检索结果-内蒙古大学图书馆

Computational and Systems Oncology 2023年第3期3卷

作者： Ai, Xusheng Smith, Melissa C Feltus, Frank Alex Electrical and Computer Engineering Department Clemson University Clemson SC United States Department of Genetics and Biochemistry Biomedical Data Science & Informatics Program Clemson Center for Human Genetics Clemson University Clemson SC United States

The remarkable flexibility and adaptability of generative adversarial networks (GANs) have led to the proliferation of its models in bioinformatics research. Proteomic and transcriptomic profiles have been shown to be promising methods for discovering and identifying disease biomarkers. However, those analyses were performed by trained human examiners making the process tedious, time consuming, and hard to standardize. With the development of GANs, it is now possible to reduce computational costs and human time for bioinformatics analysis to produce effective biomarkers. Moreover, GANs help address the lack of phenotypic state transitional gene expression data as well as avoid protected human data constraints by generating RNA sequencing (RNA-seq) data from random vectors. The purpose of this review is to summarize the use of GAN approaches and techniques to augment RNA-seq expression data and identify clinically useful biomarkers. We compare different studies that use different types of GAN models to examine the biomarkers. Also, we identify research gaps and challenges that apply GANs to bio-informatics. Finally, we propose potential directions for future research. © 2023 The Authors. Computational and Systems Oncology published by Wiley Periodicals LLC.

关键词： biomarkers data augmentation generative adversarial network RNA sequencing

来源：评论

学校读者我要写书评

暂无评论

Two fully automated data-driven 3D whole-breast segmentation strategies in MRI for MR-based breast density using image registration and U-Net with a focus on reproducibility

引用

Visual Computing for Industry,Biomedicine,and Art 2022年第1期5卷 303-314页

作者： Jia Ying Renee Cattell Tianyun Zhao Lan Lei Zhao Jiang Shahid M.Hussain Yi Gao H‑H.Sherry Chow Alison T.Stopeck Patricia A.Thompson Chuan Huang Department of Biomedical Engineering Stony Brook UniversityStony BrookNY 11794USA Department of Radiation Oncology Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Medicine Northside Hospital GwinnettLawrencevilleGA 30046USA Program of Public Health Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Radiology Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Department of Biomedical Informatics Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA School of Biomedical Engineering Health Science CenterShenzhen UniversityShenzhen 518060China University of Arizona Cancer Center TucsonAZ 85719USA Department of Medicine Renaissance School of MedicineStony Brook UniversityStony BrookNY 11794USA Stony Brook Cancer Center Stony Brook UniversityStony BrookNY 11794USA Department of Medicine Cedar Sinai CancerCedars Sinai Medical CenterLos AngelesCA 90048USA

Presence of higher breast density(BD)and persistence over time are risk factors for breast cancer.A quantitatively accurate and highly reproducible BD measure that relies on precise and reproducible whole-breast segmentation is *** this study,we aimed to develop a highly reproducible and accurate whole-breast segmentation algorithm for the generation of reproducible BD *** datasets of volunteers from two clinical trials were *** MR images were acquired on 3T Siemens Biograph mMR,Prisma,and Skyra using 3D Cartesian six-echo GRE sequences with a fat-water separation *** whole-breast segmentation strategies,utiliz-ing image registration and 3D U-Net,were *** segmentation was performed.A task-based analysis was performed:a previously developed MR-based BD measure,MagDensity,was calculated and assessed using automated and manual *** mean squared error(MSE)and intraclass correlation coefficient(ICC)between MagDensity were evaluated using the manual segmentation as a *** test-retest reproducibility of MagDensity derived from different breast segmentation methods was assessed using the difference between the test and retest measures(Δ_(2-1)),MSE,and *** results showed that MagDensity derived by the registration and deep learning segmentation methods exhibited high concordance with manual segmentation,with ICCs of 0.986(95%CI:0.974-0.993)and 0.983(95%CI:0.961-0.992),*** test-retest analysis,MagDensity derived using the regis-tration algorithm achieved the smallest MSE of 0.370 and highest ICC of 0.993(95%CI:0.982-0.997)when compared to other segmentation *** conclusion,the proposed registration and deep learning whole-breast segmentation methods are accurate and reliable for estimating *** methods outperformed a previously developed algorithm and manual segmentation in the test-retest assessment,with the registration exhibiting superior performance for highly reproducibl

关键词： Breast cancer Breast density Breast segmentation Image registration Deep learning

来源：评论

学校读者我要写书评

暂无评论

A potential imaging biomarker distinguishing neurodegenerative parkinsonism using brainstem MRI shape analysis

引用

European radiology 2023年第7期33卷 4537-4539页

作者： Ming-Ting Tsai Cheng-En Juan Yi-Jui Liu Chun-Jung Juan Department of Medical Imaging China Medical University Hsinchu Hospital Hsinchu Taiwan Republic of China. Master's Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Republic of China. Master's Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Republic of China. erliu@fcu.edu.tw. Department of Automatic Control Engineering Feng Chia University Taichung Taiwan Republic of China. erliu@fcu.edu.tw. Department of Medical Imaging China Medical University Hsinchu Hospital Hsinchu Taiwan Republic of China. peterjuancj@yahoo.com.tw. Department of Radiology School of Medicine College of Medicine China Medical University Taichung Taiwan Republic of China. peterjuancj@yahoo.com.tw. Department of Medical Imaging China Medical University Hospital Taichung Taiwan. peterjuancj@yahoo.com.tw. Department of Biomedical Engineering and Environmental Sciences National Tsing Hua University Hsinchu Taiwan Republic of China. peterjuancj@yahoo.com.tw. Department of Radiology School of Medicine National Defense Medical Center Taipei Taiwan Republic of China. peterjuancj@yahoo.com.tw.

