检索结果-内蒙古大学图书馆

Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study

BMC medical Imaging 2024年第1期24卷 92页

作者： Chang, Joseph Lin, Bo-Ru Wang, Ti-Hao Chen, Chung-Ming Department of Biomedical Engineering College of Medicine and College of Engineering National Taiwan University No. 1 Sec. 1 Jen-Ai Road Taipei 100 Taipei 100 Taiwan EverFortune.AI Co. Ltd Taichung Taiwan The Data Science Degree Program College of Electrical Engineering and Computer Science National Taiwan University and Academia Sinica Taipei Taiwan Department of Radiation Oncology China Medical University Hospital Taichung Taiwan Department of Medicine China Medical University Taichung Taiwan

Background: The study aimed to develop and validate a deep learning-based computer Aided Triage (CADt) algorithm for detecting pleural effusion in chest radiographs using an active learning (AL) framework. This is aimed at addressing the critical need for a clinical grade algorithm that can timely diagnose pleural effusion, which affects approximately 1.5 million people annually in the United States. Methods: In this multisite study, 10,599 chest radiographs from 2006 to 2018 were retrospectively collected from an institution in Taiwan to train the deep learning algorithm. The AL framework utilized significantly reduced the need for expert annotations. For external validation, the algorithm was tested on a multisite dataset of 600 chest radiographs from 22 clinical sites in the United States and Taiwan, which were annotated by three U.S. board-certified radiologists. Results: The CADt algorithm demonstrated high effectiveness in identifying pleural effusion, achieving a sensitivity of 0.95 (95% CI: [0.92, 0.97]) and a specificity of 0.97 (95% CI: [0.95, 0.99]). The area under the receiver operating characteristic curve (AUC) was 0.97 (95% DeLong’s CI: [0.95, 0.99]). Subgroup analyses showed that the algorithm maintained robust performance across various demographics and clinical settings. Conclusion: This study presents a novel approach in developing clinical grade CADt solutions for the diagnosis of pleural effusion. The AL-based CADt algorithm not only achieved high accuracy in detecting pleural effusion but also significantly reduced the workload required for clinical experts in annotating medical data. This method enhances the feasibility of employing advanced technological solutions for prompt and accurate diagnosis in medical settings. © The Author(s) 2024.

关键词： Active learning Chest radiographs Deep learning Pleural effusion X-rays

来源：评论

学校读者我要写书评

暂无评论

Integration of Government Regulations to Anticipate the Threat of Terrorism with Radioactive and Nuclear Technology 8

Integration of Government Regulations to Anticipate the Thre...

引用

8th IEEE International Conference on Computing, Engineering and Design, ICCED 2022

作者： Agustina, Mega Wijiyanti, Rika Mantoro, Teddy State Intelligence College Medical Intelligence Post-graduate Program Bogor Indonesia Sampoerna University and State Intelligence College Media-Tech Lab Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665453899

The development of science and technology is currently experiencing rapid progress, starting in the fields of energy, oil, non-destructive testing, health, agriculture, and other fields. The use of radioactive substances in the health sector is used for radiotherapy, nuclear medicine, and radiodiagnostics. The use of excess nuclear and radioactive substances can endanger living things and the environment. Monitoring and supervision of the use of these elements are very needed in order to avoid their utilization for non-peaceful purposes, such as terrorism. Nowadays, terrorist attacks in Indonesia began to evolve from the use of conventional explosives to the use of chemical, biological, radioactive, and nuclear materials. The data shows that during the period 2011-2019, there have been six attempted terror attacks using chemical, biological, radioactive, and nuclear elements. This paper examines the role of ministries/agencies in anticipating the use of nuclear and radioactive substances for terrorism. Based on the results of the library study, there are several ministries/agencies that have protocols for handling terrorism attacks that use chemical, biological, radioactive, and nuclear elements, but they are still sectoral. Therefore, it can be concluded that the integration of the regulations/protocols in handling terrorist attacks by using nuclear and radioactive elements are needed in order to increase the monitoring and supervision of the handling of radioactive waste. In addition, it is necessary to add the RPM tools to prevent the misuse of radioactive substances and nuclear materials by irresponsible parties. © 2022 IEEE.

关键词： Terrorism

来源：评论

学校读者我要写书评

暂无评论

Patient Data Security in Telemedicine Services from Data Misuse in Health Practice 8

Patient Data Security in Telemedicine Services from Data Mis...

