检索结果-内蒙古大学图书馆

Advances in artificial intelligence techniques drive the application of radiomics in the clinical research of hepatocellular carcinoma

学校读者我要写书评

暂无评论

iLIVER 2022年第1期1卷 49-54页

作者： Jingwei Wei Meng Niu Ouyang Yabo Yu Zhou Xiaoke Ma Xue Yang Hanyu Jiang Hui Hui Hongyi Cao Binwei Duan Hongjun Li Dawei Ding Jie Tian Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijing 100190China Beijing Key Laboratory of Molecular Imaging Beijing 100190China Department of Interventional Radiology The First Affiliated Hospital of China Medical UniversityShenyangLiaoning110000China Beijing YouAn Hospital Capital Medical UniversityBeijing Institute of HepatologyBeijing100069China School of Life Science and Technology Xidian UniversityXi'anChina School of Computer Science and Technology Xidian UniversityXi'anShaanxiChina Department of Radiology Beijing Youan HospitalCapital Medical UniverstiyBeijing100069China Department of Radiology West China HospitalSichuan UniversityChengduSichuan 610041China Department of Pathology College of Basic Medical ScienceChina Medical UniversityShenyangLiaoning110000China The Department of General Surgery Center Beijing YouAn HospitalCapital Medical UniversityChina School of Bioengineering Beihang UniversityBeijing100191China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine Beihang UniversityBeijing100191China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and TechnologyXidian UniversityXi'anShaanxi710126China

Hepatocellular carcinoma(HCC)remains the most common malignancy to threaten public health *** advances in artificial intelligence techniques,radiomics for HCC management provides a novel perspective to solve unmet needs in clinical settings,and reveals pixel-level radiological information for medical imaging big data,correlating the radiological phenotype with targeted clinical *** radiomics pipelines depend on handcrafted engineering features,and further deep learning-based radiomics pipelines are supplemented with deep features calculated via self-learning *** the past decade,radiomics has been widely applied in accurate diagnoses and pathological or biological behavior evaluation,as well as in prognosis *** this review,we systematically introduce the main pipelines of artificial intelligence-based radiomics and their efficacy in the clinical studies of HCC.

关键词： Artificial intelligence Diagnosis Hepatocellular carcinoma Prognosis Radiomics

Evaluation of Robustness Metrics for Defense of Machine Learning Systems

学校读者我要写书评

暂无评论

Evaluation of Robustness Metrics for Defense of Machine Lear...

International Conference on Military Communications and Information Systems (ICMCIS)

作者： J. DeMarchi R. Rijken J. Melrose B. Madahar G. Fumera F. Roli E. Ledda M. Aktaş F. Kurth P. Baggenstoss B. Pelzer L. Kanestad Collaborative Engineering Systems & Aerospace Systems Information Supremacy Royal Netherlands Aerospace Centre NLR Amsterdam NLD Cyber & Information Systems Division Defence Science and Technology Laboratory Portondown GBR Department of Electrical and Electronic Engineering University of Cagliari Cagliari ITA Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa ITA Department of Computer Control and Management Engineering Sapienza University of Rome Rome ITA Defence Systems Technologies Division ASELSAN Ankara TUR Fraunhofer Institute for Communication Information Processing and Ergonomics Bonn DEU Swedish Defence Research Agency Cyber Defence and C2 Technology Division Stockholm SWE

In this paper we explore some of the potential applications of robustness criteria for machine learning (ML) systems by way of tangible “demonstrator” scenarios. In each demonstrator, ML robustness metrics are applied to real-world scenarios with military relevance, indicating how they might be used to help detect and handle possible adversarial attacks on ML systems. We conclude by sketching promising future avenues of research in order to: (1) help establish useful verification methodologies to facilitate ML robustness compliance assessment; (2) support development of ML accountability mechanisms; and (3) reliably detect, repel, and mitigate adversarial attack.

