检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ohta, Kazuhiro Ono, Satoshi Information Science and Biomedical Engineering Program Kagoshima University Korimoto 1-21-40 Kagoshima890-0065 Japan

Neural Radiance Field (NeRF), capable of synthesizing high-quality novel viewpoint images, suffers from issues like artifact occurrence due to its fixed sampling points during rendering. This study proposes a method t... 详细信息

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Development of Inkjet-Printed PEDOT:PSS-Based Organic Electrochemical Transistor (OECT) for Biopotential Amplification

Development of Inkjet-Printed PEDOT:PSS-Based Organic Electr...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Fadi C. Khoury Sahera A. Saleh Zeina S. Habli Massoud L. Khraiche Neural Engineering and Nanobiosensors Group Biomedical Engineering Program Maroun Semaan Faculty of Engineering and Architecture American University of Beirut Lebanon

With the ever-increasing need for miniaturized and biocompatible devices for physiological recordings, high signal fidelity and ease of fabrication are key to achieve reliable data collection. This calls for the development of active recording devices such as Organic Electrochemical Transistors (OECTs) which, compared to passive electrodes, offer local amplification. In this work, we built PEDOT:PSS based OECTs using novel inkjet printing technology, achieving a transconductance of 75 mS. The device was later used to amplify arbitrary signals simulating in vivo recordings. Gate voltage offset manipulation offered a range of current peak-to-peak amplitudes. Additionally, we demonstrate a simple circuit for voltage readings, where another resistor-dependent characterization involving voltage source and drain voltage is performed. At ideal operating point and when using a 220 Ω resistor, a gain of 14.5 is *** Relevance— 1 This work demonstrates the ability to rapidly and easily develop OECT-based technology for potential signal sensing for more accurate diagnosis of pathologies and diseases.

关键词：

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

Evaluation of an Intelligent Edge Computing System for the Hospital Intensive Care Unit 3

Evaluation of an Intelligent Edge Computing System for the H...

引用

3rd IEEE Eurasia Conference on biomedical engineering, Healthcare and Sustainability, ECBIOS 2021

作者： Zida, Serge Ismael Lin, Yue-Der Lee, Cheng Lin Tsai, Yi Lun Program of Electrical and Communications Engineering Feng Chia University Taichung Taiwan Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan

ISBN: (纸本)9781728193045

The evolution of medical technology along with information and communication technologies has accelerated the development and operationalization of smart hospitals recently. Traditionally, such hospitals typically rely on cloud computing platforms for data treatment and processing. However, the expansion and popularization of Internet of Medical Things (IoMT) devices and constant data monitoring have resulted in massive amounts of generated data, leading to the overload of the cloud infrastructure. This results in high power consumption and latency in data transmission, which is critical especially in a healthcare environment where data flow must be particularly responsive. Thus, we proposed and designed a Raspberry Pi-based edge computing system to computer-intensive care unit (ICU) data at the periphery of the network to offload the hospital cloud platform. ICU medical data were simulated from the PhysioNet MIMIC III database and transferred to the edge platform for computation and identification of emergency cases that were then sent to the cloud level. We further discuss the current issues and prospects of edge computing in hospitals. © 2021 ECBIOS 2021. All rights reserved.

关键词： Intensive care units

来源：评论

学校读者我要写书评

暂无评论

Cytometry in the Short-Wave Infrared

引用

ACS Nano 2024年第28期18卷 18534-18547页

作者： Liu, Te-I Wang, Jhih-Shan Nguyen, Ai-Phuong Raabe, Marco Quiroz Reyes, Carlos Jose Lin, Chih-Hsin Lin, Ching-Wei Institute of Atomic and Molecular Sciences Academia Sinica Taipei City106319 Taiwan Department of Materials Science and Engineering National Taiwan University Taipei City106319 Taiwan Department of Physics University of Stuttgart Stuttgart70174 Germany Department of Chemistry National Tsing Hua University Hsinchu300044 Taiwan International Ph.D. Program in Biomedical Engineering Taipei Medical University New Taipei City235603 Taiwan Graduate Institute of Nanomedicine and Medical Engineering Taipei Medical University New Taipei City235603 Taiwan

