ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Hierarchical-order multimodal interaction fusion network for grading gliomas

He, Man; Han, Kangfu; Zhang, Yu*; Chen, Wufan*南方医科大学; y
Physics in Medicine and Biology2021-11-7DOI: 10.1088/1361-6560/ac30a1
6被引4阅读
引用收藏
分享

摘要

Significance. Gliomas are the most common type of primary brain tumors and have different grades. Accurate grading of a glioma is therefore significant for its clinical treatment planning and prognostic assessment with multiple-modality magnetic resonance imaging (MRI).Objective and Approach. In this study, we developed a noninvasive deep-learning method based on multimodal MRI for grading gliomas by focusing on effective multimodal fusion via leveraging collaborative and diverse high-order statistical information. Specifically, a novel high-order multimodal interaction module was designed to promote interactive learning of multimodal knowledge for more efficient fusion. For more powerful feature expression and feature correlation learning, the high-order attention mechanism is embedded in the interaction module for modeling complex and high-order statistical information to enhance the classification capability of the network. Moreover, we applied increasing orders at different levels to hierarchically recalibrate each modality stream through diverse-order attention statistics, thus encouraging all-sided attention knowledge with lesser parameters. Main results. To evaluate the effectiveness of the proposed scheme, extensive experiments were conducted on The Cancer Imaging Archive (TCIA) and Multimodal Brain Tumor Image Segmentation Benchmark 2017 (BraTS2017) datasets with five-fold cross validation to demonstrate that the proposed method can achieve high prediction performance, with area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity values of 95.2%, 94.28%, 95.24%, and 92.00% on the BraTS2017 and 93.50%, 92.86%, 97.14%, and 90.48% on TCIA datasets, respectively.

学科与关键词

关键词
glioma gradingmultimodal learningdeep learninghigh-order statisticsattention mechanism
相关
加载中…
  • Multi-modal magnetic resonance imaging-based grading analysis for gliomas by integrating radiomics and deep features
    Ning, Zhenyuan; Luo, Jiaxiu; Xiao, Qing; Cai, Longmei; Chen, Yuting; Yu, Xiaohui; Wang, Jian*; Zhang, Yu*Annals of Translational Medicine, 2021, 9(4): 298.被引 17
  • Brain tumor segmentation in multimodal MRI via pixel-level and feature-level image fusion
    Liu, Yu; Mu, Fuhao; Shi, Yu; Cheng, Juan; Li, Chang; Chen, Xun*Frontiers in Neuroscience, 2022, 16: 1000587.被引 9
  • Feature interaction network based on hierarchical decoupled convolution for 3D medical image segmentation
    Shen, Longfeng*; Zhang, Yingjie; Wang, Qiong; Qin, Fenglan; Sun, Dengdi; Min, Hai; Meng, Qianqian; Xu, Chengzhen*; Zhao, Wei; Song, XinPLoS One, 2023, 18(7): e0288658.
查看全部 →

发表信息

论文状态
公开发表
期刊
Physics in Medicine and Biology
发表日期
2021-11-07
卷期
第 66 卷, 第 21 期
页码
215016
DOI
10.1088/1361-6560/ac30a1
语言
MULTI-LANGUAGE
期刊收录
NSL
期刊等级
2区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61971213, 61671230]; Basic and Applied Basic Research Foundation of Guangdong Province [2019A1515010417]; Guangdong Provincial Key Laboratory of Medical Image Processing [2020B1212060039]

作者

  • H

    He, Man (第一作者)

    southern med univ

  • H

    Han, Kangfu

    southern med univ

查看全部 4 位作者收起作者
  • Z

    Zhang, Yu (通讯)

    southern med univ

  • C

    Chen, Wufan (通讯)

    southern med univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417