检索结果-内蒙古大学图书馆

Use of assisted reproductive technologies for male and female infertility and perinatal outcomes

学校读者我要写书评

暂无评论

Fertility and Sterility 2025年

作者： Magnus, Maria C. Skåra, Karoline H. Carlsen, Ellen Ø. Gjerdevik, Miriam Ramlau-Hansen, Cecilia H. Myrskylä, Mikko Romundstad, Liv-Bente Håberg, Siri E. Centre for Fertility and Health Norwegian Institute of Public Health Oslo Norway Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Public Health Research Unit for Epidemiology Aarhus University Aarhus Denmark Max Planck Institute for Demographic Research Rostock Germany Helsinki Institute for Demography and Population Health University of Helsinki Helsinki Finland Max Planck-University of Helsinki Center for Social Inequalities in Population Health Rostock Germany Spiren Fertility Clinic Trondheim Norway Department of Global Public Health and Primary Care University of Bergen Bergen Norway

Objective: To compare adverse perinatal outcomes between naturally conceived and pregnancies conceived by assisted reproductive technologies (ARTs) according to underlying male, female, or unexplained infertility. Design: Registry-based study. Subjects: All singleton births in Norway between 2000 and 2021 recorded in the national birth registry. Exposure: We compared ART pregnancies with underlying male (N = 9,957), female (N = 10,031), mixed (N = 3,287), or unexplained (N = 7,178) infertility with naturally conceived pregnancies (N = 1,210,709). Information on underlying causes of infertility was reported from fertility clinics. Main Outcomes and Measures: We compared the birthweight and pregnancy length using robust linear regression, and the risk of pre-eclampsia, cesarean section, stillbirth, preterm birth, low birth weight, small-for-gestational age and transfer to neonatal unit using logistic regression, adjusting for parental age, maternal parity, cohabitation, country of birth, and year of delivery. Results: Pregnancy length and birthweight were lower in all ART groups compared with the naturally conceived. The shorter pregnancy length was less pronounced in ART deliveries resulting from male infertility (adjusted difference −1.24 days;95% confidence interval [CI]: −1.43 to −1.05) than in ART deliveries resulting from female infertility (adjusted difference −1.92 days;95% CI: −2.12 to −1.73). Similarly, the lower birthweight in ART deliveries was less pronounced in those resulting from male (adjusted difference −29 grams;95% CI: −39 to −18) than those resulting from female (adjusted difference −49 grams;95% CI: −59 to −39) infertility. We also observed a higher risk of most adverse perinatal outcomes in all ART groups, with the magnitude being lower for ART deliveries resulting from male infertility. Conclusion: The increased risk of adverse perinatal outcomes in pregnancies conceived by ART was less pronounced if used for male infertility than for female in

关键词： Assisted reproductive technologies infertility perinatal outcomes

TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Rui-Jie Zhang, Malu Zhao, Qihang Deng, Haoyu Duan, Yule Deng, Liang-Jian Department of Electrical Computer Engineering University of California Santa CruzCA United States School of Public Affairs and Administration University of Electronic Science and Technology of China Chengdu China The University of Electronic Science and Technology of China China The Kuaishou Technology Beijing China

Spiking Neural Networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatio-temporal information representation ability. Given the critical role of attention mechanisms in enhancing neural network performance, the integration of SNNs and attention mechanisms exhibits tremendous potential to deliver energy-efficient and high-performance computing paradigms. In this paper, we present a novel Temporal-Channel Joint Attention mechanism for SNNs, referred to as TCJA-SNN. The proposed TCJA-SNN framework can effectively assess the significance of spike sequence from both spatial and temporal dimensions. More specifically, our essential technical contribution lies on: 1) We employ the squeeze operation to compress the spike stream into an average matrix. Then, we leverage two local attention mechanisms based on efficient 1-D convolutions to facilitate comprehensive feature extraction at the temporal and channel levels independently. 2) We introduce the Cross Convolutional Fusion (CCF) layer as a novel approach to model the inter-dependencies between the temporal and channel scopes. This layer effectively breaks the independence of these two dimensions and enables the interaction between features. Experimental results demonstrate that the proposed TCJA-SNN outperforms the state-of-the-art on all standard static and neuromorphic datasets, including Fashion-MNIST, CIFAR10, CIFAR100, CIFAR10-DVS, N-Caltech 101, and DVS128 Gesture. Furthermore, we effectively apply the TCJA-SNN framework to image generation tasks by leveraging a variation autoencoder. To the best of our knowledge, this study is the first instance where the SNN-attention mechanism has been employed for high-level classification and low-level generation tasks. Our implementation codes are available at https://***/ridgerchu/TCJA. © 2022, CC BY-NC-SA.

