检索结果-内蒙古大学图书馆

ieee International conference on Big Data

作者： Francesco Casadei Luciana Carota Gianluca Asti Saverio D’Amico Davide Piscia Santiago Zazo Patricia A. Apellániz Juan Parras Claudia Sala Cesare Rollo Nono S. C. Merleau Piero Fariselli Matteo Della Porta Tiziana Sanavia Federico Alvarez Garcia Gastone Castellani Enrico Giampieri IRCCS Istituto Delle Scienze Neurologiche di Bologna Bologna Italy Department of Medical and Surgical Sciences University of Bologna Bologna Italy Humanitas Clinical and Research Center IRCCS Milan Italy Centro Nacional de Análisis Genómico Barcelona Spain Information Processing and Telecommunications Center ETS Ingenieros de Telecomunicación Universidad Politécnica de Madrid Madrid Spain Department of Medical Sciences Computational Biomedicine Unit Turin Italy Max Planck Institute for Mathematics in the Sciences of Leipzig Leipzig Germany Department of Medical and Surgical Sciences University of Bologna IRCCS Azienda Ospedaliero-Universitaria di Bologna Bologna Italy

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Federated Learning is an emerging, powerful approach that allows training an artificial intelligence model in distributed setting. Two survival models, Cox and DeepSurv, have been trained in a federated setting, exploiting both code simulations and real experiments on the new platform, developed by the GenoMed4All consortium. Different scenarios have been tested by splitting a Myelodysplastic Syndrome dataset into three nodes and performing feature removal. A significant gain in model performance has been observed due to federated aggregation.

关键词： Training Codes Federated learning Genomics Data models Reliability bioinformatics Standards Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Approach for Evaluating Disease Focus and Interpretability of Deep Learning Models for Alzheimer’s Disease Classification

A Quantitative Approach for Evaluating Disease Focus and Int...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Thomas Yu Chow Tam Litian Liang Ke Chen Haohan Wang Wei Wu Dept. of Health Information Management University of Pittsburgh Pittsburgh PA USA Computational Biology Department Carnegie Mellon University Pittsburgh PA USA School of Information Sciences University of Illinois Urbana-Champaign Urbana USA School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Deep learning (DL) models have shown significant potential in Alzheimer’s Disease (AD) classification. However, understanding and interpreting these models remains challenging, which hinders the adoption of these models in clinical practice. Techniques such as saliency maps have been proven effective in providing visual and empirical clues about how these models work, but there still remains a gap in understanding which specific brain regions DL models focus on and whether these brain regions are pathologically associated with *** bridge such gap, in this study, we developed a quantitative disease-focusing strategy to first enhance the interpretability of DL models using saliency maps and brain segmentations; then we propose a disease-focus (DF) score that quantifies how much a DL model focuses on brain areas relevant to AD pathology based on clinically known MRI-based pathological regions of AD. Using this strategy, we compared several state-of-the-art DL models, including a baseline 3D ResNet model, a pretrained MedicalNet model, and a MedicalNet with data augmentation to classify patients with AD vs. cognitive normal patients using MRI data; then we evaluated these models in terms of their abilities to focus on disease-relevant regions. Our results show interesting disease-focusing patterns with different models, particularly characteristic patterns with the pretrained models and data augmentation, and also provide insight into their classification performance. These results suggest that the approach we developed for quantitatively assessing the abilities of DL models to focus on disease-relevant regions may help improve the interpretability of these models for AD classification and facilitate their adoption for AD diagnosis in clinical practice. The code is publicly available at https://***/Liang-lt/ADNI.

关键词： Deep learning Solid modeling Pathology Visualization Biological system modeling Brain modeling Data augmentation Data models Alzheimer's disease Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Dissect: detection and characterization of novel structural alterations in transcribed sequences

引用

bioinformatics 2012年第12期28卷 I179-I187页

作者： Yorukoglu, Deniz Hach, Faraz Swanson, Lucas Collins, Colin C. Birol, Inanc Sahinalp, S. Cenk Simon Fraser Univ Sch Comp Sci Burnaby BC V5A 1S6 Canada MIT Comp Sci & Artificial Intelligence Lab Cambridge MA 02139 USA Canc Agcy Michael Smith Genome Sci Ctr Vancouver BC V5Z 4S6 Canada Univ British Columbia Vancouver Prostate Ctr Vancouver BC V5Z 1M9 Canada Univ British Columbia Dept Urol Sci Vancouver BC V5Z 1M9 Canada

