检索结果-内蒙古大学图书馆

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Aline A.S. Thomaz Jonathan A.S. Lima Cristiano J. Miosso Mylé ne C.Q. Farias Andrey S. Krylov Yong Ding Department of Electrical Engineering University of Brasilia (UnB) Brasilia Brazil Biomedical Engineering Graduate Program University of Brasilia (UnB) Brasilia Brazil Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia College of Information Science and Electronic Engineering Zhejiang University Zhejiang China

Magnetic Resonance Imaging (MRI) plays a major role in the diagnosis of several diseases. However, the acquisition of measurements in the k-space domain, which is the basis for image reconstruction, takes a long time compared to other imaging modalities and is comparatively costly. In this context, undersampled MRI reconstruction is an approach for decreasing the acquisition duration and the exam's final cost. With this objective, both Compressed Sensing (CS) and Deep Learning (DL) provide techniques for generating good quality MRI images from undersampled measurements. In this paper, we combine CS and DL methods in order to investigate the potential increase in image quality over each isolated approach. We use reconstructions from from highly undersampled MRI signals using two CS approaches, the L1 and total minimizations, as inputs to a U-Net. We also use, for comparison, the reconstructions from the same undersampled signals using L2 minimization, and also test them as inputs to a U-net. The goal is to evaluate whether the the U-Net can improve the results of the CS reconstructions after learning from degraded and original image pairs. Our experimental results suggest that the combination of L1 or TV minimization with U-Nets can improve reconstruction, in terms of objective image quality, over each technique used in isolation.

关键词： Image quality TV Magnetic resonance imaging Magnetic resonance Minimization Time measurement Sensors

来源：评论

学校读者我要写书评

暂无评论

Wait, but Tylenol is Acetaminophen… Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

arXiv

引用

arXiv 2024年

作者： Chen Gao, Mingye Sasse, Kuleen Hartvigsen, Tom Anthony, Brian Fan, Lizhou Aerts, Hugo Gallifant, Jack Bitterman, Danielle Program Mass General Brigham Harvard Medical School BostonMA United States Department of Radiation Oncology Brigham and Women’s Hospital Dana-Farber Cancer Institute BostonMA United States Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School BostonMA United States Massachusetts Institute of Technology CambridgeMA United States Johns Hopkins University BaltimoreMD United States Department of Data Science University of Virginia CharlottesvilleVA United States Radiology and Nuclear Medicine GROW & CARIM Maastricht University Netherlands

Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinformation that impacts human well-being. Objectives/Methods: We analyzed compliance to requests to generate misleading content about medications in settings where models know the request is illogical. We investigated whether in-context directions and instruction-tuning of LLMs to prioritize logical reasoning over compliance reduced misinformation risk. Results: While all frontier LLMs complied with misinformation requests, both prompt-based and parameter-based approaches can improve the detection of logic flaws in requests and prevent the dissemination of medical misinformation. Conclusion: Shifting LLMs to prioritize logic over compliance could reduce risks of exploitation for medical misinformation. © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unbiased Estimation Using a Class of Diffusion Processes

SSRN

引用

SSRN 2022年

作者： Ruzayqat, Hamza Beskos, Alexandros Crisan, Dan Jasra, Ajay Kantas, Nikolas Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Statistical Science University College London LondonWC1E 6BT United Kingdom Department of Mathematics Imperial College London LondonSW7 2AZ United Kingdom

We study the problem of unbiased estimation of expectations with respect to (w.r.t.) π a given, general probability measure on (Rd,B(Rd)) that is absolutely continuous with respect to a standard Gaussian measure. We focus on simulation associated to a particular class of diffusion processes, sometimes termed the Schrödinger-Föllmer Sampler, which is a simulation technique that approximates the law of a particular diffusion bridge process {Xt}t∈[0,1] on Rd, d ∈ N0. This latter process is constructed such that, starting at X0 = 0, one has X1 ∼ π. Typically, the drift of the diffusion is intractable and, even if it were not, exact sampling of the associated diffusion is not possible. As a result, [10, 15] consider a stochastic Euler-Maruyama scheme that allows the development of biased estimators for expectations w.r.t. π. We show that for this methodology to achieve a mean square error of O(Ε2), for arbitrary Ε > 0, the associated cost is O(Ε−5). We then introduce an alternative approach that provides unbiased estimates of expectations w.r.t. π, that is, it does not suffer from the time discretization bias or the bias related with the approximation of the drift function. We prove that to achieve a mean square error of O(Ε2), the associated cost is, with high probability, O(Ε−2|log(Ε)|2+δ), for any δ > 0. We implement our method on several examples including Bayesian inverse problems. © 2022, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Enrollment of underserved racial and ethnic populations in pediatric asthma clinical trials

