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

2,668 篇 会议
125 篇 期刊文献
89 册 图书

馆藏范围

2,881 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,383 篇 工学
- 2,165 篇 计算机科学与技术...
- 1,123 篇 生物医学工程（可授...
- 934 篇 软件工程
- 549 篇 光学工程
- 298 篇 生物工程
- 268 篇 电气工程
- 226 篇 电子科学与技术（可...
- 183 篇 信息与通信工程
- 164 篇 控制科学与工程
- 84 篇 仪器科学与技术
- 42 篇 核科学与技术
- 30 篇 力学（可授工学、理...
- 28 篇 化学工程与技术
- 24 篇 安全科学与工程
- 23 篇 机械工程
- 23 篇 动力工程及工程热...
- 20 篇 建筑学
1,834 篇 医学
- 1,359 篇 特种医学
- 1,008 篇 临床医学
- 402 篇 基础医学(可授医学...
- 299 篇 药学(可授医学、理...
- 209 篇 医学技术（可授医学...
- 30 篇 公共卫生与预防医...
692 篇 理学
- 355 篇 数学
- 354 篇 生物学
- 329 篇 物理学
- 111 篇 统计学（可授理学、...
- 45 篇 化学
108 篇 管理学
- 66 篇 图书情报与档案管...
- 44 篇 管理科学与工程(可...
9 篇 教育学
7 篇 农学
4 篇 经济学
2 篇 法学

主题

330 篇 image segmentati...
127 篇 image registrati...
116 篇 deep learning
110 篇 magnetic resonan...
107 篇 medical imaging
65 篇 image enhancemen...
62 篇 image reconstruc...
60 篇 medical image se...
57 篇 segmentation
57 篇 artificial intel...
56 篇 image processing...
46 篇 pattern recognit...
39 篇 convolutional ne...
38 篇 image classifica...
37 篇 health informati...
35 篇 image analysis
33 篇 computer graphic...
31 篇 deformation
31 篇 computerized tom...
31 篇 image processing

机构

32 篇 ucl ctr med imag...
19 篇 simon fraser uni...
18 篇 ucl ctr med imag...
17 篇 centre for medic...
16 篇 shenzhen univ ma...
16 篇 imperial coll lo...
16 篇 shenzhen univ me...
14 篇 biomedical image...
14 篇 national center ...
14 篇 univ penn dept r...
13 篇 hong kong univ s...
13 篇 chinese univ hon...
12 篇 shanghai united ...
12 篇 univ n carolina ...
12 篇 univ penn dept r...
11 篇 department of co...
10 篇 college of physi...
10 篇 harvard med sch ...
10 篇 siemens corp res...
9 篇 yale univ dept b...

作者

78 篇 rueckert daniel
61 篇 shen dinggang
50 篇 navab nassir
49 篇 hamarneh ghassan
46 篇 ourselin sebasti...
41 篇 yang guang-zhong
24 篇 glocker ben
23 篇 ni dong
22 篇 wang qian
21 篇 hawkes david j.
21 篇 alexander daniel...
21 篇 davatzikos chris...
19 篇 golland polina
19 篇 abugharbieh rafe...
19 篇 sato yoshinobu
19 篇 fu huazhu
18 篇 yang xin
18 篇 stoyanov danail
18 篇 bai wenjia
17 篇 duncan james s.

语言

2,809 篇 英文
67 篇 其他
6 篇 中文

检索条件"任意字段=5th International Conference on Medical Image Computing and Computer-Assisted Intervention"

共 2882 条记录，以下是271-280 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：

CoLa-Diff: Conditional Latent Diffusion Model for Multi-modal MRI Synthesis 26th

CoLa-Diff: Conditional Latent Diffusion Model for Multi-moda...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Jiang, Lan Mao, Ye Wang, Xiangfeng Chen, Xi Li, Chao Univ Dundee Sch Sci & Engn Dundee Scotland Univ Cambridge Dept Clin Neurosci Cambridge England East China Normal Univ Sch Comp Sci & Technol Shanghai Peoples R China Univ Bath Dept Comp Sci Bath Avon England Univ Dundee Sch Med Dundee Scotland

