms of reconstruction accuracy, particularly in high-frequency regions. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

Towards fast and light-weight restoration of dark images 202

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lamba, Mohit Balaji, Atul Mitra, Kaushik Computational Imaging Lab Dept. of Electrical Engineering Indian Institute of Technology Madras Chennai India

关键词： Image reconstruction

High-spatial-resolution ultrafast framing imaging at 15 trillion frames per second by optical parametric amplification

学校读者我要写书评

暂无评论

Advanced Photonics 2020年第5期2卷 53-63页

作者： Xuanke Zeng Shuiqin Zheng Yi Cai Qinggang Lin Jinyang Liang Xiaowei Lu Jingzhen Li Weixin Xie Shixiang Xu Shenzhen University College of Physics and Optoelectronic EngineeringShenzhen Key Lab of Micro-Nano Photonic Information TechnologyShenzhenChina Shenzhen University College of Electronic Information EngineeringShenzhenChina Institut National de la Recherche Scientifique CentreÉnergie Matériaux TélécommunicationsLaboratory of Applied Computational ImagingVarennesQuébecCanada

We report a framing imaging based on noncollinear optical parametric amplification(NCOPA),named FINCOPA,which applies NCOPA for the first time to single-shot ultrafast optical *** an experiment targeting a laser-induced air plasma grating,FINCOPA achieved 50 fs-resolved optical imaging with a spatial resolution of^83 lp∕mm and an effective frame rate of 10 trillion frames per second(Tfps).It has also successfully visualized an ultrafast rotating optical field with an effective frame rate of 15 *** has simultaneously a femtosecond-level temporal resolution and frame interval and a micrometer-level spatial *** outstanding spatial and temporal resolutions with an ultrahigh frame rate,FINCOPA will contribute to high-spatiotemporal resolution observations of ultrafast transient events,such as atomic or molecular dynamics in photonic materials,plasma physics,and laser inertial-confinement fusion.

关键词： ultrafast imaging spatiotemporal resolution frame rate noncollinear optical parametric amplification

Radiomics-enhanced prediction of Constant-Murley scores following ultrasound-guided percutaneous irrigation of calcific tendinopathy

学校读者我要写书评

暂无评论

European Journal of Radiology Artificial Intelligence

European Journal of Radiology Artificial Intelligence 2025年 2卷 100019-100019页

作者： Matthaios Triantafyllou Evangelia E. Vassalou Alexia Maria Goulianou Theodoros H. Tosounidis Kostas Marias Apostolos H. Karantanas Michail E. Klontzas Artificial Intelligence and Translational Imaging (ATI) Lab Department of Radiology School of Medicine University of Crete Voutes Campus Heraklion Greece Department of Medical Imaging University Hospital of Heraklion Heraklion Crete Greece Department of Orthopaedic Surgery University Hospital Heraklion Heraklion Crete 71500 Greece Computational BioMedicine Laboratory Institute of Computer Science Foundation for Research and Technology (FORTH) Heraklion Crete Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Crete Greece Division of Radiology Department for Clinical Science Intervention and Technology (CLINTEC) Karolinska Institutet Stockholm Sweden

Objective Calcific tendinopathy of the rotator cuff presents challenges in symptom management and functional recovery with image-guided treatment. This study aimed to develop a regression model integrating radiomic and clinical features to predict 1-year Constant-Murley Score (CMS) improvement following ultrasound-guided percutaneous irrigation of calcific tendinopathy (US-PICT). Materials and Methods This retrospective study included 84 patients undergoing US-PICT between 2017 and 2019. Advanced Contrast Limited Adaptive Histogram Equilization (CLAHE) preprocessing was applied to US images for radiomic feature extraction. Manual segmentation of calcifications yielded 849 features, later refined to 6 predictive features through inter-rater ICC analysis, correlation filtering, and Recursive Feature Elimination (RFE). Clinical variables, including age, calcification type, and maximum diameter, were integrated. Model performance was evaluated using R 2 , MAE, RMSE, calibration curves, and SHAP analysis, while decision curve analysis assessed clinical utility. Results The regression model achieved an R 2 of 0.66 (95 % CI: 0.52–0.76) with an RMSE of 8.26. Younger age, larger calcifications, and fluid-like consistency correlated with greater CMS improvement (p < 0.001). SHAP analysis identified calcification type, age, and radiomic features as key predictors. Calibration curves demonstrated reasonable alignment between predictions and observed outcomes, while decision curve analysis highlighted the model’s clinical utility. Conclusion Radiomics combined with clinical features provides robust predictions of 1-year functional improvement after US-PICT. Further validation in larger cohorts is warranted to refine and generalize these findings.

