检索结果-内蒙古大学图书馆

4th International conference on Artificial intelligence in Information and Communication, ICAIIC 2022

作者： Agarwal, Deepesh Covarrubias-Zambrano, Obdulia Bossmann, Stefan Natarajan, Balasubramaniam Kansas State University Department of Electrical and Computer Engineering ManhattanKS United States The University of Kansas Medical Center Department of Cancer Biology Kansas CityKS United States

ISBN: (纸本)9781665458184

Cyber-Physical-Human Systems (CPHS) interconnect humans, physical plants and cyber infrastructure across space and time. Industrial processes, electromechanical systems operations and medical diagnosis are some examples where one can see the intersection of humans, physical and cyber components. Emergence of Artificial intelligence (AI) based computational models, controllers and decision support engines have improved the efficiency and cost effectiveness of such systems and processes. These CPHS typically involve a collaborative decision environment, comprising of AI-based models and human experts. Active Learning (AL) is a category of AI algorithms which aims to learn an efficient decision model by combining domain expertise of the human expert and computational capabilities of the AI model. Given the indispensable role of humans and lack of understanding about human behavior in collaborative decision environments, modeling and prediction of behavioral biases is a critical need. This paper, for the first time, introduces different behavioral biases within an AL context and investigates their impacts on the performance of AL strategies. The modelling of behavioral biases is demonstrated using experiments conducted on a real-world pancreatic cancer dataset. It is observed that classification accuracy of the decision model reduces by at least 20% in case of all the behavioral biases. © 2022 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

DistillMatch: Revisiting Self-Knowledge Distillation in Semi-Supervised Medical Image Segmentation

DistillMatch: Revisiting Self-Knowledge Distillation in Semi...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Chunshi Wang Bin Zhao Zhiyang Liu School of Artificial Intelligence Guilin University of Electronic Technology College of Electronic Information and Optical Engineering Nankai University

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Semi-supervised medical image segmentation still faces challenges although it is able to obtain better segmentation results using a small amount of labeled data and a large amount of unlabeled data. Despite the progress made by current methods in utilizing unlabeled data, they fail to exploit the full potential of labeled data in terms of improving model performance. In this paper, we propose a semi-supervised segmentation method, DistillMatch, that incorporates knowledge distillation and feature perturbation, which efficiently transfers knowledge between labeled and unlabeled data, thus making full use of the information of labeled data to improve segmentation results. DistillMatch consists of several key components: the Self-Training process based on knowledge distillation and feature perturbation, the Deterministic Knowledge Transfer (DKT) strategy, and the introduction of Teacher Assistant (TA), which work together to optimize model performance. Extensive experiments on two benchmark datasets demonstrate that our method outperforms the current state-of-the-art (SOTA) approaches, especially in terms of edge accuracy and model generalization capabilities. We also show how this performance improvement can be achieved without sacrificing computational efficiency through an effective multi-decoder implementation strategy. These experimental results not only demonstrate the effectiveness of our approach, but also highlight its practical value in medical image segmentation tasks. Code is available at https://***/AiEson/DistillMatch.

关键词： Image segmentation Perturbation methods Image edge detection computational modeling Benchmark testing Data models computational efficiency Knowledge transfer Faces Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Extracting Drug-Drug Interactions from Biomedical Texts Using BioBERT with Improved Focal Loss

Extracting Drug-Drug Interactions from Biomedical Texts Usin...

