检索结果-内蒙古大学图书馆

26th International Conference on Asia-Pacific Digital Libraries, ICADL 2024

作者： Sari, Desy Novita Prameswari, Clarissa Rahmi Anshori, Isa Master’s Program in Library Science Universitas Indonesia Kota Depok Indonesia Department of Library and Information Sciences Universitas Indonesia Kota Depok Indonesia Biomedical Engineering Department School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia National Gallery of Indonesia Central Jakarta Indonesia

ISBN: (纸本)9789819608676

Eye-tracking studies focused on art galleries and museums within the realm of Instagram, especially in the Indonesian context, are notably scant. This investigation elucidates the user interaction and experience of the art gallery’s Instagram account, @galerinasional. Employing a quantitative approach, we implemented eye-tracking experiments using the well-known online eye-tracking software RealEye. The study participants were followers of the National Gallery of Indonesia’s (Galnas) Instagram profile, seven women and three men, in two age brackets: 18–24 years (n = 5) and 25–34 years (n = 5). The experimental protocol required participants to execute five tasks centered on locating exhibition details and artwork on the Galnas Instagram platform, with a duration of 100 s allocated to each task. The Participant Quality Grade (PQG), examination duration, optimal browser dimensionality, K-factor mean, gaze and fixation frequencies, and heat maps were determined for the participants. The key findings are as follows. (1) The participants’ PQG scores were predominantly between 4 and 6. (2) Investigative browsing typically exceeded the 100-s limit. (3) The consensus on the ideal browser dimensions hovered around 1,368.6 × 814.8 px. (4) The K-factor mean across participants tended toward K > 0. (5) The average gaze occurrence was 27 items per second for most participants. (6) A noticeable disparity in fixation counts was observed between the two age groups, with individuals aged 25–34 demonstrating prolonged engagement with Galnas’ content. (7) Heat maps accentuated a pronounced concentration on visual content, encompassing photographs, videos, and their associated captions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Deep Learning for Final Infarct Prediction Using Acute Stroke CT Perfusion Data 4th

Spatio-Temporal Deep Learning for Final Infarct Prediction U...

引用

4th International Workshop on Imaging and Treatment Challenges, SWITCH 2024, and 6th International Challenge on Ischemic Stroke Lesion Segmentation Challenge, ISLES 2024, Held in Conjunction with Medical Image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Amador, Kimberly Winder, Anthony J. Forkert, Nils D. Biomedical Engineering Graduate Program University of Calgary Calgary Canada Department of Radiology University of Calgary Calgary Canada Hotchkiss Brain Institute University of Calgary Calgary Canada Alberta Children’s Hospital Research Institute University of Calgary Calgary Canada

ISBN: (纸本)9783031811005

Accurate prediction of the tissue outcome is crucial for guiding treatment decisions in acute ischemic stroke (AIS). Spatio-temporal (4D) Computed Tomography Perfusion (CTP) provides detailed insights into cerebral blood flow dynamics, which are essential for predicting final infarct regions. However, its high-dimensional and noisy nature presents challenges for direct prediction. In this study, we evaluate a deep learning model that fully leverages 4D CTP data for predicting tissue outcomes. The model integrates a shared-weight convolutional neural network (CNN) encoder, a Transformer encoder, and a CNN decoder to capture both spatial and temporal dependencies within the data. We evaluated this approach on a multicenter dataset of 143 patients from the ISLES 2024 challenge. The results reveal a Dice score of 0.20, an absolute volume difference of 17 ml, a mean lesion count difference of 19, and a lesion-wise F1-Score of 0.02, underscoring both the potential and challenges of directly utilizing 4D CTP data for final infarct prediction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Effect of cell imprinting on viability and drug susceptibility of breast cancer cells to doxorubicin" [Acta Biomaterialia, 2020, 113, 119-129] (Acta Biomaterialia (2020) 113 (119–129), (S1742706120303287), (10.1016/***.2020.06.007))

