网站首页            期刊简介             编委会             投稿指南             期刊订阅             下载中心             在线留言            联系我们             English
  2025年5月6日 星期二  
文章快速检索
中国生物医学工程学报  2024, Vol. 43 Issue (4): 467-476    DOI: 10.3969/j.issn.0258-8021.2024.04.009
  综述 本期目录 | 过刊浏览 | 高级检索 |
基于Transformer深度学习模型在医学图像分割中的研究进展
周腊珍1, 陈红池1, 李秋霞1, 李坊佐1,2*
1(赣南医科大学医学信息工程学院,江西 赣州 341000)
2(赣南医科大学, 心脑血管疾病防治教育部重点实验室,江西 赣州 341000)
Research Progress on Transformer-Based Deep Learning Models for Medical Image Segmentation
Zhou Lazhen1, Chen Hongchi1, Li Qiuxia1, Li Fangzuo1,2*
1(School of Medical Information Engineering, Gannan Medical University, Ganzhou 341000, Jiangxi, China)
2(Key Laboratory of Prevention and Treatment of Cardiovascular and Cerebrovascular Diseases, Ministry of Education, Gannan Medical University, Ganzhou 341000, Jiangxi, China)
全文: PDF (1000 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 医学图像的准确分割在现代临床影像检查、精准诊断和治疗规划中意义至关重要。近10年来,卷积神经网络(CNN)凭借其独特的特征提取能力,在医学图像分割领域成绩显著。CNN架构中存在的局部感受野和固有归纳偏置局限,限制其对图像中远程依赖关系的有效建模。近年来,Transformer架构依赖其对全局信息的捕获能力,有助于建模长距离的依赖关系并挖掘语义信息,在生物医学图像分割领域展示出卓越的性能和巨大潜力。在此,对Transformer架构的组成及其在医学图像分割中的应用进行了全面综述,从全监督、无监督和半监督的角度出发,对Transformer架构在医学图像的腹部多器官分割、心脏分割和脑肿瘤分割中的运用价值及性能进行了归纳分析,并对Transformer模型在分割任务中存在的局限不足进行了概括总结,最后对其未来发展趋势及优化路径进行了探讨展望。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
周腊珍
陈红池
李秋霞
李坊佐
关键词 Transformer图像分割卷积神经网络医学图像    
Abstract:Accurate segmentation of medical images is a crucial step in clinical diagnosis and treatment. Over the past decade, convolutional neural network (CNN) has been widely applied in the field of medical image segmentation and have achieved excellent segmentation performance. However, the inherent inductive bias in CNN architectures limits their ability to model long-range dependencies in images. In contrast, the Transformer architectures, which focus on global information and the ability to model long-range dependencies, has been demonstrated outstanding performance in biomedical image segmentation. This review introduced the components of Transformer architecture and its applications in medical image segmentation. From perspectives of fully supervised, unsupervised and semi-supervised learning, application values and performances of Transformer architectures in abdominal multi-organ segmentation, cardiac segmentation and brain tumor segmentation were summarized and analyzed. Finally, limitations of Transformer model in segmentation tasks and future optimizations were prospected.
Key wordsTransformer    image segmentation    convolutional neural network    medical image
收稿日期: 2023-09-06     
PACS:  R318  
基金资助:国家自然科学基金(11865003);江西省自然科学基金(20224BAB201020);赣南医科大学科研启动基金(QD201805)
通讯作者: *E-mail: lfz880920@163.com   
引用本文:   
周腊珍, 陈红池, 李秋霞, 李坊佐. 基于Transformer深度学习模型在医学图像分割中的研究进展[J]. 中国生物医学工程学报, 2024, 43(4): 467-476.
Zhou Lazhen, Chen Hongchi, Li Qiuxia, Li Fangzuo. Research Progress on Transformer-Based Deep Learning Models for Medical Image Segmentation. Chinese Journal of Biomedical Engineering, 2024, 43(4): 467-476.
链接本文:  
http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2024.04.009     或     http://cjbme.csbme.org/CN/Y2024/V43/I4/467
版权所有 © 2015 《中国生物医学工程学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发