Cytometry plays a crucial role in characterizing cell properties, but its restricted optical window (400-850 nm) limits the number of stained fluorophores that can be detected simultaneously and hampers the study and utilization of short-wave infrared (SWIR;900-1700 nm) fluorophores in cells. Here we introduce two SWIR-based methods to address these limitations: SWIR flow cytometry and SWIR image cytometry. We develop a quantification protocol for deducing cellular fluorophore mass. Both systems achieve a limit of detection of ∼0.1 fg cell-1 within a 30 min experimental time frame, using individualized, high-purity (6,5) single-wall carbon nanotubes as a model fluorophore and macrophage-like RAW264.7 as a model cell line. This high-sensitivity feature reveals that low-dose (6,5) serves as an antioxidant, and cell morphology and oxidative stress dose-dependently correlate with (6,5) uptake. Our SWIR cytometry holds immediate applicability for existing SWIR fluorophores and offers a solution to the issue of spectral overlapping in conventional cytometry. © 2024 The Authors. Published by American Chemical Society.

关键词： Oxygen

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

Age-Associated Perinexal Narrowing Masks Consequences of Sodium Channel Gain of Function in Guinea Pig Hearts

引用

JACC: Clinical Electrophysiology 2025年第5期11卷 919-930页

作者： Wu, Xiaobo King, David Ryan Hoeker, Gregory S. Wan, Xiaoping Deschenes, Isabelle Johnstone, Scott R. Gourdie, Robert G. Weinberg, Seth H. Poelzing, Steven Translational Biology Medicine and Health Graduate Program Virginia Polytechnic Institute and State University Roanoke VA United States Center for Vascular and Heart Research Fralin Biomedical Research Institute at Virginia Tech Carilion Roanoke VA United States Frick Center for Heart Failure and Arrhythmia Dorothy M. Davis Heart and Lung Research Institute College of Medicine The Ohio State University Wexner Medical Center Columbus OH United States Department of Biomedical Engineering and Mechanics Virginia Polytechnic Institute and State University Blacksburg VA United States Department of Biomedical Engineering Davis Heart and Lung Research Institute The Ohio State University Columbus OH United States

Background: Voltage-gated sodium channel gain of function (NavGOF) is associated with an elevated risk for cardiac arrhythmia. Recent studies have demonstrated that NavGOF can be exacerbated by widening the sodium cha... 详细信息

Background: Voltage-gated sodium channel gain of function (Na_vGOF) is associated with an elevated risk for cardiac arrhythmia. Recent studies have demonstrated that Na_vGOF can be exacerbated by widening the sodium channel–rich perinexus next to gap junction plaques. Clinically, the incidence of Na_vGOF-related cardiac events increases with advancing age. However, the impact of aging on perinexal changes and contribution to age-related risk for arrhythmias in Na_vGOF remains unclear. Objectives: The aim of this study was to test the hypothesis that age-related increase in arrhythmogenic risk is associated with perinexal remodeling in a model of Na_vGOF. Methods: Na_vGOF was pharmacologically induced in isolated adult (3 months, n = 17) and aged (15 months, n = 19) guinea pig hearts. Epicardial action potentials were optically mapped, and age-associated perinexal remodeling was measured with transmission electron microscopy. Results: Na_vGOF electrical phenotypes were comparable between adult and aged hearts despite their exacerbation after perinexal widening. The similarity in these phenotypes may be masked by the narrower perinexus with aging. Furthermore, perinexal widening led to a high incidence of arrhythmias in aged Na_vGOF hearts, whereas no arrhythmias were induced in adult Na_vGOF hearts. This increased incidence of arrhythmias in aged Na_vGOF hearts following perinexal widening may be associated with the increased dispersions of epicardial action potential duration and transmural repolarization. Conclusions: Perinexal widening exacerbates arrhythmogenic propensity with age, primarily by heterogeneously increasing action potential duration, whereas perinexal narrowing appears to be adaptive and cardio protective in the context of Na_vGOF. © 2025