ISBN: (纸本)9783031439988;9783031439995

MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions. However, most diffusion-based MRI synthesis models are using a single modality. As they operate in the original image domain, they are memory-intensive and less feasible for multi-modal synthesis. Moreover, they often fail to preserve the anatomical structure in MRI. Further, balancing the multiple conditions from multi-modal MRI inputs is crucial for multi-modal synthesis. Here, we propose the first diffusion-based multi-modality MRI synthesis model, namely Conditioned Latent Diffusion Model (CoLa-Diff). To reduce memory consumption, we perform the diffusion process in the latent space. We propose a novel network architecture, e.g., similar cooperative filtering, to solve the possible compression and noise in latent space. To better maintain the anatomical structure, brain region masks are introduced as the priors of density distributions to guide diffusion process. We further present auto-weight adaptation to employ multi-modal information effectively. Our experiments demonstrate that CoLa-Diff outperforms other state-of-the-art MRI synthesis methods, promising to serve as an effective tool for multi-modal MRI synthesis.

关键词： Multi-modal MRI medical image synthesis Latent space Diffusion models Structural guidance

来源：评论

学校读者我要写书评

暂无评论

CT Kernel Conversion Using Multi-domain image-to-image Translation with Generator-Guided Contrastive Learning 26th

CT Kernel Conversion Using Multi-domain Image-to-Image Trans...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Choi, Changyong Jeong, Jiheon Lee, Sangyoon Lee, Sang Min Kim, Namkug Univ Ulsan Coll Med Asan Med Ctr AMISTDept Biomed Engn Seoul South Korea Univ Ulsan Coll Med Asan Med Ctr Dept Convergence Med Seoul South Korea Univ Ulsan Dept Radiol Asan Med Ctr Coll Med Seoul South Korea

ISBN: (纸本)9783031439988;9783031439995

Computed tomography (CT) image can be reconstructed by various types of kernels depending on what anatomical structure is evaluated. Also, even if the same anatomical structure is analyzed, the kernel being used differs depending on whether it is qualitative or quantitative evaluation. thus, CT images reconstructed with different kernels would be necessary for accurate diagnosis. However, once CT image is reconstructed with a specific kernel, the CT raw data, sinogram is usually removed because of its large capacity and limited storage. To solve this problem, many methods have been proposed by using deep learning approach using generative adversarial networks in image-to-image translation for kernel conversion. Nevertheless, it is still challenging task that translated image should maintain the anatomical structure of source image in medical domain. In this study, we propose CT kernel conversion method using multi-domain image-to-image translation with generator-guided contrastive learning. Our proposed method maintains the anatomical structure of the source image accurately and can be easily utilized into other multi-domain image-to-image translation methods with only changing the discriminator architecture and without adding any additional networks. Experimental results showthat our proposed method can translate CT images from sharp into soft kernels and from soft into sharp kernels compared to other image-to-image translation methods. Our code is available at https://git ***/cychoi97/GGCL.

关键词： CT Kernel conversion image-to-image translation Contrastive learning Style transfer

来源：评论

学校读者我要写书评

暂无评论

3D Spleen image Registration Method Based on Reinforcement Learning Stochastic Planner-Actor-Critic Model 5

3D Spleen Image Registration Method Based on Reinforcement L...

引用

5th international conference on Artificial Intelligence and computer Engineering, ICAICE 2024

作者： Liu, Demin Xie, Yudan Han, Guocheng School of Life and Environmental Sciences Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798331528911

Conventional methods for aligning medical images encounter challenges in effectively capturing the varied morphological attributes of organs such as the spleen and liver. Deep learning algorithms often utilize loss function minimization to deduce image mapping associations, a procedure that may be impeded by local minima. To address these constraints, we introduces a new reinforcement learning strategy termed the stochastic planner-actor-critic (SPAC) model for spleen registration. the SPAC is a reinforcement learning model used for designing registration strategies. the agent observes an image and adjusts its deformation based on reward signals. through iterative transformations, the agent aligns the organ image with a fixed image. Analyzing the agent's behavior optimizes the registration process. this unsupervised training enables agents to autonomously develop registration strategies, reducing the need for manual intervention and annotation. the findings from the experiment indicate that the Dice similarity coefficient (DSC) achieved by the SPAC model-based method in the task of 3D spleen image registration is 0.829 ± 0.087. In contrast to conventional approaches, the SPAC model demonstrates superior efficacy in addressing the intricate morphology and substantial deformation of the spleen, thereby leading to a notable enhancement in registration precision. this research demonstrates the significant promise of reinforcement learning within the realm of medical image registration, with the SPAC model offering a unique and efficient method for addressing the complexities associated with spleen image registration. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

