[1]郭朝晖,王瑜,马慧鋆,等.基于迁移学习和3D-WGMobileNet的青年抑郁症辅助诊断[J].中国医学物理学杂志,2024,41(4):455-462.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.010]
　GUO Zhaohui,WANG Yu,MA Huijun,et al.Diagnosis of youth depression based on transfer learning and 3D-WGMobileNet[J].Chinese Journal of Medical Physics,2024,41(4):455-462.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.010]
点击复制

基于迁移学习和3D-WGMobileNet的青年抑郁症辅助诊断()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第4期
页码:
455-462
栏目:
医学影像物理
出版日期:
2024-04-25

文章信息/Info

Title:
Diagnosis of youth depression based on transfer learning and 3D-WGMobileNet
文章编号:
1005-202X（2024）04-0455-08
作者:
郭朝晖; 王瑜; 马慧鋆; 田恒屹
北京工商大学计算机与人工智能学院， 北京 100048
Author(s):
GUO Zhaohui;  WANG Yu;  MA Huijun;  TIAN Hengyi
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
关键词:
抑郁症; 3D-WGMobileNet; 动态分组卷积; 滑窗分组卷积; 迁移学习; 功能磁共振成像
Keywords:
Keywords: depression 3D-WGMobileNet dynamic grouping convolution sliding window grouping convolution transfer learning functional magnetic resonance imaging
分类号:
R318；TP181
DOI:
DOI:10.3969/j.issn.1005-202X.2024.04.010
文献标志码:
A
摘要:
提出一种基于3D-WGMobileNet和迁移学习的网络模型，实现对青年抑郁症不同阶段患者的正确分类。首先，对功能磁共振成像（fMRI）数据进行预处理，并通过局部一致性分析将4D fMRI数据转换为3D，进行降维处理。然后，使用迁移学习方法将阿尔茨海默症的特征迁移到提出的3D-WGMobileNet中。利用动态分组卷积构建卷积核的专家权重矩阵，提高模型的表达能力；利用滑窗分组卷积来压缩模型的参数量，增强模型的计算能力。最后，利用3D-WGMobileNet对抑郁症患者图像进行特征提取和分类。在人类连接组项目数据库上的实验结果表明结合迁移学习、动态分组卷积和滑窗分组卷积的3D-WGMobileNet获得较好的分类效果，其中，抑郁症和健康对照组、轻度抑郁症和健康对照组、轻度抑郁症和中度抑郁症的分类准确率分别达到89.00%、85.15%、87.90%，证明本文方法的可行性和有效性。 【关键词】抑郁症；3D-WGMobileNet；动态分组卷积；滑窗分组卷积；迁移学习；功能磁共振成像
Abstract:
A novel network model is proposed based on 3D-WGMobileNet and transfer learning to accurately diagnose the stage of youth depression. After functional magenetic resonance imaging (fMRI) data preprocessing and dimensionality reduction by converting 4-dimensional fMRI data into 3-dimension through regional homogeneity approach, transfer learning method is employed to transfer the characteristics of Alzheimers disease to the proposed 3D-WGMobileNet. The expert weight matrix of convolutional kernel is constructed using dynamic grouping convolution for improving the expression ability of the model. The sliding window grouping convolution is used to reduce the quantity of model parameters and enhance the computing capability. Finally, 3D-WGMobileNet is used for the image feature extraction and classification of youth depression. Experimental results on the dataset of human connectome projects show that the 3D-WGMobileNet incorporating transfer learning, dynamic grouping convolution and sliding window grouping convolution exhibit superior performance in classification, achieving 89.00%, 85.15% and 87.90% accuracies in classifying depression and healthy controls, mild depression and healthy controls, mild depression and moderate depression, which verifies the feasibility and effectiveness of the proposed method.

相似文献/References:

[1]郭家梁,等.基于振幅-周期二维分布的脑电复杂度分析[J].中国医学物理学杂志,2016,33(6):633.[doi:10.3969/j.issn.1005-202X.2016.06.019]
[2]刘岩,李幼军,陈萌. 基于固有模态分解和深度学习的抑郁症脑电信号分类分析[J].中国医学物理学杂志,2017,34(9):963.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.021]
　[J].Chinese Journal of Medical Physics,2017,34(4):963.[doi:DOI:10.3969/j.issn.1005-202X.2017.09.021]
[3]付常洋,王瑜,肖洪兵,等.基于多尺度功能脑网络融合特征的抑郁症分类算法[J].中国医学物理学杂志,2020,37(4):439.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.008]
　FU Changyang,WANG Yu,XIAO Hongbing,et al.Classification of depression using fusion features based on multi-scale functional brain network[J].Chinese Journal of Medical Physics,2020,37(4):439.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.008]
[4]王静,孔令茵,雷炳业,等.抑郁症的脑复杂网络研究进展[J].中国医学物理学杂志,2020,37(6):780.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.023]
　WANG Jing,KONG Lingyin,LEI Bingye,et al.Advances in research on complex brain networks in depression[J].Chinese Journal of Medical Physics,2020,37(4):780.[doi:DOI:10.3969/j.issn.1005-202X.2020.06.023]
[5]吴华旺,佘生林,郑伟,等.基于脑网络组图谱的首发-未服药抑郁症白质结构网络研究[J].中国医学物理学杂志,2021,38(7):909.[doi:DOI:10.3969/j.issn.1005-202X.2021.07.023]
　WU Huawang,SHE Shenglin,et al.Brainnetome atlas-based investigation of white matter structural networks in drug-na?e first-episode major depressive disorder[J].Chinese Journal of Medical Physics,2021,38(4):909.[doi:DOI:10.3969/j.issn.1005-202X.2021.07.023]
[6]计亚荣,王瑜,付常洋,等.基于典型相关分析与双模态数据融合的抑郁症辅助诊断[J].中国医学物理学杂志,2021,38(10):1316.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.024]
　JI Yarong,WANG Yu,FU Changyang,et al.Aided diagnosis of major depressive disorder based on canonical correlation analysis and bimodal data fusion[J].Chinese Journal of Medical Physics,2021,38(4):1316.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.024]
[7]刁云恒,王慧颖,董娇,等.机器学习在抑郁症辅助诊断中的应用进展[J].中国医学物理学杂志,2022,39(2):257.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.021]
　DIAO Yunheng,WANG Huiying,et al.Advances in the application of machine learning in auxiliary diagnosis of depression[J].Chinese Journal of Medical Physics,2022,39(4):257.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.021]
[8]段逸凡,王瑜,付常洋,等.基于双模态磁共振成像和决策层融合的抑郁症辅助诊断[J].中国医学物理学杂志,2022,39(3):378.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.019]
　DUAN Yifan,WANG Yu,FU Changyang,et al.Auxiliary diagnosis of depression based on bimodal magnetic resonance imaging and decision level fusion[J].Chinese Journal of Medical Physics,2022,39(4):378.[doi:DOI:10.3969/j.issn.1005-202X.2022.03.019]

备注/Memo

备注/Memo:
【收稿日期】2023-12-03 【基金项目】北京市自然科学基金-北京市教育委员会科技计划重点项目（KZ202110011015）；北京工商大学2023年研究生科研能力计划提升项目 【作者简介】郭朝晖，硕士，研究方向：图像处理、机器学习，E-mail: 15701573421@163.com 【通信作者】王瑜，博士后，教授，博士生导师，研究方向：图像处理与模式识别，E-mail: wangyu@btbu.edu.cn；马慧鋆，在读博士，高级实验师，研究方向：大数据分析，E-mail: mahuijun@btbu.edu.cn
更新日期/Last Update: 2024-04-25