引用

Acta Biomaterialia 2025年 198卷 571-572页

作者： Shahriyari, Fatemeh Janmaleki, Mohsen Sharifi, Shahriar Hesar, Milad Eyvazi Hoshian, Sasha Taghiabadi, Reza Razaghian, Ahmad Ghadiri, Majid Peirovi, Afshin Mahmoudi, Morteza Nezhad, Amir Sanati Khademhosseini, Ali Division of Engineering in Medicine Department of Medicine Brigham and Women's Hospital Harvard Medical School CambridgeMA United States Division of Health Sciences & Technology Harvard-Massachusetts Institute of Technology Massachusetts Institute of Technology CambridgeMA United States Department of Materials Engineering Faculty of Engineering Imam Khomeini International University Qazvin Iran Biomedical Engineering Graduate Program University of Calgary Canada Precision Health Program and Department of Radiology Michigan State University East LansingMI48824 United States RWTH Aachen University Templergraben 55 Aachen52062 Germany Department of Chemistry and Materials Science Aalto University School of Chemical Engineering Espoo Finland Department of Mechanical Engineering Faculty of Engineering Imam Khomeini International University Qazvin Iran Nano-Biotechnology Department Pasteur Institute of Iran Tehran Iran Departments of Bioengineering Chemical and Biomolecular Engineering and Radiological Sciences Center for Minimally Invasive Therapeutics California NanoSystems Institute University of California – Los Angeles Los AngelesCA United States Terasaki Institute for Biomedical Innovation Los AngelesCA United States

The authors regret to report that the images for panels h (Plain PDMS) and I (MCF7-imprinted PDMS) in Fig. 3 were mistakenly taken from the same dataset, resulting in the omission of the correct image in panel h for the Plain PDMS day 7 image. We sincerely apologize for this error. For an accurate representation, please see the corrected Fig. 3 provided here along with its original figure caption. This does not affect the validity of the statistical analyses or the overall conclusions drawn from the study. © 2025

关键词：

来源：评论

学校读者我要写书评

暂无评论

A high cholesterol diet increases serum estradiol in female rats with lower energy availability following a treadmill training program

引用

Sport Sciences for Health 2025年 1-9页

作者： Clark, Lyra Dellogono, Michael Wilson, Thomas A. Biomedical Engineering and Biotechnology Program University of Massachusetts Lowell One University Avenue Lowell 10854 MA United States Department of Biomedical and Nutritional Sciences University of Massachusetts Lowell 3 Solomont Way Lowell 01854 MA United States

Purpose: The aim of this study was to investigate the effects of a high cholesterol diet on sex hormone levels in female rats following a treadmill (TM) endurance training program. Methods: Female Sprague Dawley rats (n = 29) consuming a standard semi-purified low-cholesterol diet were randomly assigned to a control group (C, n = 15) or an exercise training group (EX, n = 14) that performed TM running 40 min/day, 6 days/wk for 12 weeks. At the study midpoint (end week 6), half the rats in each group were then randomized to receive a high-cholesterol (HC or EX + HC) diet. Fasting blood samples were collected at baseline, week 6, and week 12 to measure serum lipids and lipoprotein cholesterol, estradiol, progesterone and leptin levels. Results: At the end of week 6, the EX group had significantly lower body weight ( – 10%, p < 0.05), mean daily energy intake ( – 21%, p < 0.01), serum leptin ( – 27%, p < 0.05), and serum progesterone ( – 31%, p < 0.05) compared to C. There were no significant differences in serum estradiol. At end of wk 12, EX + HC group had significantly lower body weight ( – 17%, p < 0.05) and serum leptin ( – 67%, p < 0.05) compared to C. However, serum estradiol was significantly higher in EX + HC group compared to C (124%, p < 0.05) and EX (171%, p < 0.05). There was no significant difference between groups in energy intake or serum progesterone. Conclusions: Female rats consuming a high-cholesterol diet and exercising had significantly higher serum estradiol than rats consuming a low-cholesterol diet and/or exercising. Thus, it might be possible that extra dietary cholesterol consumption, without extra calories, may improve sex hormone status in female athletes. © The Author(s), under exclusive licence to Springer-Verlag Italia S.r.l., part of Springer Nature 2025.

关键词： Estrogen High cholesterol diet Leptin Progesterone Treadmill endurance training

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Military Basic Throwing Training Strategy with Machine Learning 6th

Feature Selection for Military Basic Throwing Training Strat...

