检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

6,555 篇 会议
92 篇 期刊文献
20 册 图书

馆藏范围

6,667 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,952 篇 工学
- 2,178 篇 计算机科学与技术...
- 1,739 篇 软件工程
- 1,601 篇 生物医学工程（可授...
- 871 篇 生物工程
- 706 篇 信息与通信工程
- 610 篇 电气工程
- 465 篇 光学工程
- 460 篇 化学工程与技术
- 413 篇 电子科学与技术（可...
- 350 篇 控制科学与工程
- 309 篇 仪器科学与技术
- 286 篇 材料科学与工程（可...
- 253 篇 机械工程
- 150 篇 动力工程及工程热...
- 132 篇 力学（可授工学、理...
2,354 篇 理学
- 1,019 篇 数学
- 1,006 篇 生物学
- 675 篇 物理学
- 452 篇 化学
- 279 篇 统计学（可授理学、...
- 144 篇 系统科学
1,012 篇 医学
- 805 篇 临床医学
- 803 篇 基础医学(可授医学...
- 566 篇 药学(可授医学、理...
- 175 篇 公共卫生与预防医...
- 151 篇 中西医结合
- 118 篇 医学技术（可授医学...
657 篇 管理学
- 357 篇 图书情报与档案管...
- 317 篇 管理科学与工程(可...
- 177 篇 工商管理
117 篇 农学
77 篇 法学
70 篇 教育学
69 篇 经济学
9 篇 军事学
7 篇 文学
1 篇 历史学

主题

219 篇 biomedical imagi...
216 篇 biomedical engin...
158 篇 bioinformatics
127 篇 image segmentati...
126 篇 humans
107 篇 feature extracti...
104 篇 accuracy
103 篇 magnetic resonan...
102 篇 biomedical monit...
93 篇 monitoring
85 篇 electroencephalo...
85 篇 educational inst...
83 篇 proteins
82 篇 mathematical mod...
78 篇 computational mo...
78 篇 electrodes
78 篇 testing
68 篇 data mining
66 篇 diseases
65 篇 computed tomogra...

机构

15 篇 college of chemi...
14 篇 suzhou institute...
14 篇 institute for he...
13 篇 school of biomed...
12 篇 department of bi...
11 篇 school of biomed...
10 篇 chitkara univers...
9 篇 school of inform...
9 篇 jerusalem colleg...
9 篇 department of bi...
9 篇 department of bi...
8 篇 school of inform...
8 篇 school of biomed...
8 篇 sino-dutch biome...
8 篇 department of bi...
8 篇 sathyabama insti...
8 篇 department of bi...
8 篇 graduate school ...
8 篇 school of inform...
8 篇 college of infor...

作者

17 篇 li-min zhu
14 篇 anburajan m.
13 篇 c. branford-whit...
12 篇 m anburajan
11 篇 kanna r. kishore
11 篇 yan li
10 篇 yan wang
9 篇 jian yang
9 篇 shen dinggang
9 篇 zhang yu
8 篇 lei wang
8 篇 wilson stephen j...
8 篇 yan kang
8 篇 xiaoming wu
8 篇 yang wei
8 篇 foo jong yong a.
8 篇 wan-xi peng
8 篇 li wei
7 篇 wei liu
7 篇 harris margaret-...

语言

6,565 篇 英文
95 篇 其他
7 篇 中文

检索条件"任意字段=3rd International Conference on Bioinformatics and Biomedical Engineering"

共 6667 条记录，以下是61-70 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Human Activity Recognition Using Wearable Sensors in IoT Environments: Challenges and Opportunities 3

Human Activity Recognition Using Wearable Sensors in IoT Env...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Singh, B.P. Baxi, Paramjit Parhi, Manoranjan Ahluwalia, Gunveen Sollapur, Shrishail B. Divakaran, Sindu Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Centre for Data Sciences Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi174103 India Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331542375

One of those applications, Human Activity Recognition, uses wearable sensors, made possible by the rapid rise and development of Internet of Things technology. HAR is the automated process of identifying and classifying human activities from sensor data with wearable devices such as smart watches/fabric bands. Given its utility in healthcare, HAR has immense possibilities, especially within IOT environments such as health & fitness, safety, and security. But, at the same time, it introduces new challenges of handling massive real-time sensor data streams and providing privacy for people when their daily routines are reconstructed, as well as developing accurate and reliable algorithms. In addition, human activities are diverse, and the data that sensors collect may also differ, making HAR in IOT very complicated. HAR can also provide various opportunities, e.g., real-time monitoring and analysis of human activities, personalized health/fitness advice, and safe/smart environmental improvements. Implementing artificial intelligence and machine learning models in HAR can also improve performance. HAR based on wearable sensors in an IOT environment holds promise for changing our views of and tracking human activities to a new level that could be applied to many different sectors and improve quality of life. © 2025 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