Motivation: computational identification of genomic structural variants via high-throughput sequencing is an important problem for which a number of highly sophisticated solutions have been recently developed. With the advent of high-throughput transcriptome sequencing (RNA-Seq), the problem of identifying structural alterations in the transcriptome is now attracting significant attention. In this article, we introduce two novel algorithmic formulations for identifying transcriptomic structural variants through aligning transcripts to the reference genome under the consideration of such variation. The first formulation is based on a nucleotide-level alignment model;a second, potentially faster formulation is based on chaining fragments shared between each transcript and the reference genome. Based on these formulations, we introduce a novel transcriptome-to-genome alignment tool, Dissect (DIScovery of Structural Alteration Event Containing Transcripts), which can identify and characterize transcriptomic events such as duplications, inversions, rearrangements and fusions. Dissect is suitable for whole transcriptome structural variation discovery problems involving sufficiently long reads or accurately assembled contigs. In this article, we introduce two novel algorithmic formulations for identifying transcriptomic structural variants through aligning transcripts to the reference genome under the consideration of such variation. The first formulation is based on a nucleotide-level alignment model;a second, potentially faster formulation is based on chaining fragments shared between each transcript and the reference genome. Based on these formulations, we introduce a novel transcriptome-to-genome alignment tool, Dissect (DIScovery of Structural Alteration Event Containing Transcripts), which can identify and characterize transcriptomic events such as duplications, inversions, rearrangements and fusions. Dissect is suitable for whole transcriptome structural variation d

关键词： NUCLEOTIDE sequence MOLECULAR structure GENOMICS GENETIC transcription ALGORITHMS VARIATION (biology)

来源：评论

学校读者我要写书评

暂无评论

Segmentation for SAR Image Based on a New Spectral Clustering Algorithm

Segmentation for SAR Image Based on a New Spectral Clusterin...

引用

2010 International conference on Life System Modeling and Simulation & 2010 International conference on Intelligent Computing for Sustainable Energy and Environment

作者： Li-Li Liu 1,2, Xian-Bin Wen 1,2 and Xing-Xing Gao 1,2, 1 Key Laboratory of Computer Vision and System of Ministry of Education, Tianjin University of Technology, 300191, Tianjin, China 2 Tianjin Key Laboratory of intelligence Computing and Novel Software Technology 300191 Tianjin, China

A new spectral clustering (SC) algorithm with Nystrm method is proposed for SAR image segmentation in this paper. The proposed algorithm differs from previous approaches in that not only with Nystrm method are employed for alleviating the computational and storage burdens of the SC algorithm, but also a new similarity function is constructed by combining the pixel value and the spatial location of each pixel to depict the intrinsic structure of the original SAR image better. Our algorithm and the classic spectral clustering algorithm with Nystrm method are evaluated using the real-world SAR images. The results demonstrate the running time and the error rate of the proposed approach and the classic spectral clustering algorithm with Nystrm method.

关键词： Image segmentation, spectral clustering (SC), synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Construction of a genetic AND gate under a new standard for assembly of genetic parts

引用

BMC GENOMICS 2010年第Sup4期11卷 S16-S16页

作者： Ayukawa, Shotaro Kobayashi, Akio Nakashima, Yusaku Takagi, Hidemasa Hamada, Shogo Uchiyama, Masahiko Yugi, Katsuyuki Murata, Satoshi Sakakibara, Yasubumi Hagiya, Masami Yamamura, Masayuki Kiga, Daisuke Tokyo Inst Technol Interdisciplinary Grad Sch Sci & Engn Dept Computat Intelligence & Syst Sci Midori Ku Kanagawa 2268503 Japan Keio Univ Dept Biosci & Informat Kanagawa 2238522 Japan Tohoku Univ Dept Bioengn & Robot Sendai Miyagi 9808579 Japan Univ Tokyo Grad Sch Informat Sci & Technol Dept Comp Sci Tokyo 1138656 Japan JST PRESTO Kawaguchi Saitama 3320012 Japan

Background: Appropriate regulation of respective gene expressions is a bottleneck for the realization of artificial biological systems inside living cells. The modification of several promoter sequences is required to achieve appropriate regulation of the systems. However, a time-consuming process is required for the insertion of an operator, a binding site of a protein for gene expression, to the gene regulatory region of a plasmid. Thus, a standardized method for integrating operator sequences to the regulatory region of a plasmid is required. Results: We developed a standardized method for integrating operator sequences to the regulatory region of a plasmid and constructed a synthetic promoter that functions as a genetic AND gate. By standardizing the regulatory region of a plasmid and the operator parts, we established a platform for modular assembly of the operator parts. Moreover, by assembling two different operator parts on the regulatory region, we constructed a regulatory device with an AND gate function. Conclusions: We implemented a new standard to assemble operator parts for construction of functional genetic logic gates. The logic gates at the molecular scale have important implications for reprogramming cellular behavior.