引用

6th International Conference on biomedical and Health Informatics, ICBHI 2024

作者： Han, Hsieh-Ping Chow, Tong-Hsien Ho, Wen-Hsien PhD Program in Biomedical Engineering Kaohsiung Medical University Kaohsiung807378 Taiwan Department of Sports Science R.O.C. Military Academy Kaohsiung830208 Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung807378 Taiwan

ISBN: (纸本)9783031863226

Basic military training (BMT) is important and initial period for soldiers, especially the military basic throwing performance is one of the key military tactical motor skill. In recent years, machine learning (ML) techniques have been increasingly adopted to analyze extensive datasets and derive meaningful insights. To evaluate the effectiveness of fitness training strategies for military throwing, this study analyzed seven common input features: pull-ups, push-ups, squat concentric/eccentric peak power, squat maximum strength, leg tuck, and a 3 km run. Four data mining models—Random Forest, Multilayer Perceptron, AdaboostM1, and Bagging classifier—were tested to identify the most effective method for predicting performance. The Random Forest model excelled, achieving the highest accuracy, precision, recall, and F1 score, indicating its superiority in this context. These seven attributes were thus identified as key predictors of military throwing performance. However, further research is necessary to establish a definitive ranking and to fully understand the importance of each feature in refining training strategies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Detection of retinitis pigmentosa stages with GAN and transfer learning in maps of MfERG P1 wave amplitudes

引用

Signal, Image and Video Processing 2025年第7期19卷 1-24页

作者： Güven, Aysegül Karaman, Bayram Öner, Ayse Sinim Kahraman, Neslihan Department of Biomedical Engineering Engineering Faculty Erciyes University Kayseri Turkey Biomedical Engineering Graduate Program Graduate School of Natural and Applied Sciences Erciyes University Kayseri Turkey Department of Electrical and Electronics Engineering Engineering and Architecture Faculty Tokat Gaziosmanpasa University Tokat Turkey Department of Ophthalmology Acıbadem Taksim Hospital Istanbul Turkey Department of Ophthalmology Acıbadem University Istanbul Turkey

Retinitis pigmentosa (RP) is an inherited disease caused by the dysfunction of photoreceptor cells in the retina. Effective management and therapy are crucial to delaying or preventing vision loss and blindness, making RP a leading cause of inherited retinal disorders globally. This study is the first to utilize maps of P1 wave amplitudes from multifocal electroretinography for the automatic identification and staging of RP. We enhanced raw data with image preprocessing, traditional image augmentation, and generative adversarial networks (GAN) to create comprehensive datasets, followed by classification using five transfer learning models. Initial results indicated overfitting, mitigated through advanced preprocessing and augmentation. Performance metrics showed that the Deep Convolutional GAN model effectively eliminated overfitting. ResNet50 achieved the highest performance in four-class classification with 95.2% recall, 95.2% precision, 94.9% accuracy, 98.2% specificity and 95.2% F1 score. These results suggest that maps of P1 wave amplitudes are valuable indicators for differentiating RP stages, highlighting their potential for improving RP diagnosis and management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Damage-Free Neutral Beam Etching for Gate Recess in E-Mode AlGaN/GaN HEMTs

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年第5期46卷 705-708页

作者： Chen, Yi-Ho Chu, Fu-Chuan Aslam, Muhammad Lee, Yao-Jen Li, Yiming Samukawa, Seiji National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung-Shan Institute of Science and Technology Solid State Devices Section Electronic System Research Division Taoyuan325 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

Recess gate etching is a critical technique for achieving enhancement-mode (E-mode) AlGaN/GaN high-electron mobility transistors (HEMTs) because the interface is susceptible to the etching damage. This study fabricates recess gates using the neutral beam etching (NBE) technique. By adjusting the aperture thickness in the NBE apparatus, we simulate both NB-mode and plasma-mode etching. The electrical characteristics of E-mode HEMTs fabricated using these two modes are analyzed and compared through DC, noise, and pulsed IV measurements. The results demonstrate that NB-recessed HEMTs exhibit superior performance. © 1980-2012 IEEE.

关键词： Aluminum gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Neural Networks and Explainable Artificial Intelligence for Breast Cancer Prediction and Classification

引用

Procedia Computer Science 2025年 256卷 1159-1166页

作者： Erika Yahata Pablo Deoclecia dos Santos Maria Marlene de Souza Pires Ricardo Suyama Priscyla Waleska Simoes Graduate Program in Information Engineering Federal University of ABC Santo André SP Brazil Graduate Program in Biomedical Engineering Federal University of ABC São Bernardo do Campo SP Brazil Pediatrics Department Federal University of Santa Catarina Florianópolis Santa Catarina Brazil