The Effects of Balance and Strength on Thermal Heatmap 3rd

The Effects of Balance and Strength on Thermal Heatmap

引用

3rd international conference on Artificial Intelligence over Infrared Images for Medical Applications, AIIIMA 2024

作者： Besnili, Şeyda Dinkul, İlayda Bayrak, Ahmet Çevik, Mahmut Ceylan, Murat Faculty of Engineering and Natural Sciences The Department of Electrical and Electronics Engineering Konya Technical University Konya Turkey AIVISIONTECH Electronic Software Inc. Konya Turkey Selcuk University Vocational School of Health Science Konya Turkey

ISBN: (纸本)9783031765834

This study examines the effects of balance and strength on the thermal heat map. Participants' thermal temperature values, isokinetic values and balance values were taken in a specific measurement procedure and the relationship between them was statistically analyzed. All processes were carried out under the supervision of a physiotherapist. According to the statistical results we obtained, a significant relationship was found between isometric strength and thermal temperature values in hamstring group muscles. The relationship between isometric force and thermal temperature map of the hamstring group muscles is important in terms of showing that the hamstring muscle group should be prioritized in the analysis of thermal evaluations of basketball athletes. In addition, a significant relationship was found between balance parameters and temperature values in vastus lateralis and ankle. The thermal finding we observed in the vastus lateralis muscle and ankle region in terms of balance parameters, in addition to the evaluation of ankle injury risks of basketball athletes, has raised suspicion that the frequency of knee injuries is adaptively loaded by the vastus lateralis muscle and especially knee injuries occur as a result of this adaptation. From this point of view, it provides evidence that thermal analysis is a useful tool in the analysis of injury mechanisms and injury risks in understanding the most common ankle and knee injuries in basketball. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Basketball

来源：评论

学校读者我要写书评

暂无评论

Advancements in IoT and Sensor-Enabled Wearable Devices for Healthcare Applications 3

Advancements in IoT and Sensor-Enabled Wearable Devices for ...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Chowdhury, Srijit Kaur, Ashmeet Spoorthi, B. Prince, P. Grace Kanmani Agarwal, Trapty Vashisht, Nitish Centre for Cyber Security Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi India Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Biomedical Engineering Tamil Nadu Chennai India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India

ISBN: (纸本)9798331542375

Technology has changed how healthcare is delivered- we now have the Internet of Things and sensor-enabled wearable devices today. These improvements have dramatically improved patient results by allowing actual pursuing then data analysis, translating to more customized health care being presented earlier. Linked strategies such as smart watches and suitability chasers have enabled medicinal professionals to access a patient's status remotely. These devices monitor energetic symbols, action stages, and sleeping patterns, provided actual alerts intended for early-stage recognition of fitness problems then chronic and chronic ailments remotely. Such technology facilitates uninterrupted patient-healthcare provider communication, ensuring prompt aid and better interaction. Furthermore, using AI and MI in these devices leads to better analytics for physicians' treatment options. Sensor-enabled wearable have reminded and tracked patients to better comply with treatment plans. This translates into tangible improvements in health and economic outcomes. The healthcare division has experienced an essential alteration owing to the evolution of the IOI and sensor-enabled wearable devices, bringing about better care to patients worldwide and moving one step towards predictive, personalized health. The possibilities these devices offer for changing healthcare are seemingly endless, and as technology gets more advanced, they will continue evolving. © 2025 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Evaluating Radiomics Feature Reduction for Thyroid Nodule Segmentation in Thermal Imaging 3rd

Evaluating Radiomics Feature Reduction for Thyroid Nodule Se...