TCL: Triplet Consistent Learning for Odometry Estimation of Monocular Endoscope 26th

TCL: Triplet Consistent Learning for Odometry Estimation of ...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Yue, Hao Gu, Yun Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Med Robot Shanghai Peoples R China

ISBN: (纸本)9783031439957;9783031439964

the depth and pose estimations from monocular images are essential for computer-aided navigation. Since the ground truth of depth and pose are difficult to obtain, the unsupervised training method has a broad prospect in endoscopic scenes. However, endoscopic datasets lack sufficient diversity of visual variations, and appearance inconsistency is also frequently observed in image triplets. In this paper, we propose a triplet-consistency-learning framework (TCL) consisting of two modules: Geometric Consistency module(GC) and Appearance Inconsistency module(AiC). To enrich the diversity of endoscopic datasets, the GC module generates synthesis triplets and enforces geometric consistency via specific losses. To reduce the appearance inconsistency in the image triplets, the AiC module introduces a tripletmasking strategy to act on photometric loss. TCL can be easily embedded into various unsupervised methods without adding extra model parameters. Experiments on public datasets demonstrate that TCL effectively improves the accuracy of unsupervised methods even with limited number of training samples. Code is available at https://***/ EndoluminalSurgicalVision-IMR/TCL.

关键词： Self-supervised monocular pose estimation Endoscopic images Data augmentation Appearance inconsistency

来源：评论

学校读者我要写书评

暂无评论

How Reliable are the Metrics Used for Assessing Reliability in medical Imaging? 1

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Gupta, Mayank Basu, Soumen Arora, Chetan Indian Inst Technol Delhi India

ISBN: (数字)9783031438981

ISBN: (纸本)9783031438974;9783031438981

Deep Neural Networks (DNNs) have been successful in various computer vision tasks, but are known to be uncalibrated, and make overconfident mistakes. this erodes a user's confidence in the model and is a major concern in their applicability for critical tasks like medical imaging. In the last few years, researchers have proposed various metrics to measure miscalibration, and techniques to calibrate DNNs. However, our investigation shows that for small datasets, typical for medical imaging tasks, the common metrics for calibration, have a large bias as well as variance. It makes these metrics highly unreliable, and unusable for medical imaging. Similarly, we show that state-of-the-art (SOTA) calibration techniques while effective on large natural image datasets, are ineffective on small medical imaging datasets. We discover that the reason for failure is large variance in the density estimation using a small sample set. We propose a novel evaluation metric that incorporates the inherent uncertainty in the predicted confidence, and regularizes the density estimation using a parametric prior model. We call our metric, Robust Expected Calibration Error (RECE), which gives a low bias, and low variance estimate of the expected calibration error, even on the small datasets. In addition, we propose a novel auxiliary loss - Robust Calibration Regularization (RCR) which rectifies the above issues to calibrate the model at train time. We demonstrate the effectiveness of our RECE metric as well as the RCR loss on several medical imaging datasets and achieve SOTA calibration results on both standard calibration metrics as well as RECE. We also show the benefits of using our loss on general classification datasets. the source code and all trained models have been released (https://***/MayankGupta73/Robust-Calibration).

关键词： Confidence Calibration Uncertainty Estimation image Classification

来源：评论

学校读者我要写书评

暂无评论

CortexMorph: Fast Cortical thickness Estimation via Diffeomorphic Registration Using VoxelMorph 26th

CortexMorph: Fast Cortical Thickness Estimation via Diffeomo...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： McKinley, Richard Rummel, Christian Univ Hosp Bern Univ Inst Diagnost & Intervent Neuroradiol Support Ctr Adv Neuroimaging SCAN Inselspital Bern Switzerland