Solutions based on Artificial Intelligence techniques have been proposed in the healthcare sector, however the lack of understanding of the results has been a cause for concern and one of the main barriers to their effective use. To fill the gap in understanding these models considered black boxes, the Explainable Artificial Intelligence was proposed to explain the relationship between input data and the prediction results made by the Artificial Intelligence models. In this study, we present the use of explainability techniques for a black box machine learning model in breast cancer classification. Breast cancer is the type of cancer that causes the most deaths among women in the world and early diagnosis is essential to increase the chances of survival. The study evaluated the explainability of breast tumor predictions based on the Multilayer Perceptron artificial neural networks algorithm, considering a sample that contained data from 164 female patients undergoing Core Biopsy in the southern region of Brazil. The SHAP, LIME, PDP and ICE methods were used for the global and local explainability of the predictions. The results showed that in the global assessment, the BI-RADS® 5 ultrasound and mammography attributes were considered the most important for predicting the malignant tumor. Nodule size greater than 2 cm, presence of a family history and palpable nodule were also considered important for the prediction. In the local evaluation, it was found that the model correctly classified the tumors considering different characteristics of the patients. Through the results presented, the methods of explicability show evidence that the predictive model for breast cancer can be interpreted and understood, overcoming the barrier of lack understanding of the results of a black box model.

关键词： Explainable Artificial Intelligence Predictive Model Explainability Machine Learning Breast Cancer

来源：评论

学校读者我要写书评

暂无评论

Histogram-based Res-UNet model for optical sectioning HiLo endo-microscopy

引用

Optics Express 2025年第6期33卷 12253-12268页

作者： Chung, Meng-Chen Chia, Yu-Hsin Vyas, Sunil Luo, Yuan Department of Biomedical Engineering National Taiwan University Taipei10051 Taiwan Institute of Medical Device and Imaging National Taiwan University Taipei10051 Taiwan YongLin Institute of Health National Taiwan University Taipei10087 Taiwan Molecular Imaging Center National Taiwan University Taipei10672 Taiwan Program for Precision Health and Intelligent Medicine National Taiwan University Taipei106319 Taiwan

Optical sectioning endo-microscopy has become a crucial tool for deep brain imaging, but conventional methods face challenges such as time-consuming scanning processes and the need for expensive light sources. HiLo imaging addresses these issues by providing faster acquisition and high-quality images. In this study, we introduce a histogram matching-based Res-UNet model for optical sectioning HiLo endo-microscopy. By applying our model, we achieve substantial improvements in image reconstruction quality compared to the conventional ResNet model. Our evaluation demonstrates significant enhancements in the reconstructed images’ structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) metrics. The PSNR values exceeding 30 dB and SSIM values surpassing 0.8 at various depths indicate that our method achieves image quality comparable to the HiLo system. Importantly, while our approach demonstrates high-quality, real-time reconstruction capabilities using ex-vivo samples, we are actively planning to extend our research to in-vivo imaging applications, which will further enhance the practical implications of our work. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Brain imaging Imaging systems In vivo imaging Light sources Structured light Tissue imaging

来源：评论

学校读者我要写书评

暂无评论

Conditional Convolution of Clinical Data Embeddings for Multimodal Prostate Cancer Classification

Conditional Convolution of Clinical Data Embeddings for Mult...

引用

IEEE International Symposium on biomedical Imaging

作者： Jiayang Zhong Fuyao Chen Lihui Chen Dennis Shung John A. Onofrey Department of Biomedical Engineering Medical Scientist Training Program Department of Biotatistics Yale School of Public Health CT USA Yale School of Medicine CT USA Radiology & Biomedical Imaging Urology

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Accurate risk prediction for prostate cancer (PCa) in multiparametric magnetic resonance imaging (mpMRI) is essential for non-invasive diagnosis. Current deep learning approaches, such as convolutional neural networks (CNNs), show promise in predicting Gleason scores (GS) directly from imaging data, yet often overlook valuable clinical data in other data modalities. In this study, we introduce EmbedCondConv a novel multimodal GS prediction model that incorporates clinical information by conditioning CNN kernels on principal components derived from patient clinical data. We tested our models on a public dataset of 921 selected MRI scans and corresponding structured data and compared the prediction performance to baseline models. Our results demonstrate that incorporating clinical information into the model improves GS prediction accuracy with AUROC of 0.90 compared to 0.69 using imaging alone. All code used in this study is publicly available at https://***/jiayangz/EmbedCondConv.

关键词： Dimensionality reduction Convolution Magnetic resonance imaging Predictive models Data models Convolutional neural networks Clinical diagnosis Prostate cancer Kernel Principal component analysis

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：