引用

Journal of Allergy and Clinical Immunology: Global 2024年第4期3卷 100315页

作者： Geanacopoulos, Alexandra T. Wu, Ann Chen Bourgeois, Florence T. Peltz, Alon Walsh, Ryan Han, Amy Ong, Mei-Sing Division of Emergency Medicine Boston Children's Hospital Pediatric Therapeutics and Regulatory Science Initiative Computational Health Informatics Program Boston Children's Hospital Division of Child Health Research and Policy Harvard Medical School & Harvard Pilgrim Health Care Institute Department of Population Medicine Harvard Medical School & Harvard Pilgrim Health Care Institute Department of Pediatrics Harvard Medical School

Background: The existing data on enrollment trends of historically underserved racial and ethnic children in clinical trials are limited. Objective: We sought to evaluate documentation and representation of race and ethnicity in pediatric asthma clinical trials in the United States. Methods: This is a cross-sectional study of United States–based interventional trials studying pediatric asthma that were completed between 2008 and 2022 and registered on ***. Enrollment disparities were assessed by using the measure enrollment prevalence difference (EPD) (defined as the median difference between the proportion of participants enrolled and asthma prevalence in the US population by race and ethnicity). Results: Of the 67 trials reviewed, 53 (79.2%) and 36 (53.7%) reported on race and ethnicity at ***, respectively. Most participants were White (39.1%), Black (37.1%), or non-Hispanic (66.1%). Black, Hispanic, multiracial, and White children were enrolled in the expected proportions based on their contribution to asthma burden. However, American Indian or Alaska Native (AI/AN) (EPD = –1 [95% CI = –1 to –1]) and Asian children (EPD = –3 [95% CI = –3 to –3]) were underrepresented relative to disease burden in these respective groups. Fewer Black children were enrolled in drug or device trials (β = –0.80 [95% CI = –1.60 to –0.01]) than in other trials. Fewer Hispanic children were enrolled in early-phase than late-phase trials (β = –2.42 [95% CI = –3.66 to –1.19]). Conclusions: Enrollment in pediatric asthma trials conducted in the United States was commensurate with the demographics of children affected by asthma for most racial and ethnic groups, but American Indian or Alaska Native and Asian children were underrepresented. Concerted efforts are needed to promote inclusion of these underserved groups in future trials. © 2024 The Author(s)

关键词： Asthma disparities pediatric clinical trials

来源：评论

学校读者我要写书评

暂无评论

Flow and clogging of capillary droplets

arXiv

引用

arXiv 2024年

作者： Cheng, Yuxuan Lonial, Benjamin F. Sista, Shivnag Meer, David J. Hofert, Anisa Weeks, Eric R. Shattuck, Mark D. O'Hern, Corey S. Department of Physics Yale University New HavenCT06520 United States Department of Physics Emory University AtlantaGA30322 United States Benjamin Levich Institute Physics Department The City College of New York New YorkNY10031 United States Department of Mechanical Engineering and Materials Science Yale University New HavenCT06520 United States Program in Computational Biology and Bioinformatics Yale University New HavenCT06520 United States

Capillary droplets form due to surface tension when two immiscible fluids are mixed. We describe the motion of gravity-driven capillary droplets flowing through narrow constrictions and obstacle arrays in both simulations and experiments. Our new capillary deformable particle model recapitulates the shape and velocity of single oil droplets in water as they pass through narrow constrictions in microfluidic chambers. Using this experimentally validated model, we simulate the flow and clogging of single capillary droplets in narrow channels and obstacle arrays and find several important results. First, the capillary droplet speed profile is nonmonotonic as the droplet exits the narrow orifice, and we can tune the droplet properties so that the speed overshoots the terminal speed far from the constriction. Second, in obstacle arrays, we find that extremely deformable droplets can wrap around obstacles, which leads to decreased average droplet speed in the continuous flow regime and increased probability for clogging in the regime where permanent clogs form. Third, the wrapping mechanism causes the clogging probability in obstacle arrays to become nonmonotonic with surface tension Γ. At large Γ, the droplets are nearly rigid and the clogging probability is large since the droplets can not squeeze through the gaps between obstacles. With decreasing Γ, the clogging probability decreases as the droplets become more deformable. However, in the small-Γ limit, the clogging probability increases since the droplets are extremely deformable and wrap around the obstacles. The results from these studies are important for developing a predictive understanding of capillary droplet flows through complex and confined geometries. © 2024, CC BY.