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks

arXiv

引用

arXiv 2023年

作者： Liu, Chien-Pin Li, Ju-Hsuan Chu, En-Ping Hsieh, Chia-Yeh Liu, Kai-Chun Chan, Chia-Tai Tsao, Yu Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei112 Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei242062 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei115 Taiwan

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a "long-lie." Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD. Copyright © 2023, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks

Deep Learning-based Fall Detection Algorithm Using Ensemble ...

引用

IEEE International Workshop on Medical Measurement and Applications (MEMEA)

作者： Chien-Pin Liu Ju-Hsuan Li En-Ping Chu Chia-Yeh Hsieh Kai-Chun Liu Chia-Tai Chan Yu Tsao Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei City Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei City Taiwan

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a “long-lie.” Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network-based fast seizure detection from video electroencephalograms

引用

biomedical Signal Processing and Control 2023年 80卷

作者： Chou, Chi-Hsiang Shen, Tsu-Wang Tung, Hsin Hsieh, Peiyuan F. Kuo, Chih-En Chen, Ting-Mao Yang, Chao-Wei Department of Post-Baccalaureate Medicine College of Medicine National Chung Hsing University Taichung Taiwan The Department of Neurological Institute Taichung Veterans General Hospital Taichung Taiwan Department of Neurology National Yang Ming Chiao Tung University School of Medicine Taipei Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan Master's Program in Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Department of Applied Mathematics National Chung Hsing University Taichung Taiwan

Objective: Ictal stage detection in electroencephalography (EEG) is important for epilepsy diagnosis. However, it's a laborious and time-consuming task for neurologists, especially with lengthy EEG recordings (such as video-EEG). Here we applied the current deep learning techniques to improve ictal stage detection efficiency. Methods: We enrolled epileptic patients at video-EEG examination beds of our neurology department between Jan 2016 and Apr 2020. Four stages of EEG (interictal, preictal, ictal and postictal) were labeled and confirmed by neurologists. Labeled EEG signals were transformed into second-order Poincaré difference plots. The whole dataset was divided into ‘Training’, ‘Validation’ and ‘Testing’ datasets with the proportions of 45%, 5% and 50% respectively. We applied 4 Convolutional Neural Networks (CNNs), namely, AlexNet, GoogLeNet, ResNet50 and DenseNet201, to learn classifying. The top three CNNs were put into an ensemble model for datasets classification. Results: 30 epileptic patients were included: Male/Female 16/14, mean age 42.8 ± 15.0 (range 22 ∼ 81) years old. Total recorded ictal duration was 47,444 s. Overall accuracies for each of the 4 CNN models (AlexNet, GoogLeNet, ResNet50 and DenseNet201) were 78.0%, 78.3%, 81.7% and 80.8%. We omitted the AlexNet, the other 3 CNNs were put into the ensemble model. The best performance was under test with 1% of the Testing dataset yielded the overall accuracies of 85.9%. The ictal stage accuracy was 97.7%. Conclusion: Our method is a promising computer-aid deep learning approach to detect seizures on video EEG. Significance: For testing phase, selected proportion of testing dataset may influence the performances of deep learning models. © 2022 The Author(s)

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer

Predicting Microsatellite Instability from Histology Images ...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Yun-Chi Chen Tung Chao Wimaya Nitya Phandita Tzu-Yu Sun Huai-Zhi Wang Yi-Hsien Hsieh Le-Yin Hsu Che Lin Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University (NTU) Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan Data Science Degree Program NTU Taipei Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients.

关键词： Attention mechanisms Histopathology Computational modeling Precision medicine Small satellites Immunotherapy Colorectal cancer Predictive models Transformers Genetics

来源：评论

学校读者我要写书评

暂无评论

DCGAN-based Medical Image Augmentation to Improve ELM Classification Performance

DCGAN-based Medical Image Augmentation to Improve ELM Classi...

