[1]杨传婕,马志庆,赵文华,等.基于DenseNet的儿童肺炎识别与多分类研究[J].中国医学物理学杂志,2026,43(3):393-400.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.018]
　YANG Chuanjie,MA Zhiqing,ZHAO Wenhua,et al.Identification and multi-class classification of pediatric pneumonia based on DenseNet[J].Chinese Journal of Medical Physics,2026,43(3):393-400.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.018]
点击复制

基于DenseNet的儿童肺炎识别与多分类研究()

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

卷:
43卷
期数:
2026年第3期
页码:
393-400
栏目:
医学人工智能
出版日期:
2026-03-27

文章信息/Info

Title:
Identification and multi-class classification of pediatric pneumonia based on DenseNet
文章编号:
1005-202X（2026）03-0393-08
作者:
杨传婕1; 马志庆1; 赵文华1; 赵爽1; 2
1.山东中医药大学医学信息工程学院， 山东 济南 250000； 2.山东中医药大学实验中心， 山东 济南 250000
Author(s):
YANG Chuanjie1;  MA Zhiqing1;  ZHAO Wenhua1;  ZHAO Shuang1;  2
1. School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250000, China 2. Experimental Center of Shandong University of Traditional Chinese Medicine, Jinan 250000, China
关键词:
图像分类; 医学图像处理; 儿童肺炎; 空间和信道重构卷积; 空间组智能增强
Keywords:
Keywords: image classification medical image processing pediatric pneumonia space and channel reconstruction convolution spatial group-wise enhance
分类号:
R318；TP391.4
DOI:
DOI:10.3969/j.issn.1005-202X.2026.03.018
文献标志码:
A
摘要:
针对儿童肺炎影像难以诊断的问题，提出一种基于DenseNet算法改进的儿童肺炎诊断模型，以提高诊断准确率。以DenseNet网络为基础模型融合空间和信道重构卷积，利用特征之间的空间和信道冗余对卷积神经网络进行压缩，提高推理效率。将空间组智能增强模块嵌入网络，利用注意力掩码对不同位置的特征向量进行缩放调整，从而提高各组特征在空间维度上的鲁棒性。同时，增大网络前期卷积核和池化核，提高模型的表达能力。引入A2-Nets双重注意力网络，通过高效的特征聚合与传播机制，显著提升图像识别性能。实验结果表明，提出的方法取得显著的效果，在正常和肺炎的二分类准确率为97.8%；在细菌性和病毒性肺炎的二分类实验中达到82.3%的准确率；在正常、细菌性肺炎和病毒性肺炎三分类中取得83.1%的准确率。
Abstract:
Abstract: Given the challenges in imaging-based diagnosis of pediatric pneumonia, this study presents an improved diagnostic model for pediatric pneumonia based on the DenseNet algorithm, aiming to enhance diagnostic accuracy. With DenseNet as the basic model, the spatial and channel reconstruction convolution is integrated to compress the convolutional neural network by leveraging the spatial and channel redundancy in features, thus improving inference efficiency. A spatial group-wise enhance module is embedded into the network, which utilizes attention masks to scale and adjust feature vectors at different positions, thereby strengthening the robustness of each feature group in the spatial dimension. Meanwhile, the convolutional and pooling kernels in the early stages of the network are increased to improve the models expressive capability. Furthermore, the introduction of A2-Nets dual attention network significantly improves image recognition performance through efficient feature aggregation and propagation mechanisms. Experimental results demonstrate that the proposed method achieves remarkable performances, with an accuracy of 97.8% for the binary classification of normal and pneumonia, 82.3% for the binary classification of bacterial and viral pneumonia, and 83.1% for the 3-class classification of normal, bacterial pneumonia, and viral pneumonia.