关键词： Neural networks

MoTransFrame:Model Transfer Framework for CNNs on Low-Resource Edge Computing Node

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第12期65卷 2321-2334页

作者： Panyu Liu Huilin Ren Xiaojun Shi Yangyang Li Zhiping Cai Fang Liu Huacheng Zeng National University of Defense Technology Changsha410073China Training and Administration Department the Central Military CommissionBeijing100851China Department of Science and Technology China Electronics Technology Group CorporationBeijing100846China National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data Beijing100041China School of Design Hunan UniversityChangsha410082China Department of Electrical and Computer Engineering University of LouisvilleLouisvilleKY 40292USA

Deep learning technology has been widely used in computer vision,speech recognition,natural language processing,and other related *** deep learning algorithm has high precision and high ***,the lack of resources in the edge terminal equipment makes it difficult to run deep learning algorithms that require more memory and computing *** this paper,we propose MoTransFrame,a general model processing framework for deep learning *** of designing a model compression algorithm with a high compression ratio,MoTransFrame can transplant popular convolutional neural networks models to resources-starved edge devices promptly and *** the integration method,Deep learning models can be converted into portable projects for Arduino,a typical edge device with limited *** experiments show that MoTransFrame has good adaptability in edge devices with limited *** is more flexible than other model transplantation *** can keep a small loss of model accuracy when the number of parameters is compressed by tens of *** the same time,the computational resources needed in the reasoning process are less than what the edge node could handle.

关键词： Edge computing convolutional neural network model transformation model compression

DOMINO: Domain-aware Model Calibration in Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Stolte, Skylar E. Volle, Kyle Indahlastari, Aprinda Albizu, Alejandro Woods, Adam J. Brink, Kevin Hale, Matthew Fang, Ruogu United States Department of Mechanical and Aerospace Engineering Herbert Wertheim College of Engineering UF United States Center for Cognitive Aging and Memory McKnight Brain Institute UF United States Department of Clinical and Health Psychology College of Public Health and Health Professions UF United States Department of Neuroscience College of Medicine UF United States United States Air Force Research Laboratory Eglin Air Force Base FL United States Department of Electrical and Computer Engineering Herbert Wertheim College of Engineering UF United States

Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. Medical image segmentation particularly suffers from this due to the natural uncertainty of tissue boundaries. This is exasperated by their loss functions, which favor overconfidence in the majority classes. We address these challenges with DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our experiments demonstrate that our DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation. Our results show that our method can consistently achieve better calibration, higher accuracy, and faster inference times than these methods, especially on rarer classes. This performance is attributed to our domain-aware regularization to inform semantic model calibration. These findings show the importance of semantic ties between class labels in building confidence in deep learning models. The framework has the potential to improve the trustworthiness and reliability of generic medical image segmentation models. The code for this article is available at: https://***/lab-smile/DOMINO. Copyright © 2022, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

USED: Universal Speaker Extraction and Diarization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ao, Junyi Yıldırım, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker’s voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Frequency domain analysis

Development and External Validation of Machine Learning Models to Predict Caesarean Section Following Induction of Labour Using Real-World, Population-Based Administrative Datasets