引用

3rd international conference on Artificial Intelligence over Infrared Images for Medical Applications, AIIIMA 2024

作者： Etehadtavakol, Mehdi Etehadtavakol, Mahnaz Moallem, Golnaz Ng, Eddie Y. K. Student Research Committee School of Medicine Shahid Beheshti University of Medical Sciences Tehran Iran School of Medicine Shahid Beheshti University of Medical Sciences Tehran*** Iran Department of Medical Physics School of Medicine Isfahan University of Medical Sciences Isfahan81745-33871 Iran Medical Image and Signal Processing Research Center Isfahan University of Medical Sciences Isfahan81746-73461 Iran Postdoctoral Research Fellow Stanford School of Medicine Palo AltoCA United States School of Mechanical and Aerospace Engineering College of Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

ISBN: (纸本)9783031765834

Radiomics encompasses a variety of image attributes, including intensity, texture, shape, and spatial relationships among pixels. In this study, we applied four feature selection techniques: Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Recursive Feature Elimination (RFE), to reduce the dimensionality of radiomic features extracted from thyroid thermal images. Subsequently, we employed three models: U-Net with a VGG16 backbone, U-Net with ResNet50 backbone, and U-Net with DenseNet121 backbone to segment thyroid nodules. The U-Net with a VGG16 backbone combined with the LDA model achieved an average Dice coefficient of 0.4035, significantly outperforming the other models. These results highlight the potential of feature reduction techniques in enhancing thyroid nodule segmentation in thermal imaging. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature Reduction Thermal Imaging Thyroid Nodule Segmentation

来源：评论

学校读者我要写书评

暂无评论

Do Sites Benefit Equally from Distributed Learning in Medical Image Analysis? 2nd

Do Sites Benefit Equally from Distributed Learning in Medi...

引用

2nd international Workshop on Fairness of AI in Medical Imaging, FAIMI 2024, and 3rd international Workshop on Ethical and Philosophical Issues in Medical Imaging, EPIMI 2024, Held in Conjunction with the international conference on Medical Image Computing and Computer Assisted Interventions, MICCAI 2024

作者： Souza, Raissa Stanley, Emma A. M. Camicioli, Richard Monchi, Oury Ismail, Zahinoor Wilms, Matthias Forkert, Nils D. Department of Radiology Cumming School of Medicine University of Calgary Calgary Canada Hotchkiss Brain Institute University of Calgary Calgary Canada Biomedical Engineering Graduate Program University of Calgary Calgary Canada Alberta Children’s Hospital Research Institute University of Calgary Calgary Canada University of Alberta Edmonton Canada Department of Radiology Radio-oncology and Nuclear Medicine Université de Montréal Montréal Canada Centre de Recherche Institut Universitaire de Gériatrie de Montréal Montréal Canada Department of Clinical Neurosciences Cumming School of Medicine University of Calgary Calgary Canada Department of Psychiatry University of Calgary Calgary Canada Clinical and Biomedical Sciences Faculty of Health and Life Sciences University of Exeter Exeter United Kingdom Department of Pediatrics University of Calgary Calgary Canada Department of Community Health Sciences University of Calgary Calgary Canada

ISBN: (纸本)9783031727863

Artificial intelligence (AI) has the potential to make medical image analysis more accessible to healthcare institutions worldwide. However, when trained on multi-site datasets, models may excel with data from certain institutions but struggle with others, even when exposed to their training data. This emphasizes the importance of investigating whether all sites benefit from AI models, especially within distributed learning setups. Distributed learning methods allow access to broader and more diverse datasets from multiple sites during training. In this context, the travelling model (TM) paradigm has demonstrated superior performance in limited data scenarios, making it particularly relevant in low-resource settings. This work investigates whether all sites can benefit from TM development and identifies the factors influencing performance disparities. Specifically, a Parkinson’s disease (PD) database comprising 1,817 neuroimaging datasets from 83 different sites is utilized to investigate how site-specific and participant-specific factors influence the performance of TM in classifying PD. Therefore, we analyze the false positive rate (FPR) and false negative rate (FNR) to identify the characteristics contributing to misdiagnosis. Our findings reveal disparities in benefits across sites, with class imbalance emerging as the major factor influencing FPR and FNR, especially for sites with more PD cases. This research underscores the urgency of a rigorous analysis of a model’s behaviour in distributed setups to detect misdiagnosis risks and encourage developers to evaluate and optimize models beyond overall accuracy. Thus, comprehensive analyses of this type can help pave the way for the development of more equitable AI-based medical imaging models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generation of Cell-Painted Nuclei Structures from Brightfield Images Using Residual-WGAN Model 3rd

Generation of Cell-Painted Nuclei Structures from Brightfiel...