关键词： aging APD dispersion arrhythmia GOF perinexus sodium channel

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

Ischemic Stroke Post-treatment Prediction using Machine Learning to develop Web Application for Healthcare Centers in Thailand

Ischemic Stroke Post-treatment Prediction using Machine Lear...

引用

2023 International Electrical engineering Congress, iEECON 2023

作者： Worraviseat, Kulwarin Danvirutai, Pobporn Anutrakulchai, Sirirat Kasemsap, Narongrit Srichan, Chavis Khon Kaen University Faculty of Engineering Department of Biomedical Engineering Khon Kaen Thailand Postdoctoral Research Program Khon Kaen University Khon Kaen Thailand Khan Kaen University Faculty of Medicine Department of Medicine Khon Kaen Thailand Khan Kaen University Faculty of Engineering Khon Kaen Thailand

ISBN: (纸本)9798350332360

Stroke attack is one of the most serious concerns in an emergency room. Expert diagnosis and accurate treatment are crucial for the improvement, death, or impairment of the patients. This work aims at using big data analytics for developing a system to provide the probability for each patient whether he would improve after medications. Records of N=1700 volunteers were gathered for non-linear classification training. Random Forest outperforms seven other methods compared in this study. The AI model was deployed as a web application for a rural hospital to assist medical personnel. This can be considered an important step towards AI-assisted emergency medications for stroke. Under the situation where the NIH Stroke Score was unavailable on time, the system could still provide the improvement probability via a web application based on the AI model trained in this work. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Title: Challenges in single cells sequencing Microbial community and biofilm: A case of Oleidesulfovibrio alaskensis G20 NGS protocol

Title: Challenges in single cells sequencing Microbial commu...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Singh, Ram Nageena Gnimpieba, Etienne Z. Sani, Rajesh Kumar Chemical and Biological Engineering South Dakota School of Mines and Technology Rapid City United States University of South Dakota Gear Center Biomedical Engineering Program Sioux Falls United States

ISBN: (纸本)9781665468190

Biofilm, is a special-complex organization of bacterial cells with multiple layers, formed in certain environmental conditions. In the complex biofilm different bacterial (single) cells perform different functions and contribute to overall biofilm activity, where single bacterial cells are in different physiological states of growth, stress and signaling. Sulphate reducing bacteria (SRB) contributes to huge economic loss ({}4B) causing microbial induced corrosion. To effectively combat the challenges posed by SRB, it is essential to understand their molecular mechanisms of biofilm formation and biocorrosion. Single Cell Genomics (single cell transcriptomics) is a technique which investigates the gene expression at the level of a single biological cell and could not be attainable in bulk analysis (RNASeq) could decipher the uniqueness of each cell in complex group. We are developing a NGS (oxford Nanopore)-workflow for single cell transcriptomics of biofilms using Oleidesulfovibrio alaskensis (earlier Desulfovibrio alaskensis) strain G20 (OA-G20) as a model. We encountered several challenges to design and develop the workflow such 1) absence of ploy(A) tail in mRNAs, 2) amount of total RNA, 3) half-lives of mRNAs, 4) perforation of cell membrane, 5) low copy number of mRNAs, 6) single cell suspension and cell sorting, 7) quantification of bacterial cells, 8) fixation of cells, 9) designing of probes, 10) hybridization of probes and 11) amplification of mRNAs. Here, we are presenting how we resolved some of these challenges to design and develop a single cell genomics (transcriptomics) workflow for SRB biofilms. © 2022 IEEE.

关键词： Genome

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：