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Hu, Yanan Zhang, Xin Slavin, Valerie Enticott, Joanne Callander, Emily Monash Centre for Health Research and Implementation Faculty of Medicine Nursing and Health Sciences Monash University Melbourne Australia Department of Electrical and Computer Systems Engineering Monash University Melbourne Australia Gold Coast University Hospital Gold Coast Hospital and Health Service Southport Australia School of Nursing and Midwifery Griffith University Gold Coast Australia School of Public Health University of Technology Sydney Sydney Australia

Background: Induction of labour (IOL) is a complex clinical procedure associated with varying risks and could be better informed by robust risk prediction models. This study aimed to develop, temporally and externally validate machine learning prediction models for caesarean section (CS) following IOL using population-based administrative perinatal datasets in Australia, and to make the optimal model publicly accessible through as an interactive web ***: Women who had singleton, cephalic, term, and live births following attempted IOL were included, excluding those with previous CS. Seven models were developed using logistic regression, random forest, gradient boosting, LightGBM, XGBoost, CatBoost, and AdaBoost classification algorithms. Eighteen predictors known before the start of IOL were considered. Each model underwent hyperparameter tuning and feature selection, with predictor contributions visualized using SHAP plots. Model performance was assessed using area under the receiver operating characteristic curve (AUROC), calibration plot, decision curve, Brier Score, and model parsimony, with 95% confidence intervals estimated from 1,000 bootstrapped ***: The XGBoost model exhibited superior performance and clinical utility with the fewest predictors (n=10). The AUROC achieved at 0·766 (0·763 – 0·768), 0·757 (0·747 – 0·765), and 0·747 (0·738 – 0·755), among training (n=180,700, CS%=20·8%), temporal validation (n=14,527, CS%=22·5%), and geographical external validation cohorts (n=14,755, CS%=19%), respectively. The top three predictors contributing to a higher probability of CS following IOL were nulliparity, higher pre-pregnancy BMI, and older maternal age, whilst pre-existing and pregnancy-developed diabetes or hypertension contributed the ***: By offering objective, individualized, and interpretable probability of CS following IOL, our CSAI prediction tool (https://***/) using ten routinel

关键词： Decision trees

Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Restrepo, David Wu, Chenwei Cajas, Sebastían Andrés Nakayama, Luis Filipe Celi, Leo Anthony López, Diego M. Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA United States Departamento de Telemática Universidad del Cauca Cauca Popayán Colombia Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States John A. Paulson School of Engineering and Applied Sciences Harvard University BostonMA United States School of Computer Science University College Dublin Belfield Dublin Ireland Department of Ophthalmology São Paulo Federal University São Paulo São Paulo Brazil Department of Biostatistics Harvard TH Chan School of Public Health BostonMA United States Department of Medicine Beth Israel Deaconess Medical Center BostonMA United States

Objective: Large-scale multi-modal deep learning models and datasets have revolutionized various domains such as healthcare, underscoring the critical role of computational power. However, in resource-constrained regions like Low and Middle-Income Countries (LMICs), GPU and data access is limited, leaving many dependent solely on CPUs. To address this, we advocate leveraging vector embeddings for flexible and efficient computational methodologies, aiming to democratize multimodal deep learning across diverse contexts. Background and Significance: Our paper investigates the computational efficiency and effectiveness of leveraging vector embeddings, extracted from singlemodal foundation models and multi-modal Vision-Language Models (VLM), for multimodal deep learning in low-resource environments, particularly in healthcare applications. Additionally, we propose an easy but effective inference-time method to enhance performance by further aligning image-text embeddings. Materials and Methods: By comparing these approaches with traditional multimodal deep learning methods, we assess their impact on computational efficiency and model performance using accuracy, F1-score, inference time, training time, and memory usage across 3 medical modalities such as BRSET (ophthalmology), HAM10000 (dermatology), and SatelliteBench (public health). Results: Our findings indicate that embeddings reduce computational demands without compromising the model's performance, and show that our embedding alignment method improves the performance of the models in medical tasks. Discussion: This research contributes to sustainable AI practices by optimizing computational resources in resource-constrained environments. It highlights the potential of embedding-based approaches for efficient multimodal learning. Conclusion: Vector embeddings democratize multimodal deep learning in LMICs, especially in healthcare. Our study showcases their effectiveness, enhancing AI adaptability in varied use cases