关键词：

Ramsey envelope modulation in NV diamond magnetometry

学校读者我要写书评

暂无评论

Physical Review B 2022年第5期106卷 054110-054110页

作者： Jner Tzern Oon Jiashen Tang Connor A. Hart Kevin S. Olsson Matthew J. Turner Jennifer M. Schloss Ronald L. Walsworth Department of Physics University of Maryland College Park Maryland 20742 USA Quantum Technology Center University of Maryland College Park Maryland 20742 USA Department of Electrical Engineering and Computer Science University of Maryland College Park Maryland 20742 USA Intelligence Community Postdoctoral Research Fellowship Program University of Maryland College Park Maryland 20742 USA Lincoln Laboratory Massachusetts Institute of Technology Lexington Massachusetts 02421 USA

Nitrogen-vacancy (NV) spin ensembles in diamond provide an advanced magnetic sensing platform, with applications in both the physical and life sciences. The development of isotopically engineered NV15 diamond offers advantages over naturally occurring NV14 for magnetometry, due to its simpler hyperfine structure. However, for sensing modalities requiring a bias magnetic field not aligned with the sensing NV axis, the absence of a quadrupole moment in the N15 nuclear spin leads to pronounced envelope modulation effects in time-dependent measurements of NV15 spin evolution. While such behavior in spin echo experiments are well studied, analogous effects in Ramsey measurements and the implications for magnetometry remain underexplored. Here, we derive the modulated NV15 Ramsey response to a misaligned bias field, using a simple vector description of the effective magnetic field on the nuclear spin. The predicted modulation properties are then compared to experimental results, revealing significant magnetic sensitivity loss if unaddressed. We demonstrate that double-quantum coherences of the NV S=1 electronic spin states dramatically suppress these envelope modulations, while additionally proving resilient to other parasitic effects such as strain heterogeneity and temperature shifts.

关键词： NV centers Quantum metrology Quantum sensing Nitrogen vacancy centers in diamond Magnetization measurements Numerical approximation & analysis Perturbation theory

Imaging 3D Chemistry at 1 nm Resolution with Fused Multi-Modal Electron Tomography

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schwartz, Jonathan Di, Zichao Wendy Jiang, Yi Manassa, Jason Pietryga, Jacob Qian, Yiwen Cho, Min Gee Rowell, Jonathan L. Zheng, Huihuo Robinson, Richard D. Gu, Junsi Kirilin, Alexey Rozeveld, Steve Ercius, Peter Fessler, Jeffrey A. Xu, Ting Scott, Mary Hovden, Robert Department of Materials Science and Engineering University of Michigan Ann ArborMI United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL United States Advanced Photon Source Facility Argonne National Laboratory LemontIL United States Department of Material Science and Engineering Northwestern University EvanstonIL United States Department of Materials Science and Engineering University of California at Berkeley BerkeleyCA United States Department of Chemistry and Chemical Biology Cornell University IthacaNY United States Argonne Leadership Computing Facility Argonne National Laboratory LemontIL United States Department of Material Science and Engineering Cornell University IthacaNY United States Kavli Institute at Cornell for Nanoscale Science Cornell University IthacaNY United States Dow Chemical Co. MidlandMI United States National Center for Electron Microscopy Molecular Foundry Lawrence Berkeley National Laboratory BerkeleyCA United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States Materials Science Division Lawrence Berkeley National Laboratory BerkeleyCA United States Applied Physics Program University of Michigan Ann ArborMI United States

Measuring the three-dimensional (3D) distribution of chemistry in nanoscale matter is a longstanding challenge for metrological science. The inelastic scattering events required for 3D chemical imaging are too rare, requiring high beam exposure that destroys the specimen before an experiment completes. Even larger doses are required to achieve high resolution. Thus, chemical mapping in 3D has been unachievable except at lower resolution with the most radiation-hard materials. Here, high-resolution 3D chemical imaging is achieved near or below one nanometer resolution in a Au-Fe3O4 metamaterial, Co3O4 - Mn3O4 core-shell nanocrystals, and ZnS-Cu0.64S0.36 nanomaterial using fused multi-modal electron tomography. Multi-modal data fusion enables high-resolution chemical tomography often with 99% less dose by linking information encoded within both elastic (HAADF) and inelastic (EDX / EELS) signals. Now sub-nanometer 3D resolution of chemistry is measurable for a broad class of geometrically and compositionally complex materials. © 2023, CC BY.