ISBN: (纸本)9783031439988;9783031439995

the thickness of the cortical band is linked to various neurological and psychiatric conditions, and is often estimated through surface-based methods such as Freesurfer in MRI studies. the DiReCT method, which calculates cortical thickness using a diffeomorphic deformation of the gray-white matter interface towards the pial surface, offers an alternative to surface-based methods. Recent studies using a synthetic cortical thickness phantom have demonstrated that the combination of DiReCT and deep-learning-based segmentation is more sensitive to subvoxel cortical thinning than Freesurfer. While anatomical segmentation of a T1-weighted image now takes seconds, existing implementations of DiReCT rely on iterative image registration methods which can take up to an hour per volume. On the other hand, learning-based deformable image registration methods like Voxel-Morph have been shown to be faster than classical methods while improving registration accuracy. this paper proposes Cortex Morph, a new method that employs unsupervised deep learning to directly regress the deformation field needed for DiReCT. By combining Cortex Morph with a deep-learning-based segmentation model, it is possible to estimate region-wise thickness in seconds from a T1-weighted image, while maintaining the ability to detect cortical atrophy. We validate this claim on the OASIS-3 dataset and the synthetic cortical thickness phantom of Rusak et al.

关键词： MRI Morphometry cortical thickness Unsupervised image registration Deep learning

来源：评论

学校读者我要写书评

暂无评论

A General Stitching Solution for Whole-Brain 3D Nuclei Instance Segmentation from Microscopy images 26th

A General Stitching Solution for Whole-Brain 3D Nuclei Insta...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Wei, Ziquan Dan, Tingting Ding, Jiaqi Dere, Mustafa Wu, Guorong Univ N Carolina Dept Psychiat Chapel Hill NC 27599 USA Univ N Carolina Dept Comp Sci Chapel Hill NC 27599 USA

ISBN: (纸本)9783031439001;9783031439018

High-throughput 3D nuclei instance segmentation (NIS) is critical to understanding the complex structure and function of individual cells and their interactions within the larger tissue environment in the brain. Despite the significant progress in achieving accurate NIS within small image stacks using cutting-edge machine learning techniques, there has been a lack of effort to extend this approach towards whole-brain NIS from light-sheet microscopy. this critical area of research has been largely overlooked, despite its importance in the neuroscience field. To address this challenge, we propose an efficient deep stitching neural network built upon a knowledge graph model characterizing 3D contextual relationships between nuclei. Our deep stitching model is designed to be agnostic, enabling existing limited methods (optimized for image stack only) to overcome the challenges of whole-brain NIS, particularly in addressing the issue of inter- and intra-slice gaps. We have evaluated the NIS accuracy on top of three state-of-the-art deep models with 128x128x64 image stacks, and visualized results in both inter- and intra-slice gaps of whole brain. With resolved gap issues, our deep stitchingmodel enables the whole-brain NIS (gigapixel-level) on entry-level GPU servers within 27 h.

关键词： image stitching 3D microscopy image Whole-brain nucleus instance segmentation Graph neural network

来源：评论

学校读者我要写书评

暂无评论

PET image Denoising with Score-Based Diffusion Probabilistic Models 26th

PET Image Denoising with Score-Based Diffusion Probabilistic...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Shen, Chenyu Yang, Ziyuan Zhang, Yi Sichuan Univ Sch Cyber Sci & Engn Chengdu Peoples R China Sichuan Univ Coll Comp Sci Chengdu Peoples R China

ISBN: (纸本)9783031439063;9783031439070

Low-count positron emission tomography (PET) imaging is an effective way to reduce the radiation risk of PET at the cost of a low signal-to-noise ratio. Our study aims to denoise low-count PET images in an unsupervised mode since the mainstream methods usually rely on paired data, which is not always feasible in clinical practice. We adopt the diffusion probabilistic model in consideration of its strong generation ability. Our model consists of two stages. In the training stage, we learn a score function network via evidence lower bound (ELBO) optimization. In the sampling stage, the trained score function and low-count image are employed to generate the corresponding high-count image under two handcrafted conditions. One is based on restoration in latent space, and the other is based on noise insertion in latent space. thus, our model is named the bidirectional condition diffusion probabilistic model (BC-DPM). Real patient whole-body data are utilized to evaluate our model. the experiments show that our model achieves better performance in both qualitative and quantitative aspects compared to several traditional and recently proposed learning-based methods.