关键词： Regulatory Region Synthetic biology Operator Part High Fluorescence Intensity Synthetic Promoter

来源：评论

学校读者我要写书评

暂无评论

Description and Composition of Bio-inspired Design Patterns: The Gossip Case

Description and Composition of Bio-inspired Design Patterns:...

引用

ieee Workshop on Engineering of Autonomic and Autonomous Systems (EASE)

作者： Jose Luis Fernandez-Marquez Josep Lluis Arcos Giovanna Di Marzo Serugendo Matteo Casadei IIIA Artificial Intelligence Research Institute Spanish Scientific Research Council CSIC Catalonia Spain Centre Universitaire d'Informatique Universita de Genève Switzerland Dipartimento di Elettronica Informatica e Sistemistica Alma Mater Studiorum Università di Bologna Italy

Today's software applications increasingly feature a great deal of openness, dynamism and unpredictable behavior, forcing to shift design and engineering from traditional, centralized approaches to nature-inspired, self-organizing techniques. Among the others, biology has been adopted as a source of inspiration to solve some of the issues proper of nowadays systems by self-organizing techniques, usually exploited in an ad-hoc way. As a result, little or no effort has been made to clearly describe and classify these techniques in terms of design patterns, preventing them from being systematically applied to solve recurrent problems. Correspondingly, this paper is targeted at modeling bio-inspired mechanisms in terms of design patterns, arguing that some fundamental biological behavior can play the role of basic design patterns to define higher-level patterns featuring more complex behavior and interaction. In this way, we aim at easing both the creation of new mechanisms from adaptation of existing ones, and the classification of the biological behaviors underlying each pattern. The viability of this approach is exemplified through the description of two bio-inspired mechanisms, aggregation and spreading, taken as basic design patterns to define gossip as a composite design pattern.

关键词： Organisms computational modeling Biological system modeling Software Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

SimICL: A Simple Visual In-context Learning Framework for Ultrasound Segmentation

SimICL: A Simple Visual In-context Learning Framework for Ul...

引用

Annual International conference of the ieee Engineering in Medicine and biology Society (EMBC)

作者： Yuyue Zhou Banafshe Felfeliyan Shrimanti Ghosh Jessica Knight Fatima Alves-Pereira Christopher Keen Jessica Küpper Abhilash Rakkunedeth Hareendranathan Jacob L. Jaremko Department of Radiology and Diagnostic Imaging University of Alberta Edmonton Canada Department of Biomedical Engineering University of Alberta Edmonton Canada

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning (ICL) is a new and exciting area of research in computer vision. Unlike conventional deep learning, ICL emphasizes the model's ability to adapt to new tasks based on given examples quickly. Inspired by MAE-VQGAN, we proposed a new simple visual ICL method called SimICL, combining visual ICL pairing images with masked image modeling (MIM) designed for self-supervised learning. We validated our method on bony structures segmentation in a wrist ultrasound (US) dataset with limited annotations, where the clinical objective was to segment bony structures to help with further fracture detection. We used a test set containing 3822 images from 18 patients for bony region segmentation. SimICL achieved an remarkably high Dice coeffient (DC) of 0.96 and Jaccard Index (IoU) of 0.92, surpassing state-of-the-art segmentation and visual ICL models (a maximum DC 0.86 and IoU 0.76), with SimICL DC and IoU increasing by at least 0.10 and 0.16 respectively. This remarkably high agreement with limited manual annotations indicates SimICL could be used for training AI models even on small US datasets. This could dramatically decrease the human expert time required for image labeling compared to conventional approaches, and enhance the real-world use of AI assistance in US image analysis.

关键词： Wrist Deep learning Visualization Image segmentation Adaptation models Ultrasonic imaging computational modeling Labeling Artificial intelligence Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Optimized Prediction of Extreme Treatment Outcomes in Ovarian Cancer

Optimized Prediction of Extreme Treatment Outcomes in Ovaria...

引用

ieee Annual conference on Decision and Control

作者： Burook Misganaw Eren Ahsen Nitin Singh Keith A. Baggerly Anna Unruh Michael A. White M. Vidyasagar Erik Jonsson School of Engineering and Computer Science The University of Texas at Dallas Richardson TX Department of Bioinformatics and Computational Biology M. D. Anderson Cancer Center Houston TX UT Graduate School of the Biomedical Sciences UT Southwestern Medical Center Dallas TX