引用

ieee International conference on bioinformatics and computational biology (ICBCB)

作者： Weixin Xie Huirui Han Jiayu Xu Chengkui Zhao Tianyi Li Limei Wang Jin Li Weixing Feng College of Intelligent Systems and Engineering Harbin Engineering University Harbin China Key Laboratory of Tropical Translational Medicine of Ministry of Education Bioinformatics for Major Diseases Science Innovation Group College of Biomedical Informatics and Engineering Hainan Medical University Haikou China

Drug-drug interaction (DDIs) extraction has become a vital task for biomedical and clinical research and public health safety. There are many excellent and effective methods based on neural network models have been proposed on DDIs extraction task and achieved good performance. However, most of the previous models suffer from the serious problem of imbalance data, which can affect the relation extraction results. In this study, a bidirectional encoder representation from transformer pretrained on biomedical corpora (BioBERT) is applied to DDIs extraction from biomedical literature. After the semantic vectors are obtained to represent the entities in a sentence by BioBERT, the embeddings of two entities in a sentence are averaged into two vectors, concatenate the first token, and go through the fully connected layer with an activation operation. Then, we explore an improved focal loss function to dealing with the imbalance data. The performance of our proposed approach gets an F-score of 80.45% on the DDIExtraction 2013 and achieves a significant improvement over the methods of BioBERT with traditional cross-entropy loss function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Three-Step Framework for Automatically Registering Immunohistochemical and H&E Stained Whole Slide Images Targeting Clinical Applications

A Three-Step Framework for Automatically Registering Immunoh...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Yingjia Yang Yuan Wang Cheng Li Dehua Cao Baochuan Pang Hailian Xiao Junfeng Wang Juan Liu Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China Landing Artificial Intelligence Centre for Pathological Diagnosis Landing Intelligent Medicine Co. Ltd Wuhan China Wei County Maternal and Child Health Hospital Handan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Joint analysis of multiple biomarker images and tissue morphology plays an important role in disease diagnosis, treatment planning, and drug development. This necessitates precise cross-staining comparison among Whole Slide Images (WSIs) of immunohistochemical (IHC) and hematoxylin and eosin (H&E) stained microscopic slides. In this paper, we propose a novel three-step, feature-based, automatic cross-staining WSI alignment method to support clinical practice. The comparative and ablation experiments have shown the good performance of our method, suggesting that it can offer a simple and effective cross-staining WSIs alignment contributing to pathological diagnosis.

关键词： Deep learning Training Pathology computational modeling Microscopy Morphology Planning Medical diagnosis Immune system Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation of the Substantia Nigra in Susceptibility-Weighted Imaging of Non-Parkinson and Parkinson's Disease Patients

Automatic Segmentation of the Substantia Nigra in Susceptibi...

引用

ieee International conference on bioinformatics and computational biology (ICBCB)

作者： Helena Rico Pereira Hugo Alexandre Ferreira José Manuel Fonseca Faculdade de Ciências Instituto de Biofísica e Engenharia Biomédica Universidade de Lisboa Lisboa Portugal Centre of Technology and Systems UNINOVA Caparica Portugal Physics Department NOVA School of Science and Technology NOVA University of Lisbon Caparica Portugal Electrical and Computer Engineering Department NOVA School of Science and Technology NOVA University of Lisbon Caparica Portugal

ISBN: (数字)9798350375749

ISBN: (纸本)9798350375756

The loss of neurons in the substantia nigra (SN) is a pathological feature of Parkinson's disease (PD), but its segmentation in medical imaging is challenging. This study proposes an automatic method to segment Non-PD and PD patients' left and right SN in susceptibility-weighted images (SWI) and Magnitude SWI-derived images. The images used in this study were obtained from the NTUA Parkinson's disease database: 11 SWI image volumes (4 Non-PD and 7 PD) and 8 Magnitude image volumes (3 Non-PD and 5 PD). One Non-PD template was created per each image type to obtain a mask of the left and right SN. All images were registered to the respective template. The segmentation method consisted of setting a seed point based on the masks of 2D image slices created to perform a flood fill algorithm. The method's performance was evaluated using the dice similarity coefficient (DSC) between automatic and manual segmentation. The segmentation method achieved higher performance using the SWI images (DSC: SN $=0.684 \pm 0.182$ ; left SN $=0.722 \pm 0.137$ ; right SN: $0.664 \pm 0.226$ ) than using the Magnitude images (DSC: SN $=0.589 \pm 0.249$ ; left SN $=0.604 \pm 0.223$ ; right SN $=0.569 \pm$ 0.284), suggesting that the SWI images are more suitable for SN segmentation. Although not yet as effective as manual segmentation, the proposed method may aid in SN segmentation.

