检索结果-内蒙古大学图书馆

Computer Sciences, Engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Nur Adhianti Heryanto Mahmud Isnan Matthew Martianus Henry Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

Many studies have focused on classifying lung nodules in CT scans, primarily utilizing 2D approaches. However, CT scans are inherently 3D representations, which presents challenges for traditional convolutional neural networks (CNNs) designed for 2D images. In this work, a novel combination of 3D transfer learning and batch oversampling was adopted to classify benign and malignant lung nodules using the Lung Nodule Analysis - Intelligent Systems in Medical Imaging (LUNA22-ISMI) dataset. The preprocessing pipeline consisted of excluding indeterminate labeled nodules, clamping patches to the lung window, extracting nodule regions based on diameter, and applying z-score normalization. Batch oversampling with augmentation was implemented for the training set. Multiple models pre-trained on ImageNet with weights adapted for 3D were evaluated using a five-fold cross-validation setup. Notably, EfficientNetB1 achieved the highest overall and balanced metrics on the test sets, surpassing 90% in sensitivity, specificity, precision, and accuracy, highlighting its potential for binary classification of lung nodules. https://***/nheryanto/luna22

关键词： Training Solid modeling Adaptation models Three-dimensional displays Lungs Computed tomography Transfer learning Windows Cancer Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

InDRI: Intelligent Diagnosis Radiology Images 6

InDRI: Intelligent Diagnosis Radiology Images

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Isnan, Mahmud Elwirehardja, Gregorius Natanael Nugroho, Kuncahyo Setyo Ritonga, Imelda Liana Gultom, Roby Pahala Januario Lubis, Elida Afni Pardamean, Bens Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Universitas Imelda Medan Indonesia Medan20238 Indonesia Universitas Imelda Medan Indonesia Medan20238 Indonesia Clinical Pathology Unit Rumah Sakit Imelda Pekerja Indonesia Medan20239 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

The need for an early screening and Computer-Aided Diagnosis (CAD) system based on Artificial Intelligence (AI) for the field of radiology is essential to realize considering the large impact of lung diseases globally. However, developing AI requires a lot of data, which is a challenge because data in the health sector tends to be limited in quantity and has disparities between diagnostic categories (data imbalance). To overcome this issue, DINO ViT models was trained with the publicly available COVID-19 Radiography Database in our previous study. The model was subsequently implemented into a web application, with this study focusing on the development of a prototype for the application. The study found this application can be useful for medical personnel and doctors in carrying out early screening and CAD. Meanwhile, it also highlighted the general unfamiliarity with AI applications among medical staff, emphasizing the need for increased education and training on AI's role in healthcare. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Computational Approach for Elucidating a Nonstructural Protein Interaction in Dengue Virus 2

引用

Procedia Computer Science 2024年 245卷 470-479页

作者： Alam Ahmad Hidayat Rudi Nirwantono Bens Pardamean Mathematics Department School of Computer Science Bina Nusantara University Indonesia 11480 Biotechnology Department Faculty of Engineering Bina Nusantara University Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia 11480

As the dengue infection still impacts hundreds of millions of people globally, unprecedented efforts in dengue drug development have been more progressive in recent decades. Computational methods provide a fast, sustainable, and efficient screening of active compounds and newly created drug molecules, including those specifically targeting nonstructural proteins (NS) of dengue viruses. In this work, protein modeling for the NS proteins of DENV-2/16681 strain was performed using a template-based homology modeling for the NS3 protein and an Artificial Intelligence (AI)-based prediction via AlphaFold for the NS4B protein. Moreover, the protein-protein interaction between the two structures was predicted using the HADDOCK server, which employs information about active and passive residues of the interaction interface to guide the docking process. After the modeling and its respective refinement process, the predicted structures of NS3 and NS4B improved their steric clashing scoring from MolProbity assessment. The refined models were then docked, and the resulting docking pose was analyzed to extract the interacting residues based on the polar contacts within the interface of the two proteins. Our result presents a preliminary study to create a dataset related to in silico molecular interactions of the NS3-NS4B interaction of different DENV types. It is helpful for building a computational pipeline for elucidating protein-ligand problems in dengue drug screenings.