关键词： Radiomics Calcific Tendinopathy/(US-PICT) Machine Learning Artificial Intelligence Shoulder

A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Jingang Su, Runmu Fu, Qiang Ren, Wenqi Heide, Felix Nie, Yunfeng School of Future Technology University of Chinese Academy of Sciences Beijing100039 China School of Computer Science and Technology Xidian University Xi’an710071 China King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Computational Imaging Lab Princeton University PrincetonNJ08544 United States Department of Applied Physics and Photonics Vrije Universiteit Brussel Brussels1050 Belgium

Hyperspectral imaging enables many versatile applications for its competence in capturing abundant spatial and spectral information, which is crucial for identifying substances. However, the devices for acquiring hyperspectral images are typically expensive and very complicated, hindering the promotion of their application in consumer electronics, such as daily food inspection and point-of-care medical screening, etc. Recently, many computational spectral imaging methods have been proposed by directly reconstructing the hyperspectral information from widely available RGB images. These reconstruction methods can exclude the usage of burdensome spectral camera hardware while keeping a high spectral resolution and imaging performance. We present a thorough investigation of more than 25 state-of-the-art spectral reconstruction methods which are categorized as prior-based and data-driven methods. Simulations on open-source datasets show that prior-based methods are more suitable for rare data situations, while data-driven methods can unleash the full potential of deep learning in big data cases. We have identified current challenges faced by those methods (e.g., loss function, spectral accuracy, data generalization) and summarized a few trends for future work. With the rapid expansion in datasets and the advent of more advanced neural networks, learnable methods with fine feature representation abilities are very promising. This comprehensive review can serve as a fruitful reference source for peer researchers, thus paving the way for the development of computational hyperspectral imaging. Copyright © 2021, The Authors. All rights reserved.

关键词： Hyperspectral imaging

Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks

学校读者我要写书评

暂无评论

Medical Image Analysis 2022年 78卷 102396-102396页

作者： Subramaniam, Pooja Kossen, Tabea Ritter, Kerstin Hennemuth, Anja Hildebrand, Kristian Hilbert, Adam Sobesky, Jan Livne, Michelle Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar Madai, Vince I. 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 Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine Charité Universitätsmedizin Berlin Berlin Germany Fraunhofer MEVIS Max-von-Laue-Str. 2 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 School of Computing and Digital Technology Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom QUEST-Center for Transforming Biomedical Research Berlin Institute of Health Charité Universitätsmedizin Berlin Charitéplatz 1 Berlin10117 Germany

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark

关键词： Generative adversarial networks

Mitosis domain generalization in histopathology images - The MIDOG challenge

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Aubreville, Marc Stathonikos, Nikolas Bertram, Christof A. Klopfleisch, Robert ter Hoeve, Natalie Ciompi, Francesco Wilm, Frauke Marzahl, Christian Donovan, Taryn A. Maier, Andreas Breen, Jack Ravikumar, Nishant Chung, Youjin Park, Jinah Nateghi, Ramin Pourakpour, Fattaneh Fick, Rutger H.J. Hadj, Saima Ben Jahanifar, Mostafa Rajpoot, Nasir Dexl, Jakob Wittenberg, Thomas Kondo, Satoshi Lafarge, Maxime W. Koelzer, Viktor H. Liang, Jingtang Wang, Yubo Long, Xi Liu, Jingxin Razavi, Salar Khademi, April Yang, Sen Wang, Xiyue Veta, Mitko Breininger, Katharina Technische Hochschule Ingolstadt Ingolstadt Germany Pathology Department UMC Utrecht Netherlands Institute of Pathology University of Veterinary Medicine Vienna Austria Institute of Veterinary Pathology Freie Universität Berlin Berlin Germany Computational Pathology Group Radboud UMC Nijmegen Netherlands Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Department of Anatomic Pathology Schwarzman Animal Medical Center New York United States CISTIB Center for Computational Imaging and Simulation Technologies in Biomedicine School of Computing University of Leeds United Kingdom Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Electrical and Electronics Engineering Department Shiraz University of Technology Shiraz Iran Tehran Iran Tribun Health Paris France Tissue Image Analytics Centre Department of Computer Science University of Warwick United Kingdom Fraunhofer-Institute for Integrated Circuits IIS Erlangen Germany Muroran Institute of Technology Hokkaido Japan Department of Pathology and Molecular Pathology University Hospital University of Zurich Zurich Switzerland School of Life Science and Technology Xidian University Shannxi China Histo Pathology Diagnostic Center Shanghai China Xi'an Jiaotong-Liverpool University Suzhou China Electrical Computer and Biomedical Engineering Ryerson University TorontoON Canada Tencent AI Lab Shenzhen518057 China College of Computer Science Sichuan University Chengdu610065 China Medical Image Analysis Group TU Eindhoven Netherlands Department of Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

The density of mitotic figures within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of mitotic figures by pathologists is known to be subject to a strong inter-rater bias, which limits the prognostic value. State-of-the-art deep learning methods can support the expert in this assessment but are known to strongly deteriorate when applied in a different clinical environment than was used for training. One decisive component in the underlying domain shift has been identified as the variability caused by using different whole slide scanners. The goal of the MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that counter this domain shift and derive scanner-agnostic mitosis detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As a test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were given. The best approaches performed on an expert level, with the winning algorithm yielding an F1 score of 0.748 (CI95: 0.704-0.781). In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Scanning