关键词： Image segmentation Pathology Parkinson's disease Databases Neurons Manuals Floods bioinformatics Biomedical imaging computational biology

来源：评论

学校读者我要写书评

暂无评论

PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding

PA-LLaVA: A Large Language-Vision Assistant for Human Pathol...

引用

ieee International conference on bioinformatics and Biomedicine (BIBM)

作者： Dawei Dai Yuanhui Zhang Long Xu Qianlan Yang Xiaojing Shen Shuyin Xia Guoyin Wang Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China Shanghai First Maternity and Infant Hospital School of Medicine Tongji University Shanghai China College of Computer and Information Science Chongqing Normal University Chongqing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The previous advancements in pathology image understanding primarily involved developing models tailored to specific tasks. Recent studies has demonstrated that the large vision-language model can enhance the performance of various downstream tasks in medical image understanding. In this study, we developed a domain-specific large language-vision assistant (PA-LLaVA) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domain-specific alignment; (2) Using the proposed image-text data, we first train a pathology language-image pretraining (PLIP) model as the specialized visual encoder for pathology image, and then we developed scale-invariant connector to avoid the information loss caused by image scaling; (3) We adopt two-stage learning to train PA-LLaVA, first stage for domain alignment, and second stage for end to end visual question & answering (VQA) task. In experiments, we evaluate our PA-LLaVA on both supervised and zero-shot VQA datasets, our model achieved the best overall performance among multimodal models of similar scale. The ablation experiments also confirmed the effectiveness of our design. We posit that our PA-LLaVA model and the datasets presented in this work can promote research in field of computational pathology. All codes are available at: https://***/ddw2AIGROUP2CQUPT/PA-LLaVA

关键词： Connectors Pathology Visualization Codes computational modeling Biological system modeling Data models Cleaning bioinformatics Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Endoscopic colorectal polyp detection based on improved YOLOv8

Endoscopic colorectal polyp detection based on improved YOLO...

引用

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

作者： Jincai Huang Jianyuan Zeng Jinfeng Peng Mengye Lyu Shaojun Liu College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Colorectal tumors typically arise from colorectal polyps and are commonly identified through colonoscopy during clinical examinations. Manual detection of polyps, crucial for distinguishing between benign and malignant cases, suffers from a limited detection rate of approximately 25%, influenced by subjective factors and other variables. This study leverages advancements in deep learning and computer detection technology to explore the application of artificial intelligence in polyp detection. Specifically, we employ an improved YOLOv8 model for polyp detection to boost the detection capabilities. The proposed method demonstrates superior accuracy and efficiency compared to existing artificial intelligence approaches.

关键词： Deformable models Deep learning Accuracy Convolution computational modeling Colonoscopy Object detection Manuals Artificial intelligence Engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

An Integrated Genomics Workflow Tool: Simulating Reads, Evaluating Read Alignments, and Optimizing Variant Calling Algorithms

An Integrated Genomics Workflow Tool: Simulating Reads, Eval...

引用

ieee International conference on bioinformatics and computational biology (ICBCB)

作者： Fathima Nuzla Ismail Shanika Amarasoma Information Science University of Otago Otago New Zealand Analytics & AI Department Axiata Digital Labs Colombo Sri Lanka