关键词： bioinformatics computational biology dengue protein docking structural biology

来源：评论

学校读者我要写书评

暂无评论

Optimized Neuron Tracing Using Post Hoc Reanalysis

Optimized Neuron Tracing Using Post Hoc Reanalysis

引用

IEEE International Symposium on Biomedical Imaging

作者： Sara Azzouz Logan A. Walker Alexandra Doerner Kellie L. Geisel Arianna K. Rodríguez Rivera Ye Li Douglas H. Roossien Dawen Cai EECS University of Michigan Biophysics University of Michigan Bioinformatics Michigan Medicine Department of Biology Ball State University Biology Program Yale University Cell and Developmental Biology Michigan Medicine Michigan Neuroscience Institute University of Michigan

Over the last decade, the advances in Brainbow labeling allowed labeling hundreds of neurons with distinct colors in the same field of view of a brain [1], [2]. Reconstruction (or "tracing") of the 3D structures of these images has been enabled by a growing set of software tools for automatic and manual annotation. It is common, however, to have errors introduced by heuristics used by tracing software, namely that they assume the "best" path is the highest intensity one, a more pertinent issue when dealing with multicolor microscope images. Here, we report nCorrect, an algorithm for correcting this error by reanalyzing previously created neuron traces to produce more physiologically-relevant ones. Specifically, we use a four dimensional minimization algorithm to identify a more-optimal reconstruction of the image, allowing us to better take advantage of existing manual tracing results. We define a new metric (hyperspectral cosine similarity) for describing the similarity of different neuron colors to each other. Our code is available in an open source license and forms the basis for future improved neuron tracing software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nuclear Factor I/A Controls A-fiber Nociceptor Development

引用

Neuroscience Bulletin 2020年第7期36卷 685-695页

作者： Lu Qi Guangjuan Yin Yongchao Zhang Yeqi Tao Xiaohua Wu Richard M.Gronostajski Mengsheng Qiu Yang Liu College of Life Sciences Zhejiang UniversityHangzhou 310058China Zhejiang Key Laboratory of Organ Development and Regeneration Institute of Life SciencesHangzhou Normal UniversityHangzhou 310036China Department of Biochemistry Program in GeneticsGenomics and BioinformaticsCenter of Excellence in Bioinformatics and Life SciencesState University of New York at BuffaloBuffaloNY 14203USA

Noxious mechanical information is transmitted through molecularly distinct nociceptors,with pinprickevoked sharp sensitivity via A-fiber nociceptors marked by developmental expression of the neuropeptide Y receptor 2(Npy2 r)and von Frey filament-evoked punctate pressure information via unmyelinated C fiber nociceptors marked by ***,the molecular programs controlling their development are only beginning to be *** we demonstrate that Npy2 r-expressing sensory neurons are in fact divided into two groups,based on transient or persistent Npy2 r ***2 r-transient neurons are myelinated,likely including A-fiber nociceptors,whereas Npy2 r-persistent ones belong to unmyelinated pruriceptors that co-express *** then showed that the transcription factors NFIA and Runx1 are necessary for the development of Npy2 r-transient A-fiber nociceptors and MrgprD^+C-fiber nociceptors,***,mice with conditional knockout of Nfia,but not Runx1 showed a marked attenuation of pinprick-evoked nocifensive *** studies therefore identify a transcription factor controlling the development of myelinated nociceptors.

关键词： Dorsal root ganglion Acute pain Pinprick pain Npy2r Nppb Nociceptor A-fiber mechanonociceptor

来源：评论

学校读者我要写书评

暂无评论

Deciphering the Binding Mode and Structural Perturbations in Floxuridine-Human Serum Albumin Complexation with Spectroscopic, Microscopic, and Computational Techniques

SSRN

引用

SSRN 2023年

作者： Tayyab, Saad Rehman, Fazal Abubakar, Mujaheed Wahidah Ridzwan, Nor Farrah Mohamad, Saharuddin B. Abd. Halim, Adyani Azizah Biochemistry Program Institute of Biological Sciences Faculty of Science Universiti Malayaand Malaysia Bioinformatics Program Institute of Biological Sciences Faculty of Science Universiti Malaya Malaysia Department of Oral and Craniofacial Sciences Faculty of Dentistry Universiti Malaya Malaysia Department of Pharmaceutical Chemistry Faculty of Pharmaceutical Sciences UCSI University Kuala Lumpur Malaysia

The binding mode of antineoplastic antimetabolite, floxuridine (FUDR), with human serum albumin (HSA), the leading carrier in blood circulation, was ascertained using multi-spectroscopic, microscopic, and computational techniques. A static fluorescence quenching was established due to decreased Ksv values with rising temperatures, suggesting FUDR-HSA complexation. UV-vis absorption spectral results also supported this conclusion. The binding constant, Ka values, were found within 9.6-7.9 × 103 M-1 at 290, 300, and 310 K, demonstrating a moderate binding affinity for the FUDR-HSA system. Thermodynamic data (ΔS = +46.35 ***-1.K-1 and ΔH = -8.77 ***-1) predicted the nature of stabilizing forces (hydrogen-bonds, hydrophobic, and van der Waals interactions) for the FUDR-HSA complex. Circular dichroism spectra displayed a minor disruption in the protein’s 2o and 3o structures. At the same time, atomic force microscopy images proved variations in the FUDR-HSA surface morphology, confirming its complex formation. The protein's microenvironment around Trp/Tyr residues was also modified, as judged by 3-D fluorescence spectra. FUDR-bound HSA showed better resistance against thermal stress. As disclosed from ligand displacement studies, the FUDR binding site was placed in subdomain IIA (Site I). Further, the molecular docking analysis corroborated the competing displacement studies. Molecular dynamics evaluations revealed that the complex achieved equilibrium during simulations, confirming the FUDR–HSA complex's stability. © 2023, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory-based Models for Sleep Quality Prediction from Wearable Device Time Series Data