相似文献/References:

[1]许红玉,聂生东,刘颖,等.《医学图像处理》课程网站建设[J].中国医学物理学杂志,2013,30(02):4076.[doi:10.3969/j.issn.1005-202X.2013.02.027]
[2]王弈,李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志,2013,30(03):4138.[doi:10.3969/j.issn.1005-202X.2013.03.013]
[3]张红军,闫士举.基于双侧乳腺图像“共用”阈值分割的乳腺癌近期发病预测[J].中国医学物理学杂志,2017,34(8):820.[doi:DOI:10.3969/j.issn.1005-202X.2017.08.013]
[4]皮一飞,吴茜,裴曦,等.基于掩膜优化的多模态医学图像刚性配准[J].中国医学物理学杂志,2018,35(9):1022.[doi:10.3969/j.issn.1005-202X.2018.09.006]
　PI Yifei,WU Qian,PEI Xi,et al.Rigid registration of multimodal medical images based on mask optimization[J].Chinese Journal of Medical Physics,2018,35(3):1022.[doi:10.3969/j.issn.1005-202X.2018.09.006]
[5]张育,赵轶峰,苏卓彬,等.基于卷积神经网络的胃癌癌前病变图像分类方法[J].中国医学物理学杂志,2022,39(2):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]
　ZHANG Yu,ZHAO Yifeng,SU Zhuobin,et al.Image classification of gastric precancerous lesions based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(3):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]
[6]孙旭阳,石更强.基于CT影像的人体踝关节三维重建[J].中国医学物理学杂志,2022,39(7):850.[doi:DOI:10.3969/j.issn.1005-202X.2022.07.010]
　SUN Xuyang,SHI Gengqiang.Three-dimensional reconstruction of the ankle joint based on CT image[J].Chinese Journal of Medical Physics,2022,39(3):850.[doi:DOI:10.3969/j.issn.1005-202X.2022.07.010]
[7]孙晓晗,孔祥勇,吴滢,等.基于卷积神经网络的肾小球病理图像分类算法[J].中国医学物理学杂志,2022,39(10):1313.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.023]
　SUN Xiaohan,KONG Xiangyong,WU Ying,et al.Glomerular pathological image classification algorithm based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(3):1313.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.023]
[8]王怡伟,李晓兵,聂生东,等.基于深度学习的超声多模态乳腺肿块良恶性分类[J].中国医学物理学杂志,2023,40(8):988.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.011]
　WANG Yiwei,LI Xiaobing,NIE Shengdong,et al.Deep learning-based classification for benign and malignant breast masses using multimodal ultrasound images[J].Chinese Journal of Medical Physics,2023,40(3):988.[doi:DOI:10.3969/j.issn.1005-202X.2023.08.011]
[9]张子宇,赵可辉,牛慧芳,等.基于轻量级RG-DenseNet的COVID-19 CT图像分类[J].中国医学物理学杂志,2023,40(12):1494.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.007]
　ZHANG Ziyu,ZHAO Kehui,NIU Huifang,et al.COVID-19 classification on CT image using lightweight RG DenseNet[J].Chinese Journal of Medical Physics,2023,40(3):1494.[doi:DOI:10.3969/j.issn.1005-202X.2023.12.007]
[10]潘依乐,高永彬.多模态弱监督学习在肝癌图像生成与分割中的应用[J].中国医学物理学杂志,2024,41(1):8.[doi:DOI:10.3969/j.issn.1005-202X.2024.01.002]
　PAN Yile,GAO Yongbin.Application of multimodal weakly-supervised learning in image synthesis and segmentation of liver cancer[J].Chinese Journal of Medical Physics,2024,41(3):8.[doi:DOI:10.3969/j.issn.1005-202X.2024.01.002]

备注/Memo

备注/Memo:
【收稿日期】2025-10-29 【基金项目】山东省自然科学基金青年项目（ZR2023QF146）；山东省医药卫生科技项目（202425020411）；山东中医药大学科学研究基金（KYZK2024Q30） 【作者简介】杨传婕，硕士研究生，研究方向：医学图像处理，E-mail:294650663@qq.com 【通信作者】马志庆，教授，硕士生导师，研究方向：生物医学图像处理与分析、人体信息检测技术，E-mail: mazhq126@163.com
更新日期/Last Update: 2026-03-30