引用

8th IEEE International Conference on Computing, Engineering and Design, ICCED 2022

作者： Yuninda, Sinka Puji Aga Pasma, Satriani Mantoro, Teddy State Intelligence College Medical Intelligence Post-graduate Program Bogor Indonesia Sampoerna University and State Intelligence College Media-Tech Lab Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665453899

Misuse of a person's data can be found anywhere because of a lack of knowledge about how to manage data and secure it properly. The rapid development of information technology, creates various activities easily, including in the health sector. In the field of health itself, there is a long-distance consultation using various applications that facilitate long-distance relationships between doctors and patients, known as telemedicine. However, the emergence of this development does not deny the existence of cybermedicine. Cyber medicine is the dissemination of clinical and non-clinical patient information that can be misused for personal gain that can harm others. This can be used in telemedicine, all online-based, so there is a possibility of data leakage. The authors want to examine the extent of data protection for patients who use telemedicine services. This study was conducted using a literature review method taken from articles related to telemedicine. Therefore, there is a need for regulations to provide legal protection for victims who experience theft of personal data by providing certainty in the management of data and information, especially the management of personal data. If the data is not managed properly and appropriately, it will lead to abuse and cybercriminal attacks. © 2022 IEEE.

关键词： Hospital data processing

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study of Semi-supervised Intrusion Detection Systems for Industrial Control Systems 10

Feasibility Study of Semi-supervised Intrusion Detection Sys...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Loo, Fu-Nie Chen, Tung-Shou Tsai, Chia-Wei Lin, Jason Yang, Chun-Wei National Taichung University of Science and Technology Department of Computer Science and Information Engineering No.129 Sec.3 Sanmin Rd. North Dist. Taichung City404 Taiwan National Chung Hsing University Department of Computer Science and Engineering 145 Xingda Rd. South Dist. Taichung City402202 Taiwan China Medical University Master Program for Digital Health Innovation No. 100 Sec. 1 Jingmao Rd. Beitun Dist. Taichung City406040 Taiwan

ISBN: (纸本)9798350394924

Industrial Control systems (ICS) automate industrial processes but also introduces cybersecurity threats. Intrusion Detection System (IDS) are crucial for detecting cyber-attacks on ICS, yet zero-day attacks are often inefficiently detecting with supervised learning. This study employs semi-supervised learning using one-class SVM, isolation forest, and Local Outlier Factor (LOF), to train IDS models. Utilizing dataset collected from a self-build virtual ICS environment, the study demonstrates the feasibility of these models in detecting common attack like Injection, ARP, and Man-in-the-Middle. © 2024 IEEE.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Pediatric and Adults Brain MRI with Generative Model 46

Anomaly Detection in Pediatric and Adults Brain MRI with Gen...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Chen, Chaojun Namdar, Khashayar Wagner, Matthias W. Ertl-Wagner, Birgit B. Khalvati, Farzad Department of Mechanical and Industrial Engineering University of Toronto Canada Institute of Medical Science University of Toronto Canada Neurosciences & Mental Health Research Program SickKids Research Institute TorontoON Canada Department of Diagnostic & Interventional Radiology The Hospital for Sick Children TorontoON Canada Department of Diagnostic and Interventional Neuroradiology University Hospital Augsburg Germany Department of Medical Imaging University of Toronto Canada Department of Computer Science University of Toronto Canada Vector Institute TorontoON Canada

ISBN: (纸本)9798350371499

Magnetic Resonance Imaging (MRI) serves as a valuable tool for detecting abnormalities in brain structures. However, a notable 5-10% of pathologies remain unnoticed in MRI scans. To address this challenge and reduce the burden on radiologists, machine learning methods have been used to automate anomaly detection. In this work, we propose to use Denoising Diffusion Probabilistic Model (DDPM) for anomaly detection in MRI. DDPM learns to reconstruct healthy brain MRI and generates anomaly maps to facilitate the classification of the input MRI as healthy or unhealthy. The proposed model correctly differentiated all healthy or unhealthy test patients. Additionally, localized regions of interest in the generated anomaly maps, and the diffusion model achieved a Dice coefficient of 0.376, outperforming other generative models such as generative adversarial network (GAN). © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Benefits and drawbacks of radiofrequency ablation via percutaneous or minimally invasive surgery for treating hepatocellular carcinoma

