[1]陈立伟,彭逸飞,余仁萍,等.基于多视图融合和2.5D U-Net的海马体图像分割[J].郑州大学学报(工学版),2025,46(05):26-34.[doi:10.13705/j.issn.1671-6833.2025.02.013]
　CHEN Liwei,PENG Yifei,YU Renping,et al.Hippocampus Image Segmentation Based on Multi-view Fusion and 2.5D U-Net[J].Journal of Zhengzhou University (Engineering Science),2025,46(05):26-34.[doi:10.13705/j.issn.1671-6833.2025.02.013]
点击复制

基于多视图融合和2.5D U-Net的海马体图像分割()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年05期
页码:
26-34
栏目:
出版日期:
2025-08-10

文章信息/Info

Title:
Hippocampus Image Segmentation Based on Multi-view Fusion and 2.5D U-Net
文章编号:
1671-6833(2025)05-0026-09
作者:
陈立伟;  彭逸飞;  余仁萍;  孙源呈
郑州大学 电气与信息工程学院,河南 郑州 450001
Author(s):
CHEN Liwei;  PENG Yifei;  YU Renping;  SUN Yuancheng
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China
关键词:
海马体图像分割;  卷积神经网络;  U-Net;  Triplet Attention;  注意力机制;  体积融合网络
Keywords:
hippocampus image segmentation;  CNN;  U-Net;  Triplet Attention;  attention mechanism;  volume fusion network
分类号:
TP391.7 TP183
DOI:
10.13705/j.issn.1671-6833.2025.02.013
文献标志码:
A
摘要:
针对现有海马体图像自动分割方法不能很好地利用上下文信息导致分割准确率难以提高以及训练和检测过程中内存消耗大的问题,提出了一种基于多视图融合和2.5D U-Net的海马体图像分割模型MVF-2.5D U-Net。首先,模型对2D U-Net进行了改进,增加Triplet Attention模块的同时调整了网络的层深;其次,使用相邻切片组成的三通道2.5D图像代替传统的单切片输入;最后,构建了一个体积融合网络代替传统的众数投票机制。在HarP数据集上通过交叉验证的方式对网络进行了实验验证。实验结果表明:所提模型在海马体图像分割任务上的平均Dice系数和豪斯多夫距离分别为0.902和3.02,准确率和稳定性优于传统的U-Net模型和对比算法,同时适用于资源受限的环境。实验证明所提模型能够更有效地实现磁共振影像上的海马体分割。
Abstract:
Aiming at the problem in existing methods of automatic segmentation of hippocampus image, which can not make good use of the context information, might lead to the difficulty in improving the segmentation accuracy and large memory consumption in the process of training and detection, a new model called MVF-2.5D U-Net based on multi-view fusion and 2.5D U-Net was introduced. Firstly, this model improved the 2D U-Net by incorporating a Triplet Attention module and adjusting the depth of the network. Secondly, the traditional single-slice input was replaced by a three-channel 2.5D image composed of adjacent slices. Finally, a volume fusion network was constructed to replace the conventional majority voting scheme. This study was validated by cross-validation on the HarP dataset. The experimental results showed that the average Dice coefficient and Hausdorff distance of the model on the hippocampus image segmentation task were 0.902 and 3.02, respectively, the accuracy and stability was better than the traditional U-Net model and comparison algorithm, and it was also suitable for the resource-constrained situation, which proved that the proposed model could achieve hippocampus segmentation on MRI more effectively.

参考文献/References:

[1]SÄMANN P G, IGLESIAS J E, GUTMAN B, et al. FreeSurfer-based segmentation of hippocampal subfields: a review of methods and applications, with a novel quality control procedure for ENIGMA studies and other collaborative efforts[J]. Human Brain Mapping, 2022, 43(1): 207-233. 