关键词： Drop formation

来源：评论

学校读者我要写书评

暂无评论

A holistic exploration of the potentially recoverable redshift information of Stage IV galaxy surveys

arXiv

引用

arXiv 2024年

作者： Scott, Bryan R. Malz, Alex I. Sorba, Robert Northwestern University 1800 Sherman Ave 8th Floor EvanstonIL60201 United States LSST Discovery Alliance Data Science Fellowship Program United States McWilliams Center for Cosmology and Astrophysics Department of Physics Carnegie Mellon University United States Institute for Computational Astrophysics Saint Mary’s University 923 Robie Street HalifaxNSB3H 3C3 Canada

Extragalactic science and cosmology with Stage IV galaxy surveys will rely almost exclusively on redshift measurements derived solely from photometry, which are subject to systematic and statistical uncertainties with numerous analysis choices, such as that of an estimator and prior information and no universal solution. Single-survey photometric redshift estimates ought to be improved by combining data from multiple surveys, with common wisdom asserting that optical data benefits from additional infrared coverage but not from additional ultraviolet coverage. The degree of improvement for either case is not well-characterized and attempts to quantify it necessitate assumptions of a chosen estimator and its prior information. We apply an information theoretic metric of potentially recoverable redshift information to assess the impact of multi-survey photometry combinations without assuming an estimator nor priors in the context of the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) in the optical, Roman and Euclid Surveys in the infrared, and Cosmological Advanced Survey Telescope for Optical-UV Research (CASTOR) in the ultraviolet. We conclude that the addition of UV photometry can benefit redshift determination of certain galaxy populations, but that gain is tempered by their decreased chance of meeting detection criteria at higher wavelengths. We explore the spectral energy distribution (SEDs) of galaxies whose potentially recoverable redshift information is most impacted by additional photometry to provide a basis for future evaluation of which science cases may motivate which combinations. The holistic assessment approach we develop here is generic and may be applied to quantify the impact of combining photometric datasets, changing experimental design choices, including observing strategy optimization, and evaluating systematics mitigation procedures. © 2024, CC BY.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

A biomedically oriented automatically annotated twitter COVID-19 dataset

arXiv

引用

arXiv 2021年

作者： Hernandez, Luis Alberto Robles Callahan, Tiffany J. Banda, Juan M. Department of Computer Science Georgia State University AtlantaGA30303 United States Computational Bioscience Program University of Colorado Anschutz Medical Campus AuroraCO80045 United States

The use of social media data, like Twitter, for biomedical research has been gradually increasing over the years. With the COVID-19 pandemic, researchers have turned to more non-traditional sources of clinical data to characterize the disease in near-real time, study the societal implications of interventions, as well as the sequelae that recovered COVID-19 cases present (Long-). However, manually curated social media datasets are difficult to come by due to the expensive costs of manual annotation and the efforts needed to identify the correct texts. When datasets are available, they are usually very small and their annotations don't generalize well over time or to larger sets of documents. As part of the 2021 Biomedical Linked Annotation Hackathon, we release our dataset of over 120 million automatically annotated tweets for biomedical research purposes. Incorporating best-practices, we identify tweets with potentially high clinical relevance. We evaluated our work by comparing several SpaCy-based annotation frameworks against a manually annotated gold-standard dataset. Selecting the best method to use for automatic annotation, we then annotated 120 million tweets and released them publicly for future downstream usage within the biomedical domain. © 2021, CC BY-NC-SA.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

MoCab: A framework for the deployment of machine learning models across health information systems

引用

Computer Methods and programs in Biomedicine 2024年 255卷 108336页

作者： Kuo, Zhe-Ming Chen, Kuan-Fu Tseng, Yi-Ju Department of Information Management National Central University Taoyuan Taiwan College of Intelligent Computing Chang Gung University Taoyuan Taiwan Medical Statistics Research Center Chang Gung University Taoyuan Taiwan Department of Emergency Medicine Chang Gung Memorial Hospital Keelung Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Computational Health Informatics Program Boston Children's Hospital BostonMA United States

Background and Objective: Machine learning models are vital for enhancing healthcare services. However, integrating them into health information systems (HISs) introduces challenges beyond clinical decision making, such as interoperability and diverse electronic health records (EHR) formats. We proposed Model Cabinet Architecture (MoCab), a framework designed to leverage fast healthcare interoperability resources (FHIR) as the standard for data storage and retrieval when deploying machine learning models across various HISs, addressing the challenges highlighted by platforms such as EPOCH®, ePRISM®, KETOS, and others. Methods: The MoCab architecture is designed to streamline predictive modeling in healthcare through a structured framework incorporating several specialized parts. The Data Service Center manages patient data retrieval from FHIR servers. These data are then processed by the Knowledge Model Center, where they are formatted and fed into predictive models. The Model Retraining Center is crucial in continuously updating these models to maintain accuracy in dynamic clinical environments. The framework further incorporates Clinical Decision Support (CDS) Hooks for issuing clinical alerts. It uses Substitutable Medical Apps Reusable Technologies (SMART) on FHIR to develop applications for displaying alerts, prediction results, and patient records. Results: The MoCab framework was demonstrated using three types of predictive models: a scoring model (qCSI), a machine learning model (NSTI), and a deep learning model (SPC), applied to synthetic data that mimic a major EHR system. The implementations showed how MoCab integrates predictive models with health data for clinical decision support, utilizing CDS Hooks and SMART on FHIR for seamless HIS integration. The demonstration confirmed the practical utility of MoCab in supporting clinical decision making, validated by its application in various healthcare settings. Conclusions: We demonstrate MoCab's potential in

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

A Method for Automatic Generation of 3D Background Models Using Fractal Models and Genetic Algorithms

A Method for Automatic Generation of 3D Background Models Us...