引用

World Journal of Gastrointestinal Surgery 2024年第11期16卷 3400-3407页

作者： Ching-Lung Hsieh Cheng-Ming Peng Chun-Wen Chen Chang-Hsien Liu Chih-Tao Teng Yi-Jui Liu Department of Computer Science and Information Engineering Feng Chia UniversityTaichung 40724Taiwan Department of Surgery Chung Shan Medical University HospitalTaichung 40201Taiwan School of Medicine Chung Shan Medical UniversityTaichung 40201Taiwan Department of Radiology Taichung Armed Forces General HospitalTaichung 406Taiwan Department of Medical Imaging and Radiological Sciences Central Taiwan University of Science and TechnologyTaichung 406Taiwan Department of Radiology School of MedicineNational Defense Medical CenterTaipei 11490Taiwan Department of Medical Imaging China Medical University Hsinchu Hospital and China Medical UniversityHsinchu 302Taiwan Institute of Nuclear Engineering and Science National Tsing Hua UniversityHsinchu 300Taiwan Department of Radiology Nantou Hospital of the Ministry of Health and WelfareNantou 540Taiwan Master’s Program of Biomedical Informatics and Biomedical Engineering Feng Chia UniversityTaichung 407Taiwan Department of Automatic Control Engineering Feng Chia UniversityTaichung 407Taiwan

The management of early stage hepatocellular carcinoma(HCC)presents significant *** radiofrequency ablation(RFA)has shown safety and effectiveness in treating HCC,with lower mortality rates and shorter hospital stays,its high recurrence rate remains a significant ***,achieving improved survival solely through RFA is challenging,particularly in retrospective studies with inherent *** is commonly used for guiding percutaneous RFA,but its low contrast can lead to missed tumors and the risk of HCC *** enhance the efficiency of ultrasound-guided percutaneous RFA,various techniques such as artificial ascites and contrast-enhanced ultrasound have been developed to facilitate complete tumor *** invasive surgery(MIS)offers advantages over open surgery and has gained traction in various surgical *** studies suggest that laparoscopic intraoperative RFA(IORFA)may be more effective than percutaneous RFA in terms of survival for HCC patients unsuitable for surgery,highlighting its ***,combining MIS-IORFA with these enhanced percutaneous RFA techniques may hold greater significance for HCC treatment using the MIS-IORFA *** article reviews liver resection and RFA in HCC treatment,comparing their merits and proposing a trajectory involving their combination in future therapy.

关键词： Percutaneous radiofrequency ablation Minimally invasive surgery Hepatocellular carcinoma Intraoperative radiofrequency ablation Contrast-enhanced ultrasound

来源：评论

学校读者我要写书评

暂无评论

Improving Interpretability of Radiology Report-based Pediatric Brain Tumor Pathology Classification and Key-phrases Extraction Using Large Language Models

Improving Interpretability of Radiology Report-based Pediatr...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Zhao, Chen Kudus, Kareem Ketabi, Sara Namdar, Khashayar Wagner, Matthias W. Ertl-Wagner, Birgit B. Khalvati, Farzad University of Toronto Department of Mechanical and Industrial Engineering TorontoON Canada Neurosciences & Mental Health Research Program Research Institute The Hospital for Sick Children TorontoON Canada Institute of Diagnostic and Interventional Neuroradiology University Hospital Augsburg Germany The Hospital for Sick Children Department of Diagnostic & Interventional Radiology TorontoON Canada University of Toronto Department of Medical Imaging TorontoON Canada University of Toronto Department of Computer Science TorontoON Canada Institute of Medical Science University of Toronto TorontoON Canada

ISBN: (纸本)9798350351552

Radiology reports are crucial for bridging the expertise of radiologists and other clinicians. Machine Learning models trained on these reports have shown promising performance in various downstream clinical tasks, such as predicting the necessity of future follow-up procedures, based on past radiology reports. However, for clinicians to adopt these models and for radiologists to validate the results, interpretability of the model is essential. In this study, we train BERT models on radiology reports to classify pediatric brain tumor pathologies. These large language models enable accurate report-level classification, without the need for costly word-level annotations. To identify and extract keywords and key-phrases related to distinct pathologies from radiology reports, we used a modified Term Frequency-Inverse Document Frequency to determine phrase importance based on prevalence and attributions scores. We achieved an overall multiclass Area Under Receiver Operating Characteristic Curve (AUROC) of 79.57% using ClinicaiBERT. Moreover, the per-class AUROC values were 86%, 71.2%, and 81.5%, for 'Pilocytic Astrocytoma', 'Low-Grade Astrocytoma', and 'Other' pathologies, respectively. Our explainability analysis identified hypotonia and mesencephalon as the most important terms for 'Pilocytic Astrocytoma' and 'Low-Grade Astrocytoma', respectively. © 2024 IEEE.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Updating Clinical Risk Stratification Models Using Rank-Based Compatibility: Approaches for Evaluating and Optimizing Clinician-Model Team Performance 8

Updating Clinical Risk Stratification Models Using Rank-Base...

