[1]史雯雯,刘石坚,邹峥.多尺度融合与位置增强的多模态脑肿瘤分割模型[J].计算机技术与发展,2025,(10):53-61.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0130]
　SHI Wen-wen,LIU Shi-jian,ZOU Zheng.Multimodal Brain Tumor Segmentation Model Based on Multi-scale Fusion and Position Enhancement[J].,2025,(10):53-61.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0130]
点击复制

多尺度融合与位置增强的多模态脑肿瘤分割模型()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年10期
页码:
53-61
栏目:
媒体计算
出版日期:
2025-10-10

文章信息/Info

Title:
Multimodal Brain Tumor Segmentation Model Based on Multi-scale Fusion and Position Enhancement
文章编号:
1673-629X(2025)10-0053-09
作者:
史雯雯1; 刘石坚1; 邹峥2
1. 福建省大数据挖掘与应用技术重点实验室,福建福州 350118;
2. 福建师范大学 计算机与网络空间安全学院,福建福州 350117
Author(s):
SHI Wen-wen1; LIU Shi-jian1; ZOU Zheng2
1. Fujian Provincial Key Laboratory of Big Data Mining and Applications,Fuzhou 350118,China;
2. School of Computer and Cyber Security,Fujian Normal University,Fuzhou 350117,China
关键词:
医学图像分割; 脑部肿瘤; 多尺度; 多模态信息; 注意力机制
Keywords:
medical image segmentation; brain tumor; multi-scale; multimodal information; attention mechanism
分类号:
TP391
DOI:
10.20165/j.cnki.ISSN1673-629X.2025.0130
摘要:
多模态脑肿瘤图像具有综合信息,可以为医生提供更加全面、准确的信息。然而,由于脑肿瘤图像数据的匮乏,加之脑部结构错综复杂且变化多端,以及肿瘤形态的差异性和与正常组织的紧密交织状态,这些综合因素共同构成了脑肿瘤分割模型在有效利用和深度挖掘多模态图像关键信息方面所面临的严峻挑战。为此,该文提出一种基于多尺度融合与位置增强的多模态脑瘤分割模型。首先,设计了残差预激活模块替换U-Net中的编码与解码层,以保留低层次特征的细节。其次,在瓶颈层中设计了多尺度空洞融合注意力模块,对脑肿瘤的全局与局部信息进行了多源采样,旨在有效利用多模态医学图像之间的综合信息。最后,在跳跃连接层嵌入坐标信息增强模块,充分挖掘脑肿瘤区域的空间位置信息。在BraTS2018和BraTS2019数据集上的实验结果表明,该网络对WT、TC和ET分割的Dice系数分别为91.64%、90.28%和88.57%,Sensitivity系数和Hausdorff距离相较于其他网络也达到最优。这表明了所示设计的网络能够有效利用不同模态图像展现的病灶信息,能够融合不同尺度的肿瘤特征,有效地提升分割精度。
Abstract:
Multimodal brain tumor images have comprehensive information,which can provide doctors with more comprehensive and accurate information. However,due to the lack of brain tumor image data,the complex and varied brain structure,the difference of tumor morphology and the close interweaving state with normal tissues,these comprehensive factors together constitute the severe challenges faced by brain tumor segmentation models in effectively utilizing and deeply mining the key information of multi-modal images.Therefore,we propose a multimodal brain tumor segmentation model based on multi-scale fusion and position enhancement.Firstly,a residual pre-activation module is designed to replace the coding and decoding layers in U-Net to preserve the details of low-level features. Secondly,a multi-scale cavity fusion attention module is designed in the bottleneck layer to conduct multi-source sampling of global and local information of brain tumors,aiming to effectively utilize the comprehensive information between multi-modal medical images. Finally,the coordinate information enhancement module is embedded in the jump connection layer to fully mine the spatial location information of the brain tumor region. Experimental results on the BraTS2018 and BraTS2019 datasets show that the Dice coefficients of the proposed network for WT,TC and ET segmentation are 91.64%,90.28% and 88.57%,respectively,and the Sensitivity coefficient and Hausdorff distance are also optimal compared with other networks. It is showed that the designed network can effectively utilize lesion information presented by different modal images,and can fuse tumor features of different scales,effectively improving segmentation accuracy.

相似文献/References:

[1]王艳华 管一弘.基于模糊集理论的医学图像分割的应用[J].计算机技术与发展,2008,(11):223.
　WANG Yan-hua,GUAN Yi-hong.Application of Medical Image Segmentation Technology Based on Fuzzy - Set - Theory[J].,2008,(10):223.
[2]薛晓君 张立强 薛忠 杨建华.基于水平集的三维脑部肿瘤分割[J].计算机技术与发展,2010,(12):201.
　XUE Xiao-jun,ZHANG Li-qiang,XUE Zhong,et al.A Brain Tumor Segmentation Method Based on Level Set[J].,2010,(10):201.
[3]喻建锋,吕毅斌,房巾莉,等.基于 Canny 算子的 C-V 水平集模型[J].计算机技术与发展,2019,29(07):145.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 029]
　YU Jian-feng,LYU Yi-bin,FANG Jin-li,et al.C-V Level Set Model Based on Canny Operator[J].,2019,29(10):145.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 029]
[4]宋 杰,刘彩霞,李慧婷.基于 U-Net 网络的医学图像分割研究综述[J].计算机技术与发展,2024,34(01):9.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 002]
　SONG Jie,LIU Cai-xia,LI Hui-ting.Review of Medical Image Segmentation Based on U-Net Network[J].,2024,34(10):9.[doi:10. 3969 / j. issn. 1673-629X. 2024. 01. 002]
[5]曾庆鹏,崔 鹏.基于 PRAU-Net 的新冠肺炎 CT 图像分割研究[J].计算机技术与发展,2024,34(03):133.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 020]
　ZENG Qing-peng,CUI Peng.Research of COVID-19 CT Image Segmentation Based on PRAU-Net[J].,2024,34(10):133.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 020]
[6]吴英豪,杜晓刚,雷涛,等.基于形状特征引导的息肉分割网络[J].计算机技术与发展,2024,34(05):52.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0040]
　WU Ying-hao,DU Xiao-gang,LEI Tao,et al.Shape Features Guided Network for Polyp Segmentation[J].,2024,34(10):52.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0040]
[7]杨萍,陈立伟,王庆凤,等.融合卷积和Transformer的腹部多器官分割网络[J].计算机技术与发展,2024,34(09):47.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0161]
　YANG Ping,CHEN Li-wei,WANG Qing-feng,et al.Abdominal Multi Organ Segmentation Network Combining Convolution and Transformer[J].,2024,34(10):47.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0161]
[8]秦钰,刘芳,霍宏雯.基于自注意力机制的胃肠息肉图像分割算法[J].计算机技术与发展,2025,(01):67.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0306]
　QIN Yu,LIU Fang,HUO Hong-wen.Image Segmentation Algorithm of Gastrointestinal Polyps Based on Self-attention Mechanism[J].,2025,(10):67.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0306]

更新日期/Last Update: 2025-10-10