关键词： Embeddings

Resilience of renewable power systems under climate risks

学校读者我要写书评

暂无评论

Nature Reviews Electrical Engineering

Nature Reviews electrical engineering 2024年第1期1卷 53-66页

作者： Luo Xu Kairui Feng Ning Lin A.T.D. Perera H. Vincent Poor Le Xie Chuanyi Ji X. Andy Sun Qinglai Guo Mark O’Malley Department of Civil and Environmental Engineering Princeton University Princeton NJ USA Center for Policy Research on Energy and the Environment Princeton NJ USA Andlinger Center for Energy and the Environment Princeton University Princeton NJ USA Department of Electrical and Computer Engineering Princeton University Princeton NJ USA Department of Electrical and Computer Engineering Texas A&M University College Station TX USA School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Sloan School of Management Operations Research Center Massachusetts Institute of Technology Cambridge MA USA Department of Electrical Engineering Tsinghua University Beijing China Department of Electrical and Electronic Engineering Imperial College London London UK

Climate change is expected to intensify the effects of extreme weather events on power systems and increase the frequency of severe power outages. The large-scale integration of environment-dependent renewables during energy decarbonization could induce increased uncertainty in the supply–demand balance and climate vulnerability of power grids. This Perspective discusses the superimposed risks of climate change, extreme weather events and renewable energy integration, which collectively affect power system resilience. Insights drawn from large-scale spatiotemporal data on historical US power outages induced by tropical cyclones illustrate the vital role of grid inertia and system flexibility in maintaining the balance between supply and demand, thereby preventing catastrophic cascading failures. Alarmingly, the future projections under diverse emission pathways signal that climate hazards — especially tropical cyclones and heatwaves — are intensifying and can cause even greater impacts on the power grids. High-penetration renewable power systems under climate change may face escalating challenges, including more severe infrastructure damage, lower grid inertia and flexibility, and longer post-event recovery. Towards a net-zero future, this Perspective then explores approaches for harnessing the inherent potential of distributed renewables for climate resilience through forming microgrids, aligned with holistic technical solutions such as grid-forming inverters, distributed energy storage, cross-sector interoperability, distributed optimization and climate–energy integrated modelling.

关键词：

Semi-automatic segmentation of knee cartilage in longitudinal MR images by seed transfer 2

学校读者我要写书评

暂无评论

Semi-automatic segmentation of knee cartilage in longitudina...

2nd International Conference on electrical, Communication and computer engineering, ICECCE 2020

作者： Kim, Myoung Jin Park, Taewoo Lee, Soochahn Jung, Ho Yup Yun, Il Dong Hankuk University of Foreign Studies Dept. Computer and Electronic System Yongin Korea Republic of Geumgang University Division of Public Policy Nonsan Korea Republic of School of Electrical Engineering Kookmin University Seoul Korea Republic of Chosun Niveristy Dept. Compter Engineering Gwangju Korea Republic of

ISBN: (数字)9781728171166

ISBN: (纸本)9781728171166

In this paper, we propose an efficient and effective semi-automatic segmentation framework for knee cartilage in longitudinal MR images. The proposed method provides a seamless and efficient combination of initial automatic segmentation and interactive segmentation. The main idea is to generate and transfer the seeds, rather than the labels, of the manual segmentation results of the initial image, to segment sequential images. Here, segmentation seeds are defined as sample voxels that are highly likely to be either the organ of interest or background. Similar to user annotations by scribbles, seeds can be used to determine labels for remaining voxels. Compared to methods that transfer segmentation labels, the proposed method is able to reduce the amount of required user annotations, since it does not require the user to identify and correct erroneous regions in the transferred segmentation labels, while still providing a robust initial segmentation based on transferred initial seeds. We evaluate the effectiveness of the proposed framework by measuring the interaction time of the user to segment the cartilage within the images. We compare the results with previous methods and show that the proposed method reduces the required interaction time. © 2020 IEEE.

关键词： Cartilage