引用

Procedia Computer Science 2023年 227卷 1062-1069页

作者： Alam Ahmad Hidayat Arif Budiarto Bens Pardamean Mathematics Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Several studies suggest that sleep quality is associated with physical activities. Moreover, deep sleep time can be used to determine the sleep quality of an individual. In this work, we aim to find the association between physical activities and deep sleep time by modeling the time series data such as heart rate and a number of steps captured from a commercial wearable device. Our previous study demonstrates that deep learning-based time series modeling is well suited for our problem since the temporal patterns in the two physical parameters need to be captured to obtain more accurate results. We first preprocess our series data to have a time-step size of 10 minutes. To improve our previous effort in this modeling, we compare four different variants of Long Short-Term Memory (LSTM)-based models, ranging from single input to dual input models. Our result shows that the simple stacked LSTM model performs better for our data because the remaining models suffer from overfitting due to a larger number of the trained parameters.

关键词： deep learning forecasting sleep quality time series wearable devices

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of deep learning models for detecting face mask 7

Comparative analysis of deep learning models for detecting f...

引用

7th International Conference on Computer Science and Computational Intelligence, CSCI 2022

作者： Ramadhan, M. Vickya Muchtar, Kahlil Nurdin, Yudha Oktiana, Maulisa Fitria, Maya Maulina, Novi Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-The-Art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-Trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification. © 2022 Elsevier B.V.. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Variance estimation for the average treatment effects on the treated and on the controls

arXiv

引用

arXiv 2022年

作者： Matsouaka, Roland A. Liu, Yi Zhou, Yunji Department of Biostatistics and Bioinformatics Duke University DurhamNC United States Program for Comparative Effectiveness Methodology Duke Clinical Research Institute DurhamNC United States

Common causal estimands include the average treatment effect (ATE), the average treatment effect of the treated (ATT), and the average treatment effect on the controls (ATC). Using augmented inverse probability weighting methods, parametric models are judiciously leveraged to yield doubly robust estimators, i.e., estimators that are consistent when at least one the parametric models is correctly specified. Three sources of uncertainty are associated when we evaluate these estimators and their variances, i.e., when we estimate the treatment and outcome regression models as well as the desired treatment effect. In this paper, we propose methods to calculate the variance of the normalized, doubly robust ATT and ATC estimators and investigate their finite sample properties. We consider both the asymptotic sandwich variance estimation, the standard bootstrap as well as two wild bootstrap methods. For the asymptotic approximations, we incorporate the aforementioned uncertainties via estimating equations. Moreover, unlike the standard bootstrap procedures, the proposed wild bootstrap methods use perturbations of the influence functions of the estimators through independently distributed random variables. We conduct an extensive simulation study where we vary the heterogeneity of the treatment effect as well as the proportion of participants assigned to the active treatment group. We illustrate the methods using an observational study of critical ill patients on the use of right heart catherization. Copyright © 2022, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Overlap, matching, or entropy weights: what are we weighting for?

arXiv

引用

arXiv 2022年

There has been a recent surge in statistical methods for handling the lack of adequate positivity when using inverse probability weights (IPW). However, these nascent developments have raised a number of questions. Thus, we demonstrate the ability of equipoise estimators (overlap, matching, and entropy weights) to handle the lack of positivity. Compared to IPW, the equipoise estimators have been shown to be flexible and easy to interpret. However, promoting their wide use requires that researchers know clearly why, when to apply them and what to expect. In this paper, we provide the rationale to use these estimators to achieve robust results. We specifically look into the impact imbalances in treatment allocation can have on the positivity and, ultimately, on the estimates of the treatment effect. We zero into the typical pitfalls of the IPW estimator and its relationship with the estimators of the average treatment effect on the treated (ATT) and on the controls (ATC). Furthermore, we also compare IPW trimming to the equipoise estimators. We focus particularly on two key points: What fundamentally distinguishes their estimands? When should we expect similar results? Our findings are illustrated through Monte-Carlo simulation studies and a data example on healthcare expenditure. Copyright © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

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：