[2]JOULES R, WOLZ R. Fully automatic deep-learning based segmentation of hippocampal subfields from standard resolution T1W MRI in Alzheimer′s disease[J]. Alzheimer′s & Dementia, 2023, 19: e076575. 
[3]SACKL M, TINAUER C, URSCHLER M, et al. Fully automated hippocampus segmentation using T2-informed deep convolutional neural networks[J]. NeuroImage, 2024, 298: 120767. 
[4]NI T W, XIE L X, ZHENG H J, et al. Elastic boundary projection for 3D medical image segmentation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 2109-2118. 
[5]LIU M H, LI F, YAN H, et al. A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer′s disease[J]. NeuroImage, 2020, 208: 116459. 
[6]ÇIÇEK Ö, ABDULKADIR A, LIENKAMP S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation[C]∥Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2016: 424-432. 
[7]MANJON J V, ROMERO J E, COUPE P. A novel deep learning based hippocampus subfield segmentation method [J]. Scientific Reports, 2022, 12(1): 1333. 
[8]KNUTH F, ADDE I A, HUYNH B N, et al. MRI-based automatic segmentation of rectal cancer using 2D U-Net on two independent cohorts[J]. Acta Oncologica, 2022, 61(2): 255-263. 
[9]ZETTLER N, MASTMEYER A. Comparison of 2D vs. 3D U-Net organ segmentation in abdominal 3D CT images [EB/OL].(2021-07-08)[2024-07-16].https:∥doi. org/10.48550/arXiv.2107.04062. 
[10] ROTH H R, LU L, SEFF A, et al. A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations[C]∥ Medical Image Computing and Computer Assisted Intervention. Cham: Springer International Publishing, 2014: 520-527. 
[11] ROTH H R, LU L, FARAG A, et al. DeepOrgan: multilevel deep convolutional networks for automated pancreas segmentation[C]∥Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2015: 556-564. 
[12] YU Q H, XIE L X, WANG Y, et al. Recurrent saliency transformation network: incorporating multi-stage visual cues for small organ segmentation[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018: 8280-8289. 
[13] CHEN J, LU Y, YU Q, et al. TransUNet: Transformers make strong encoders for medical image segmentation [EB/OL].(2021-02-08)[2024-07-16].https:∥doi. org/10.48550/arXiv.2102.04306. 
[14]欧宇轩, 高敏, 赵地, 等. SA-TF-UNet: 基于空间注意力机制和Transformer的MRI海马体分割[J]. 中国图象图形学报, 2023, 28(10): 3191-3202. 
OU Y X, GAO M, ZHAO D, et al. SA-TF-UNet: a Transformer and spatial attention mechanisms based hippocampus segmentation network[J]. Journal of Image and Graphics, 2023, 28(10): 3191-3202. 
[15] OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: learning where to look for the pancreas [EB/OL].(2018-04-18) [2024-07-16] . https:∥ doi.org/10.48550/arXiv.1804.03999. 
[16]WANG H, LEI C, ZHAO D, et al. DeepHipp: accurate segmentation of hippocampus using 3D dense-block based on attention mechanism[J]. BMC Medical Imaging, 2023, 23(1): 158. 
[17]魏明军, 王镆涵, 刘亚志, 等. 基于特征融合和混合注意力的小目标检测[J]. 郑州大学学报(工学版), 2024, 45(3): 72-79. 
WEI M J, WANG M H, LIU Y Z, et al. Small object detection based on feature fusion and mixed attention[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(3): 72-79. 
[18]高宇飞, 马自行, 徐静, 等. 基于卷积和可变形注意力的脑胶质瘤图像分割[J]. 郑州大学学报(工学版), 2024, 45(2): 27-32. 
GAO Y F, MA Z X, XU J, et al. Brain glioma image segmentation based on convolution and deformable attention[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(2): 27-32. 
[19] ZHOU Y Y, XIE L X, SHEN W, et al. A fixed-point model for pancreas segmentation in abdominal CT scans [C]∥Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2017: 693-701. 
[20] XIA Y D, XIE L X, LIU F Z, et al. Bridging the gap between 2D and 3D organ segmentation with Volumetric Fusion Net[C]∥Medical Image Computing and Computer Assisted Intervention. Cham: Springer, 2018: 445-453. 
[21] BOCCARDI M, BOCCHETTA M, MORENCY F C, et al. Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol[J]. Alzheimer′s & Dementia,2015, 11(2): 175-183. 
[22] AVESTA A, HOSSAIN S, LIN M D, et al. Comparing 3D, 2.5D, and 2D approaches to brain image auto-segmentation[J]. Bioengineering, 2023, 10(2): 181. 
[23] ATALOGLOU D, DIMOU A, ZARPALAS D, et al. Fast and precise hippocampus segmentation through deep convolutional neural network ensembles and transfer learning[J]. Neuroinformatics, 2019, 17(4): 563-582. 
[24] CARMO D, SILVA B, INITIATIVE A D N, et al. Hippocampus segmentation on epilepsy and Alzheimer′s disease studies with multiple convolutional neural networks[J]. Heliyon, 2021, 7(2): e06226. 
[25] NOBAKHT S, SCHAEFFER M, FORKERT N D, et al. Combined atlas and convolutional neural network-based segmentation of the hippocampus from MRI according to the ADNI harmonized protocol[J]. Sensors, 2021, 21 (7):2427. 
[26] CHEN Y, YUE H L, KUANG H L, et al. RBS-Net: hippocampus segmentation using multi-layer feature learning with the region, boundary and structure loss[J]. Computers in Biology and Medicine, 2023, 160: 106953. 
[27] ZHENG Q, LIU B, GAO Y, et al. HGM-cNet: integrating hippocampal gray matter probability map into a cascaded deep learning framework improves hippocampus segmentation[J]. European Journal of Radiology, 2023, 162: 110771.