引用

IEEE International Conference on Communication, Networks and Satellite (ComNetSat)

作者： Rando Noor Akhmad Setiawan Adhistya Erna Permanasari Riries Rulaningtyas Andriyan Bayu Suksmono Imas Sukaesih Sitanggang Dept. of Electrical and Information Engineering Universitas Gadjah Mada Yogyakarta Indonesia Dept. of Physics Universitas Airlangga Biomedical Engineering Program Surabaya Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Department of Computer Science IPB University Bogor Indonesia

ISBN: (数字)9781665460309

ISBN: (纸本)9781665460316

Cervical cancer is one of the deadliest diseases in women. One of the cervical cancer screening methods is pap smear method. However, using a pap smear method to detect cervical cancer takes a long time for a pathologist to diagnose. Hence, a rapid development of medical computerization for early detection to get the results quickly is needed. This paper proposes synthetic data augmentation by using Deep Convolutional Generative Adversarial Network (DCGAN) to increase number of pap smear samples in dataset. Gray Level Co-occurrence Matrix (GLCM) is employed to extract features from dataset. Classification of 3 classes which are Adenocarcinoma, High-Grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC) is conducted using Extreme Learning Machine (ELM). The result shows that the addition of synthetic data improves the performance of ELM with the accuracy of 90%. This accuracy is better than the accuracy of ELM using only the original dataset which is 85%.

关键词： Satellites Extreme learning machines Medical services Feature extraction Generative adversarial networks Entropy Lesions

来源：评论

学校读者我要写书评

暂无评论

Anterior Cruciate Ligament Classification in Knee MRI using Automated Pseudo-Masking

Anterior Cruciate Ligament Classification in Knee MRI using ...

引用

Medical Imaging 2023: Computer-Aided Diagnosis

作者： Dadsetan, Saba Albers, Marcio Weinstock, Allison Musahl, Volker Kitamura, Gene Arefan, Dooman Wu, Shandong Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA15213 United States Department of Radiology School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Biomedical Informatics School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Bioengineering School of Engineering University of Pittsburgh PittsburghPA15213 United States Department of Orthopedic Surgery School of Medicine University of Pittsburgh PittsburghPA15213 United States Department of Radiology Loma Linda University Medical Center Loma LindaCA92354 United States

ISBN: (纸本)9781510660359

Anterior cruciate ligament (ACL) is one of the most common injuries associated with sports. Knee osseous morphology can play a role in increased knee instability. Our hypothesis is that the morphological features of the knee, as seen in knee osseous morphology, can contribute to increased knee instability and, thus, increase the likelihood of ACL tear. To test this relationship, it is necessary to segment the femur and tibia bones and extract relevant imaging features. However, manual annotation of 3D medical images, such as on magnetic resonance imaging (MRI) scans, can be a time-consuming and challenging task. In this work, we propose an automated pipeline for creating pseudo-masks of the femur and tibia bones in knee MRI. Our approach involves unsupervised segmentation and deep learning models to classify ACL integrity (intact or torn). Our results demonstrate a high agreement between the automated pseudo-masks and a radiologist's manual segmentation, which also leads to comparable AUC values for the ACL integrity classification. © 2023 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automated Microorganism Classification: A Study on the Influence of Compression, Non-Uniform Scaling, and Data Augmentation Using Deep Learning

SSRN

引用

SSRN 2024年

作者： Boukouvalas, Dimitria Theophanis Bissaco, Márcia A.S. Dellê, Humberto Deana, Alessandro M. Belan, Peterson A. de Araújo, Sidnei Alves Universidade Nove de Julho Informatics and Knowledge Management Graduate Program Rua Vergueiro 235/249 SP São Paulo01504-001 Brazil Universidade de Mogi das Cruzes Biomedical Engineering Graduate Program Av. Dr. Cândido Xavier de Almeida e Souza 200 Mogi das Cruzes SP São Paulo08780-911 Brazil Universidade Nove de Julho Medicine Graduate Program Rua Vergueiro 235/249 SP São Paulo01504-001 Brazil

With the advent of "Laboratory 4.0", a concept that represents the recent technological breakthroughs in laboratory automation, there is an increasing demand for solutions that can automate, standardize, and enhance the accuracy and speed of microorganism classification. One promising approach is the use of convolutional neural networks (CNNs), a powerful deep learning technique that has shown significant results in biomedical image analysis. However, its application in microorganism classification is still nascent mainly due to the unavailability of extensive datasets, which is a basic requirement to ensure generalization ability in learning CNNs. This study aims to fill a significant gap in the literature by exploring the influence of factors such as image compression, non-uniform scaling, and data augmentation on the performance of CNNs, specifically when using small image datasets of microorganisms. We focus on two CNN architectures, AlexNet and DenseNet-121, which have shown promising results in previous microorganism classification studies. Our experiments reveal that certain factors like the type of data compression and non-uniform scaling applied to the images can negatively impact the performance of CNNs. On the other hand, data augmentation techniques such as mirroring, rotation, and noise addition can enhance their performance. By utilizing training datasets and optimized parameters based on our findings, we were able to achieve classification accuracies of 98.61% and 99.82% with AlexNet and DenseNet-121, respectively, surpassing the results reported in current state-of-the-art studies. This research has significant implications for Laboratory 4.0, potentially reducing dataset preparation and CNN training time, lowering computational costs, and improving the consistency and accuracy of microorganism classification. It paves the way for more efficient and accurate microorganism classification methods in automated laboratories. © 2024, The Authors. All righ

关键词： Classification (of information)

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：