引用

8th Machine Learning for Healthcare Conference, MLHC 2023

作者： Ötles, Erkin Denton, Brian T. Wiens, Jenna Medical Scientist Training Program University of Michigan Ann ArborMI United States Department of Industrial and Operations Engineering University of Michigan Ann ArborMI United States Division of Computer Science and Engineering University of Michigan Ann ArborMI United States

As data shift or new data become available, updating clinical machine learning models may be necessary to maintain or improve performance over time. However, updating a model can introduce compatibility issues when the behavior of the updated model does not align with user expectations, resulting in poor user-model team performance. Existing compatibility measures depend on model decision thresholds, limiting their applicability in settings where models are used to generate rankings based on estimated risk. To address this limitation, we propose a novel rank-based compatibility measure, CR, and a new loss function that aims to optimize discriminative performance while encouraging good compatibility. Applied to a case study in mortality risk stratification leveraging data from MIMIC, our approach yields more compatible models while maintaining discriminative performance compared to existing model selection techniques, with an increase in CR of 0.019 (95% confidence interval: 0.005, 0.035). This work provides new tools to analyze and update risk stratification models used in clinical care. © 2023 E. Ötles., B.T. Denton & J. Wiens.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Leveraging EEG Signals and Machine Learning for Schizophrenia Classification

Leveraging EEG Signals and Machine Learning for Schizophreni...

引用

Computing and Informatics (ICCI), International Conference on

作者： Abdelrahman Elfarsy Sara El-Metwally Medical Informatics Program Faculty of Computers and Information Mansoura University Mansoura Egypt Computer Science Department Faculty of Computers and Information Mansoura University Mansoura Egypt

Schizophrenia is a neurological disorder known for its potential to disrupt brain function and cause erratic behavior. Timely diagnosis and intervention are crucial for improving patient outcomes. This paper conducts a comprehensive comparative study of three machine learning models: Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) to classify EEG signals associated with schizophrenia. The dataset utilized in this study comprises EEG data obtained from 28 individuals, data preprocessing techniques, including artifact removal, filtering, and normalization, were applied to enhance data quality. A set of informative statistical features was extracted from the EEG signals to capture relevant information. The three machine learning models are trained and evaluated using various performance metrics, including accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). Random Forest achieved the highest accuracy (96 % ), while SVM demonstrated strong precision and recall (95 % ). These findings highlight the potential of machine learning in aiding early schizophrenia diagnosis through EEG signal analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benefits and Threats of Telemedical Application in Psychiatric Services

Benefits and Threats of Telemedical Application in Psychiatr...

引用

Technology, Engineering, and Computing Applications (ICTECA), International Conference on

作者： Farra Martaningga Teddy Mantoro Djoko Andoko Postgraduate Program of Medical Intelligence National Intelligence College Bogor Indonesia Department of Computer Science Sampoerna University Jakarta Indonesia

Health development is one part of national development. Telemedical is an innovation in engineering and computing application technology healthcare in the era of society 5.0 is needed as a supporting tool. The purpose of this paper is to explain the benefits and threats of using telemedicine in the field of psychiatry in the care system. This study uses a qualitative descriptive method, data collection by literature study, which is a method that explains a phenomenon regarding the benefits and threats of telemedicine in psychiatric services. Telepsychiatry is a health service carried out by mental medicine specialists using information and communication technology to diagnose, treat and estimate the patient’s health condition in accordance with their ability and authority as evidenced by the validity of the Registration Certificate (STR) and Practice Permit (SIP) while maintaining service quality and patient safety. Telepsychiatry is carried out by mental medicine specialists with other doctors, or mental medicine specialists with patients in a Health Service Facility (Fasyankes), or between Fasyankes. As a result of the dialogue, Telepsychiatry has demonstrated significant cost-effectiveness and efficiency as a viable option to conventional psychiatric services, increasing accessibility for patients seeking providers. Innovative advances in the field of mental healthcare technology solutions have the potential to provide substantial benefits to recipients and stakeholders. Threats to telemedicine, including telepsychiatry, include misuse of patients’ personal data by employees or hacking by cybercriminals for purposes that jeopardise the security of patients and the country. Special attention should be paid to the problem of misuse and hacking of patient data in telemedicine by individuals and hackers.

关键词：

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：