关键词： Zinc sulfide

Label-free SARS-CoV-2 detection and classification using phase imaging with computational specificity

学校读者我要写书评

暂无评论

Light(science & Applications) 2021年第9期10卷 1797-1808页

作者： Neha Goswami Yuchen R.He Yu-Heng Deng Chamteut Oh Nahil Sobh Enrique Valera Rashid Bashir Nahed Ismail Hyunjoon Kong Thanh H.Nguyen Catherine Best-Popescu Gabriel Popescu Department of Bioengineering University of Illinois Urbana-ChampaignUrbanaIllinois61801USA Beckman Institute of Advanced Science and Technology University of Illinois Urbana-ChampaignUrbanaIllinois61801USA Department of Electrical and Computer Engineering University of Illinois Urbana-ChampaignUrbanaIllinois61801USA Department of Chemical and Biomolecular Engineering University of Illinois at Urbana-ChampaignUrbanaIL61801USA Department of Civil and Environmental Engineering University of Illinois at Urbana-ChampaignUrbanaIL61801USA NCSA Center for Artificial Intelligence Innovation University of Illinois at Urbana-ChampaignUrbanaIL61801USA Holonyak Micro and Nanotechnology Laboratory University of Illinois at Urbana-ChampaignUrbanaIllinois61801USA Biomedical Research Center Carle Foundation Hospital509W University Ave.UrbanaIllinois61801USA Carle Illinois College of Medicine 807 South Wright St.UrbanaIllinois61801USA Mayo-Illinois Alliance for Technology Based Healthcare UrbanaIllinois61801USA Department of Pathology College of MedicineUniversity of Illinois at ChicagoChicagoILUSA

Efforts to mitigate the COVID-19 crisis revealed that fast,accurate,and scalable testing is crucial for curbing the current impact and that of future *** propose an optical method for directly imaging unlabeled viral particles and using deep learning for detection and *** ultrasensitive interferometric method was used to image four virus types with nanoscale optical path-length *** these data with fluorescence images for ground truth,we trained semantic segmentation models based on U-Net,a particular type of convolutional neural *** trained network was applied to classify the viruses from the interferometric images only,containing simultaneously SARS-CoV-2,H1N1(influenza-A virus),HAdV(adenovirus),and ZIKV(Zika virus).Remarkably,due to the nanoscale sensitivity in the input data,the neural network was able to identify SARS-CoV-2 *** other viruses with 96%*** inference time for each image is 60 ms,on a common graphic-processing *** approach of directly imaging unlabeled viral particles may provide an extremely fast test,of less than a minute per *** the imaging instrument operates on regular glass slides,we envision this method as potentially testing on patient breath *** necessary high throughput can be achieved by translating concepts from digital pathology,where a microscope can scan hundreds of slides automatically.

关键词： testing neural hundreds

electrically Reconfigurable Intelligent Optoelectronics in 2-D van der Waals Materials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yu Zhang, Dehui Song, Yihao Lee, Jea Jung Tian, Meng Biswas, Souvik Xia, Fengnian Guo, Qiushi Photonics Initiative Advanced Science Research Center City University of New York 85 St Nicholas Terrace New YorkNY10031 United States Physics Program Graduate Center City University of New York 365 5th Ave New YorkNY10016 United States Department of Electrical Engineering and Computer Sciences University of California Berkeley 566 Cory Hall BerkeleyCA94720 United States Department of Electrical Engineering Yale University 15 Prospect St New HavenCT06511 United States E. L. Ginzton Laboratory Stanford University 348 Via Pueblo Mall StanfordCA94305 United States

In optoelectronics, achieving electrical reconfigurability is crucial as it enables the encoding, decoding, manipulating, and processing of information carried by light. In recent years, two-dimensional van der Waals (2-D vdW) materials have emerged as promising platforms for realizing reconfigurable optoelectronic devices. Compared to materials with bulk crystalline lattice, 2-D vdW materials offer superior electrical reconfigurability due to high surface-to-volume ratio, quantum confinement, reduced dielectric screening effect, and strong dipole resonances. Additionally, their unique band structures and associated topology and quantum geometry provide novel tuning capabilities. This review article seeks to establish a connection between the fundamental physics underlying reconfigurable optoelectronics in 2-D materials and their burgeoning applications in intelligent optoelectronics. We first survey various electrically reconfigurable properties of 2-D vdW materials and the underlying tuning mechanisms. Then we highlight the emerging applications of such devices, including dynamic intensity, phase and polarization control, and intelligent sensing. Finally, we discuss the opportunities for future advancements in this field. Copyright © 2025, The Authors. All rights reserved.