关键词： PET denoising diffusion probabilistic model latent space conditions

来源：评论

学校读者我要写书评

暂无评论

Shape-Guided Conditional Latent Diffusion Models for Synthesising Brain Vasculature 1

引用

3rd Workshop on Deep Generative Models for medical image computing and computer assisted intervention (DGM4MICCAI) at the 26th international conference on medical image computing and computer assisted intervention (MICCAI)

作者： Deo, Yash Dou, Haoran Ravikumar, Nishant Frangi, Alejandro F. Lassila, Toni Univ Leeds Ctr Computat Imaging & Simulat Technol Biomed CIS Sch Comp Leeds England Univ Leeds Sch Med Leeds England NIHR Leeds Biomed Res Ctr BRC Leeds England Alan Turing Inst London England Katholieke Univ Leuven Med Imaging Res Ctr MIRC Elect Engn Dept Leuven Belgium Katholieke Univ Leuven Med Imaging Res Ctr MIRC Cardiovasc Sci Dept Leuven Belgium Univ Manchester Div Informat Imaging & Data Sci Sch Comp Sci Manchester England Univ Manchester Div Informat Imaging & Data Sci Sch Hlth Sci Manchester England

ISBN: (数字)9783031537677

ISBN: (纸本)9783031537660;9783031537677

the Circle ofWillis (CoW) is the part of cerebral vasculature responsible for delivering blood to the brain. Understanding the diverse anatomical variations and configurations of the CoW is paramount to advance research on cerebrovascular diseases and refine clinical interventions. However, comprehensive investigation of less prevalent CoW variations remains challenging because of the dominance of a few commonly occurring configurations. We propose a novel generative approach utilising a conditional latent diffusion model with shape and anatomical guidance to generate realistic 3D CoW segmentations, including different phenotypical variations. Our conditional latent diffusion model incorporates shape guidance to better preserve vessel continuity and demonstrates superior performance when compared to alternative generative models, including conditional variants of 3D GAN and 3D VAE. We observed that our model generated CoW variants that are more realistic and demonstrate higher visual fidelity than competing approaches with an FID score 53% better than the best-performing GAN-based model.

关键词： image Synthesis Deep Learning Brain Vasculature Vessel Synthesis Diffusion Latent Diffusion

来源：评论

学校读者我要写书评

暂无评论

UPCoL: Uncertainty-Informed Prototype Consistency Learning for Semi-supervised medical image Segmentation 26th

UPCoL: Uncertainty-Informed Prototype Consistency Learning f...

引用

26th international conference on medical image computing and computer-assisted intervention (MICCAI)

作者： Lu, Wenjing Lei, Jiahao Qiu, Peng Sheng, Rui Zhou, Jinhua Lu, Xinwu Yang, Yang Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Vasc Surg Shanghai Peoples Hosp 9 Shanghai Peoples R China Anhui Med Univ Chaohu Clin Medcial Coll Hefei Peoples R China Anhui Med Univ Sch Biomed Engn Hefei Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples Hosp 9 Shanghai Key Lab Tissue Engn Sch Med Shanghai Peoples R China

ISBN: (纸本)9783031439001;9783031439018

Semi-supervised learning (SSL) has emerged as a promising approach for medical image segmentation, while its capacity has still been limited by the difficulty in quantifying the reliability of unlabeled data and the lack of effective strategies for exploiting unlabeled regions with ambiguous predictions. To address these issues, we propose an Uncertainty-informed Prototype Consistency Learning (UPCoL) framework, which learns fused prototype representations from labeled and unlabeled data judiciously by incorporating an entropy-based uncertainty mask. the consistency constraint enforced on prototypes leads to a more discriminative and compact prototype representation for each class, thus optimizing the distribution of hidden embeddings. We experiment with two benchmark datasets of two-class semi-supervised segmentation, left atrium and pancreas, as well as a three-class multi-center dataset of type B aortic dissection. For all three datasets, UPCoL outperforms the state-of-the-art SSL methods, demonstrating the efficacy of the uncertainty-informed prototype learning strategy (Code is available at https://***/VivienLu/UPCoL).

关键词： Semi-supervised learning Uncertainty assessment Prototype learning medical image segmentation

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289页 << < 24 25 26 27 28 29 30 31 32 33 > >>

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：