引用

International Symposium on Computing and Networking Workshops (CANDARW)

作者： Kaito Watanabe Hirotaka Nakayama Atsushi Shiraki Tomoyoshi Ito Katsumi Hirata Naoto Hoshikawa Advanced Course General Engineering Program National Institute of Technology Oyama College Oyama Japan Center for Computational Astrophysics National Astronomical Observatory of Japan Mitaka Japan Graduate School of Engineering Chiba University Chiba Japan Department of Innovative Electrical and Electronic Engineering National Institute of Technology Oyama College Oyama Japan Graduate School of Science and Tecnology University of Tsukuba Tsukuba Japan

In recent years, 3DCG-related industries have grown rapidly and the demand for 3DCG content has increased. However, 3DCG production requires special skills and a lot of time. In particular, the creation of background data requires a lot of human resources at the production site because the data is huge and complex. Therefore, we propose an automatic creation system that generates 3D background data for 3DCG production. The proposed system consists of three functions: 3D model generation, generation parameter optimization, and fitness evaluation. The user inputs a landscape photograph as idea information into the system, and the system optimizes the generation parameters so that the 3D object shape approximates the input image. To evaluate the accuracy of the system's performance, we observe the optimization process and the 3D object output when a previously generated fractal image or landscape photos are input. Experimental results show that the system accurately optimizes the generation parameters and generates 3D objects that are almost identical to the shape of the fractal image. In addition, the parameters were also optimized with a certain degree of accuracy for landscape photographs for which no specific solution had been determined.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Narrative Sleep Reports Utilizing Portable Electroencephalogram Data Through ChatGPT

Automated Generation of Narrative Sleep Reports Utilizing Po...

引用

IEEE International Conference on Healthcare Informatics (ICHI)

作者： Saki Tsumoto Fusae Kawana Kazumasa Horie Minori Masaki Kei Nishida Kazuya Miyanishi Jaehoon Seol Morie Tominaga Takashi Amemiya Tetsuro Hiei Akihiro Tani Masaki Matsubara Atsuyuki Morishima Hiroyuki Kitagawa Masashi Yanagisawa Ph.D. Program in Humanics University of Tsukuba Tsukuba Japan Juntendo University Graduate School of Medicine Tokyo Japan Center for Computational Sciences (CCS) University of Tsukuba Tsukuba Japan Faculty of Health and Sports Sciences University of Tsukuba Tokyo Japan S ‘ UIMIN Inc Tokyo Japan Institute of Library Information and Media Science University of Tsukuba Tsukuba Japan International Institute for Integrative Sleep Medicine (WPI-IIIS)) University of Tsukuba Tsukuba Japan

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

Sleep is a very important activity, but many people do not know their own sleep conditions. A sleep test personalizes sleep quality assessment and detects potential sleep disorders by measuring biological signals. The rise in sleep-related issues has necessitated the development of automated testing methods. Machine learning plays a pivotal role in interpreting sleep data and determining sleep stages. However, the generation of detailed reports and tailored recommendations still demands expert intervention. Automating the report generation to provide personalized sleep insights is a crucial and desired step for the future of sleep healthcare. Recently emerged Generative AI, such as ChatGPT, has attracted considerable attention in recent years. It can generate new sentences and images from input data. In this study, we investigate the practicality and applicability of using ChatGPT to generate narrative sleep reports for sleep test. In our proposed method, GPT-4 receives the information about the sleep habits of the participants and the sleep assessment automatically summarized by the rule-based algorithm. In the evaluation, we used in-home sleep EEG data obtained from 100 subjects by S'UIMIN inc. The generated reports were evaluated by experienced technicians and physicians on a 5- point scale for medical correctness and appropriateness as informative reports. The results of the evaluation showed that 60 % of the reports were the acceptable or above range in both aspects. While more than half of the results were judged to be above the acceptable range, differences between the generative AI and humans were also identified. Whereas humans comment on semantically weighted important findings such as medication and subjective insomnia, ChatGPT tends to make broad, shallow and flat comments on the input data. These facts suggest that although practical report generation only using generative AI is at present not easy, generative AI is a promising tool for improving the ef

关键词： Sleep Generative AI Medical services Machine learning Chatbots Electroencephalography Quality assessment

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：