ISBN: (数字)9798350375749

ISBN: (纸本)9798350375756

Next-generation sequencing (NGS) is a pivotal technique in genome sequencing due to its high throughput, rapid results, cost-effectiveness, and enhanced accuracy. Its significance extends across various domains, playing a crucial role in identifying genetic variations and exploring genomic complexity. NGS finds applications in diverse fields such as clinical genomics, comparative genomics, functional genomics, and metagenomics, contributing substantially to advancements in research, medicine, and scientific disciplines. Within the sphere of genomics data science, the execution of read simulation, mapping, and variant calling holds paramount importance for obtaining precise and dependable results. Given the plethora of tools available for these purposes, each employing distinct methodologies and options, a nuanced understanding of their intricacies becomes imperative for optimization. This research, situated at the intersection of data science and genomics, involves a meticulous assessment of various tools, elucidating their individual strengths and weaknesses through rigorous experimentation and analysis. This comprehensive evaluation has enabled the researchers to pinpoint the most accurate tools, reinforcing the alignment between the established workflow and the demonstrated efficacy of specific tools in the context of genomics data analysis. To meet these requirements, “VarFind”, an open-source and freely accessible pipeline tool designed to automate the entire process has been introduced (VarFind GitHub repository: VarFinder.)

关键词： Sequential analysis Accuracy Translation Pipelines Genomics Standardization Data science Throughput bioinformatics Software development management

来源：评论

学校读者我要写书评

暂无评论

Emergence of Pathological Slow Waves due to Elevated Neurotransmitter Release

Emergence of Pathological Slow Waves due to Elevated Neurotr...

引用

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

作者： Md Ashfaq Ahmed Ranu Jung TD-Artificial Intelligence Baptist Health South Florida Miami FL USA The Institute for Integrative and Innovative Research (I3R) University of Arkansas Fayetteville AR USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

A physiologically based computational framework was used to develop a novel gastric motility network model. Along with the widely assumed electrical gap junction coupling between the pacemaker and muscle cells as well as the second messenger molecules, in this model we also included a rostro-caudal linear decreasing gradient of neural stimulus to the pacemakers along the length of the stomach to mimic enteric neurotransmitter release and an increasing gradient of muscarinic receptor density. We find that aberrant responses of different parts of the stomach (corpus, antrum etc.) to exogenous application of excitatory neurotransmitters such as Acetylcholine, can be explained by an interplay between the level of neurotransmitter and density of receptors available. This model can also explain anomalous behavior such as retrograde propagation and functional uncoupling in the entire stomach in response to external neuro-agonists.

关键词： Couplings Stomach Pathology Neurotransmitters computational modeling Pacemakers Muscles Physiology Junctions Engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

CEPZ: A Novel Predictor for Identification of DNase I Hypersensitive Sites

引用

ieee-ACM TRANSACTIONS ON computational biology AND bioinformatics 2021年第6期18卷 2768-2774页

作者： Zheng, Yan Wang, Hao Ding, Yijie Guo, Fei Tianjin Univ Sch Chem Engn & Technol Tianjin 300350 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Suzhou Univ Sci & Technol Sch Elect & Informat Engn Suzhou 215009 Jiangsu Peoples R China

DNase I hypersensitive sites (DHSs) have proven to be tightly associated with cis-regulatory elements, commonly indicating specific function on the chromatin structure. Thus, identifying DHSs plays a fundamental role in decoding gene regulatory behavior. While traditional experimental methods turn to be time-consuming and expensive, computational techniques promise to be practical to discovering and analyzing regulatory factors. In this study, we applied an efficient model that considered composition information and physicochemical properties and effectively selected features with a boosting algorithm. CEPZ, our predictor, greatly improved a Matthews correlation coefficient and accuracy of 0.7740 and 0.9113 respectively, more competitive than any predictor before. This result suggests that it may become a useful tool for DHSs research in the human and other complex genomes. Our research was anchored on the properties of dinucleotides and we identified several dinucleotides with significant differences in the distribution of DHS and non-DHS samples, which are likely to have a special meaning in the chromatin structure. The datasets, feature sets and the relevant algorithm are available at https://***/YanZheng-16/CEPZ_DHS/.

关键词： DNA Feature extraction Proteins Genomics Encoding Strain DNase I hypersensitive sites XGBoost dinucleotide human 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：