ISBN: (纸本)9781479978878

The TCGA ovarian cancer database shows that about 10% of patients respond poorly to platinum-based chemotherapy, with tumors relapsing in seven months or less. At the other extreme, another 10% or so enjoy disease-free survival of three years or more [1]. At present there are more than a dozen prognostic signatures that claim to predict the survival prospects of a patient based on her genetic profile. Yet, according to [2], none of these signatures performs significantly better than pure guessing. Accordingly, in this paper the objective is to propose and validate another gene-based signature. TCGA ovarian cancer data is analyzed using the "lone star" algorithm [3] that is specifically developed for identifying a small number of highly predictive features from a very large set. Using this algorithm, we are able to identify a biomarker panel of 25 genes (out of 12,000) that can be used to classify patients into one of three groups: super-responders (SR), medium responders (MR), and non-responders (NR). We are also able to determine a discriminant function that can divide patients into two classes, such that there is a clear survival advantage of one group over the other. This signature is developed using the TCGA Agilent platform data, and cross-validated on the TCGA Affymetrix platform data, as well as entirely independent data due to Tothill et al. [4]. The P-value on the training data is below machine zero, while the P-values on cross-validation are well below the widely accepted threshold of 0.05.

关键词： Ovary Cancer Treatment Outcome signatures Patients p-Value cross-validation self retaining retractor

来源：评论

学校读者我要写书评

暂无评论

Duck Eggs Hatching Procedure with A Low Cost User Convenient Integrated Device for Developing Countries

Duck Eggs Hatching Procedure with A Low Cost User Convenient...

引用

ieee Region 10 Humanitarian Technology conference (R10-HTC)

作者： Eftakhar Hossain Mohammad Zeyad S.M. Masum Ahmed Md Sadik Tasrif Anubhove Energy and Technology Research Division Advanced Bioinformatics Computational Biology and Data Science Laboratory Bangladesh Chattogram Bangladesh Erasmus+ Joint MSC in Smart Cities and Communities University of the Basque Country (UPV/EHU) Bilbao Spain

Poultry agriculture is a form of livestock farming that involves raising chickens, turkeys, ducks, etc, and raises them to provide eggs or meat. However, this work sheds light on the method of hatching duck eggs which maintains a suitable environment around the eggs through an automated and low cost device by controlling temperature (T) and relative humidity (RH). This paper presents a control strategy for automatic temperature and relative humidity control systems for the egg/s hatching procedure for rural areas people or unprivileged communities in the developing countries. One of the best outcomes of this work is the proper hatching procedure steps shown from the beginning to the end. Moreover, for a better understanding and outcomes, the research work has been done under a poultry farm in Charsita village, Lakshmipur, Bangladesh for 6 consecutive months of 2020. The experiment (egg/s hatching) has been conducted under an ice-box. Furthermore, a microcontroller (ATmega328p) is used to monitor the temperature and relative humidity by receiving data from the sensor DHT22 and manipulating the appropriate temperature and humidity using a logic algorithm code. Egg/s need a constant temperature and relative humidity of 35.6 °C to 37.8 °C and 60% to 80%, respectively. Nonetheless, an LCD (16*2) with a matrix keypad (4*4) has been integrated into the unit, allowing farmers to easily set, run, and monitor the appropriate temperature and relative humidity levels within the ice-box. Finally, the results of sensor testing, system device management, and performance rates are recorded to ensure the research's success.

关键词： Temperature sensors Temperature measurement Temperature distribution Costs Rural areas Humidity Developing countries

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Liver Diseases from P31 MRS Data Based on Feature Selection Using Genetic Algorithm

Diagnosis of Liver Diseases from P31 MRS Data Based on Featu...

引用

2010 International conference on Life System Modeling and Simulation & 2010 International conference on Intelligent Computing for Sustainable Energy and Environment

作者： Jinyong Cheng1 Yihui Liu1, Jun Sang1 , Qiang Liu2, Shaoqing Wang2 1 School of Computer Science and Information Technology, Shandong Institute of Light Industry, Jinan, Shandong, China, 250353 2 Department of Magnetic Resonance Imaging, Shandong Medical Imaging Research Institute Jinan, Shandong, China, 250021

P31 MRS technique is important either in diagnosis or in treatment of many hepatic diseases for it can provides non-invasive information about the chemical content of the energy metabolism in cellular level. The data samples from P31 MRS are classified into three types of hepatocellular carcinoma, hepatic cirrhosis and normal hepatic tissue using computational intelligence methods. A genetic algorithm is used as main feature selection method and the Gaussian model is selected in the mutation operation. Two classification algorithms are used which consist of fisher linear discriminant analysis and quadratic discriminant analysis. Experiments show that the application of genetic algorithm and fisher linear classifier offers more reliable information for diagnostic prediction of liver cancer in vivo. And when the cross-validation method is 10-fold model, this algorithm can improve the average recognition correction rate of three types to 94.28%.

关键词： Genetic algorighm, fisher linear classifier, hepatic cirrhosis, hepatocellular carcinoma, P31 MRS

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：