关键词： Van der Waals forces

Ensemble ranking: An aggregation of multiple multicriteria methods and scenarios and its application to power generation planning

学校读者我要写书评

暂无评论

Decision Analytics Journal 2024年 10卷

作者： Alves, Marcos Antonio Oliveira, Bruno Alberto Soares Guimarães, Frederico Gadelha Graduate Program in Electrical Engineering Av. Antônio Carlos 6627 MG Belo Horizonte 31270-901 Brazil FITec - Technological Innovations Av. Cristóvão Colombo 485 Funcionários MG Belo Horizonte 30140-150 Brazil Department of Computer Science Rua Reitor Píres Albuquerque ICEx MG Belo Horizonte 31270-901 Brazil

Evaluating maintenance plans for power generation is a critical task managed by the National System Operator, as it is directly related to criteria such as operational cost, rationing, and availability of natural resources. This study identifies the most suitable maintenance schedule between uncertainties related to solution ranking methods and future scenarios. We investigated the performance of various multicriteria decision-making methods, including the Analytic Hierarchy Process (AHP), TODIM ((an acronym in Portuguese for Interactive Multicriteria decision-making), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Vlse Kriterijumska Optimizacija Kompromisno Resenje (VIKOR), and Weighted Aggregated Sum Product ASsessment (WASPAS), in prioritizing maintenance plans across three scenarios. These included a scenario derived from an energy generation problem and two others based on variations in hydrology and energy demand parameters. The results analyze and discuss the similarities and differences in the rankings. Due to the lack of consensus among the methods regarding the optimal maintenance plan, we propose an ensemble ranking that considers an important factor for both the method and the scenario. The solution from the ensemble ranking, compared to the lowest-cost solution obtained in the optimization process, showed a slight cost increase of 0.32% and a 9.34% deviation from the base maintenance plan, yet it can deal with different uncertainties. The findings of this study can provide useful and robust information to energy stakeholders and serve as a reference for energy policy. © 2024 The Authors

关键词： Generation maintenance scheduling problems Hydrothermal dispatch Multicriteria decision-making Power generation planning Robust decision-making Uncertainty scenarios

Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rajendran, Suraj Pan, Weishen Sabuncu, Mert R. Chen, Yong Zhou, Jiayu Wang, Fei Tri-Institutional Computational Biology & Medicine Program Cornell University NY United States Division of Health Informatics Department of Population Health Sciences Weill Cornell Medicine New YorkNY United States School of Electrical and Computer Engineering Cornell University IthacaNY United States Cornell Tech New YorkNY United States Department of Radiology Weill Cornell Medical School New YorkNY United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania PhiladelphiaPA United States Department of Computer Science and Engineering Michigan State University East LansingMI United States

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows. © 2023, CC BY.

关键词： Data privacy

Efficient Noise Calculation in Deep Learning-based MRI Reconstructions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dalmaz, Onat Desai, Arjun D. Heckel, Reinhard Çukur, Tolga Chaudhari, Akshay S. Hargreaves, Brian A. Department of Electrical Engineering Stanford University StanfordCA United States Department of Radiology Stanford University StanfordCA United States Department of Computer Engineering Technical University of Munich Munich Germany Department of Electrical and Electronics Engineering Bilkent University Ankara Turkey Department of Biomedical Data Science Stanford University StanfordCA United States Department of Bioengineering Stanford University StanfordCA United States

Accelerated MRI reconstruction involves solving an ill-posed inverse problem where noise in acquired data propagates to the reconstructed images. Noise analyses are central to MRI reconstruction for providing an explicit measure of solution fidelity and for guiding the design and deployment of novel reconstruction methods. However, deep learning (DL)-based reconstruction methods have often overlooked noise propagation due to inherent analytical and computational challenges, despite its critical importance. This work proposes a theoretically grounded, memory-efficient technique to calculate voxel-wise variance for quantifying uncertainty due to acquisition noise in accelerated MRI reconstructions. Our approach approximates noise covariance using the DL network’s Jacobian, which is intractable to calculate. To circumvent this, we derive an unbiased estimator for the diagonal of this covariance matrix—voxel-wise variance—, and introduce a Jacobian sketching technique to efficiently implement it. We evaluate our method on knee and brain MRI datasets for both data- and physics-driven networks trained in supervised and unsupervised manners. Compared to empirical references obtained via Monte-Carlo simulations, our technique achieves near-equivalent performance while reducing computational and memory demands by an order of magnitude or more. Furthermore, our method is robust across varying input noise levels, acceleration factors, and diverse undersampling schemes, highlighting its broad applicability. Our work reintroduces accurate and efficient noise analysis as a central tenet of reconstruction algorithms, holding promise to reshape how we evaluate and deploy DL-based MRI. Our code will be made publicly available upon *** Codes 65C60, 94A08, 68T07 © 2025, CC BY-NC-ND.

关键词： Monte Carlo methods