引用

3rd international conference on Emerging Electronics and Automation, E2A 2023

作者： Aravindan, Abhinav Anthiyur Palanisamy, Rohini Department of Electronics and Communication Engineering Indian Institute of Information Technology Design and Manufacturing Kancheepuram Tamil Nadu Chennai India

ISBN: (纸本)9789819768011

Cell painting is a high-content morphological assay, with a wide range of applications particularly in the field of pharmacology, contributing significantly to the advancement of biomedical research. The prediction of cell painting from brightfield images facilitates rapid analysis and identification of cellular features across numerous samples. This study aims to generate nuclei cell-painted images from corresponding brightfield images using deep learning methods to extract visual information, thus eliminating the need for expensive equipment and the staining process associated with the cell painting assay. A Conditional Generative Adversarial Network (GAN) with Wasserstein loss and Gradient Penalty (GP) is utilized, comprising a U-Net generator along with a ResNet attention input, and a patch discriminator. The brightfield images are fed as input to the ResNet. The output of the ResNet, along with the brightfield images, is then fed into the U-Net model to generate the nuclei cell painting. The evaluation of the predicted images reveals promising results, with a Mean Absolute Error (MAE) value of 0.21, Mean Square Error (MSE) value of 0.34, Structural Similarity Index Measure (SSIM) value of 0.66, and a Peak Signal to Noise Ratio (PSNR) value of 53.42. These metrics collectively demonstrate a notable enhancement compared to the current industry-standard (Cross-Zamirski et al, Label-free prediction of cell painting from brightfield images, 2022). Thus, the framework comprising a Residual WGAN architecture is proposed for the generation of cell-painted nuclei images from brightfield microscopy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Assessment of Range of Motion Before and After Hamstring Percussion Therapy Using Thermography and CNN 3rd

Assessment of Range of Motion Before and After Hamstring Per...

引用

3rd international conference on Artificial Intelligence over Infrared Images for Medical Applications, AIIIMA 2024

作者： Vilchis-Yubi, Alejandra Cedeno-Moreno, Rogelio Espino-Gonzalez, Julio A. Mancilla-Morales, Alberto Morales-Hernandez, Luis A. Cruz-Albarran, Irving A. Engineering Faculty Campus Aeropuerto Autonomous University of Queretaro Ejido Bolaños Queretaro Santiago de Queretaro76140 Mexico Laboratory of Artificial Vision and Thermography/Mechatronics Faculty of Engineering Autonomous University of Queretaro Campus San Juan del Rio San Juan del Rio76807 Mexico Physical Therapy Polytechnic University of Santa Rosa de Jauregui Santa Rosa Jauregui Queretaro Santiago de Queretaro76220 Mexico

ISBN: (纸本)9783031765834

Percussion therapy has positive effects on the human body, such as increasing strength, improving range of motion and flexibility. This is due to the vibrations it produces, which when applied to the human body, cause vasodilatory responses. The main contribution of this work is a methodology based on infrared thermography and convolutional neural network to evaluate and classify the range of motion in patients undergoing hamstring percussion therapy. It consists of three steps: (1) data preparation, (2) data augmentation, and (3) convolutional neural network design and validation. In the data preparation step, 50 images acquired in the pre- and post-percussion therapy phases were pooled, and then each image was labeled in one of the two classes: Within and outside range of motion. Data augmentation, including techniques such as flipping and contrast adjustment, was used to expand the dataset. A convolutional neural network model was used to classify the images. When evaluated on a test set, an accuracy of 90.48% was obtained for the classification of 2 classes. These results demonstrate the efficacy and robustness of the approach to assess range of motion in patients undergoing hamstring percussion therapy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Normative Modeling with Focal Loss and Adversarial Autoencoders for Alzheimer’s Disease Diagnosis and Biomarker Identification 3rd

Normative Modeling with Focal Loss and Adversarial Autoenc...