相似文献/References:

[1]郝旺身,陈耀,孙浩,等.基于全矢-CNN的轴承故障诊断研究[J].郑州大学学报(工学版),2020,41(05):92.[doi:10.13705/j.issn.1671-6833.2020.03.004]
　HAO Wangshen,CHEN Yao,SUN Hao,et al.Bearing Fault Diagnosis Based on Full Vector-CNN[J].Journal of Zhengzhou University (Engineering Science),2020,41(05):92.[doi:10.13705/j.issn.1671-6833.2020.03.004]
[2]孙 宁,王龙玉,刘佶鑫,等.结合特权信息与注意力机制的场景识别[J].郑州大学学报(工学版),2021,42(01):42.[doi:10.13705/j.issn.1671-6833.2021.01.007]
　SUN Ning,WANG Longyu,LIU Jixin,et al.Scene Recognition Based on Privilege Information and Attention Mechanism[J].Journal of Zhengzhou University (Engineering Science),2021,42(05):42.[doi:10.13705/j.issn.1671-6833.2021.01.007]
[3]贲可荣,杨佳辉,张献,等.基于Transformer和卷积神经网络的代码克隆检测[J].郑州大学学报(工学版),2023,44(06):12.[doi:10.13705/j.issn.1671-6833.2023.03.012]
　BEN Kerong,YANG Jiahui,ZHANG Xian,et al.Code Clone Detection Based on Transformer and Convolutional Neural Network[J].Journal of Zhengzhou University (Engineering Science),2023,44(05):12.[doi:10.13705/j.issn.1671-6833.2023.03.012]
[4]李卫军,张新勇,高庾潇,等.基于门控时空注意力的视频帧预测模型[J].郑州大学学报(工学版),2024,45(01):70.[doi:10.13705/j.issn.1671-6833.2024.01.017]
　LI Weijun,ZHANG Xinyong,GAO Yuxiao,et al.Video Frame Prediction Model Based on Gated Spatio-Temporal Attention[J].Journal of Zhengzhou University (Engineering Science),2024,45(05):70.[doi:10.13705/j.issn.1671-6833.2024.01.017]
[5]高宇飞,马自行,徐 静,等.基于卷积和可变形注意力的脑胶质瘤图像分割[J].郑州大学学报(工学版),2024,45(02):27.[doi:10.13705/j.issn.1671-6833.2023.05.007]
　GAO Yufei,MA Zixing,XU Jing,et al.Brain Glioma Image Segmentation Based on Convolution and Deformable Attention[J].Journal of Zhengzhou University (Engineering Science),2024,45(05):27.[doi:10.13705/j.issn.1671-6833.2023.05.007]
[6]杨 青,王亚群,文 斗,等.基于改进 StackCNN 网络和集成学习的脑电信号视觉分类算法[J].郑州大学学报(工学版),2024,45(05):69.[doi:10.13705/j.issn.1671-6833.2024.02.009]
　YANG Qing,WANG Yaqun,WEN Dou,et al.EEG Visual Classification Algorithm Based on Improved StackCNN Network andEnsemble Learning[J].Journal of Zhengzhou University (Engineering Science),2024,45(05):69.[doi:10.13705/j.issn.1671-6833.2024.02.009]
[7]张 震,周一成,田鸿朋.基于空间特征和生成对抗网络的网络入侵检测[J].郑州大学学报(工学版),2024,45(06):40.[doi:10.13705/j.issn.1671-6833.2024.06.001]
　ZHANG Zhen,ZHOU Yicheng,TIAN Hongpeng.Network Intrusion Detection Based on Spatial Features and GenerativeAdversarial Networks[J].Journal of Zhengzhou University (Engineering Science),2024,45(05):40.[doi:10.13705/j.issn.1671-6833.2024.06.001]
[8]蒋建东,张海峰,郭嘉琦.基于改进蜣螂优化算法的短期风电功率预测[J].郑州大学学报(工学版),2025,46(04):129.[doi:10.13705/j.issn.1671-6833.2025.01.015]
　JIANG Jiandong,ZHANG Haifeng,GUO Jiaqi.Short-term Wind Power Prediction Based on Improved Dung Beetle Optimization Algorithm[J].Journal of Zhengzhou University (Engineering Science),2025,46(05):129.[doi:10.13705/j.issn.1671-6833.2025.01.015]

更新日期/Last Update: 2025-09-19