引用

3rd international Workshop on Applications of Medical Artificial Intelligence, AMAI 2024 held in conjunction with the 27th international conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Zhao, Songlin Zhou, Rong Zhang, Yu Chen, Yong He, Lifang Department of Computer Science and Engineering Lehigh University BethlehemPA United States Department of Bioengineering Lehigh University BethlehemPA United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania PhiladelphiaPA United States

ISBN: (纸本)9783031820069

In this paper, we introduce a novel normative modeling approach that incorporates focal loss and adversarial autoencoders (FAAE) for Alzheimer’s Disease (AD) diagnosis and biomarker identification. Our method is an end-to-end approach that embeds an adversarial focal loss discriminator within the autoencoder structure, specifically designed to effectively target and capture more complex and challenging cases. We first use the enhanced autoencoder to create a normative model based on data from healthy control (HC) individuals. We then apply this model to estimate total and regional neuroanatomical deviation in AD patients. Through extensive experiments on the OASIS-3 and ADNI datasets, our approach significantly outperforms previous state-of-the-art methods. This advancement not only streamlines the detection process but also provides a greater insight into the biomarker potential for AD. Our code can be found at https://***/soz223/FAAE. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fair and Private CT Contrast Agent Detection 2nd

Fair and Private CT Contrast Agent Detection

引用

作者： Kaess, Philipp Ziller, Alexander Mantz, Lea Rueckert, Daniel Fintelmann, Florian J. Kaissis, Georgios AI in Healthcare and Medicine Technical University of Munich Munich Germany Department of Radiology Massachusetts General Hospital Boston United States Department of Diagnostic and Interventional Radiology University Medical Center of the Johannes Gutenberg University Mainz Mainz Germany Department of Computing Imperial College London London United Kingdom Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Germany

ISBN: (纸本)9783031727863

Intravenous (IV) contrast agents are an established medical tool to enhance the visibility of certain structures. However, their application substantially changes the appearance of Computed Tomography (CT) images, which - if unknown - can significantly deteriorate the diagnostic performance of neural networks. Artificial Intelligence (AI) can help to detect IV contrast, reducing the need for labour-intensive and error-prone manual labeling. However, we demonstrate that automated contrast detection can lead to discrimination against demographic subgroups. Moreover, it has been shown repeatedly that AI models can leak private training data. In this work, we analyse the fairness of conventional and privacy-preserving AI models during the detection of IV contrast on CT images. Specifically, we present models which are substantially fairer compared to a previously published baseline. For better comparability, we extend existing metrics to quantify the fairness of a model on a protected attribute in a single value. We provide a model, fulfilling a strict Differential Privacy protection of (Ε,δ)=(8,2.8·10-3), which with an accuracy of 97.42% performs 5%-points better than the baseline. Additionally, while confirming prior works, that strict privacy preservation increases the discrimination against underrepresented subgroups, the proposed model is fairer than the baseline over all metrics considering race and sex as protected attributes, which extends to age for a more relaxed privacy guarantee. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Cycle-GANs Generated Difference Maps to Interpret Race Prediction from Medical Images 2nd

Cycle-GANs Generated Difference Maps to Interpret Race Pred...

引用

作者： Rathi, Lakshika Nebbia, Giacomo Chang, Ken Kumar, Sourav Gupta, Aarushi Ahmed, Syed Rakin Patel, Jay Clark, Christopher Veturi, Yoga Advaith Coyner, Aaron Rana, Aakanksha Bridge, Christopher McNamara, Stephen Campbell, J. Peter Li, Matthew Kalpathy-Cramer, Jayashree Singh, Praveer Indian Institute of Technology Delhi Delhi India University of Colorado Anschutz Medical Campus AuroraCO United States Athinoula A. Martinos Center for Biomedical Imaging BostonMA United States Harvard University CambridgeMA United States Massachusetts Institute of Technology CambridgeMA United States Oregon Health And Science University PortlandOR United States Massachusetts General Hospital BostonMA United States University of Alberta EdmontonAB Canada

ISBN: (纸本)9783031727863

Recent research has revealed the remarkable ability of artificial intelligence (AI) to identify features related to an individual’s self-reported race in medical images, but what such features may be remains an unanswered question. In this work, we aim to identify image regions relevant to race prediction. We argue that previous methods toward this goal (namely, occlusion maps) are not sufficient as they are unable to locate such regions, and we propose to use Cycle-GANs as an alternative. Specifically, we train a Race-specific Cycle-GAN to artificially transform images from patients of one race to images from patients of a different race. We then obtain difference maps by computing the pixel-wise difference between original and transformed image. Difference maps highlight pixels whose values are crucial for an image to be considered as belonging to a patient of a specific race. Additionally, we examine whether such regions are gender dependent by subgrouping our analysis for male and female patients. We show how difference maps are able to identify relevant image regions when previously introduced methods fail, and that, while some differences do exist between genders, the relevant regions mainly overlap. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： difference maps interpretability race prediction

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 3 4 5 6 7 8 9 10 11 12 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：