[1]樊星佳,邢雄飞,李睿.基于交互注意力与特征融合的胸片分类算法[J].中国医学物理学杂志,2026,43(6):766-773.[doi:DOI:10.3969/j.issn.1005-202X.2026.06.009]
　FAN Xingjia,XING Xiongfei,LI Rui.Chest X-ray image classification algorithm based on interactive attention and feature fusion[J].Chinese Journal of Medical Physics,2026,43(6):766-773.[doi:DOI:10.3969/j.issn.1005-202X.2026.06.009]
点击复制

基于交互注意力与特征融合的胸片分类算法()

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

卷:
43卷
期数:
2026年第6期
页码:
766-773
栏目:
医学影像物理
出版日期:
2026-06-26

文章信息/Info

Title:
Chest X-ray image classification algorithm based on interactive attention and feature fusion
文章编号:
1005-202X（2026）06-0766-08
作者:
樊星佳1; 邢雄飞1; 李睿2
1.甘肃中医药大学医学信息工程学院， 甘肃 兰州 730000； 2.兰州大学第二医院信息中心， 甘肃 兰州 730030
Author(s):
FAN Xingjia1;  XING Xiongfei1;  LI Rui2
1. School of Medical Information Engineering , Gansu University of Chinese Medicine, Lanzhou 730000, China 2. Information Center, Lanzhou University Second Hospital, Lanzhou 730030, China
关键词:
胸部X光片; 深度学习; 可变形交互注意力; 多尺度特征融合
Keywords:
chest X-ray image deep learning deformable interactive attention multi-scale feature fusion
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2026.06.009
文献标志码:
A
摘要:
针对胸部X光片分类算法特征提取不充分、细节信息丢失的问题，提出一种基于交互注意力和特征融合改进ConvNeXt的胸部X光片图像分类模型。引入可变形交互注意力模块，通过双路径特征解耦与交互调制机制，实现不同属性特征信息的协同增强；同时，构建多尺度特征融合模块，用于融合不同抽象层级的判别信息，提升模型留存细节信息的能力；此外，还采用加权焦点损失函数弥补传统交叉熵函数的不足。在ChestX-Ray14数据集上进行实验，结果表明，该方法在14种疾病分类的平均AUC达到0.851，和现有的深度学习模型相比具有一定的竞争力。本文方法可提高分类精度，为胸部X光片的辅助诊断提供有力的技术支持。
Abstract:
An improved ConvNeXt-based model for chest X-ray image classification that integrates interactive attention and feature fusion is proposed to address the issues of insufficient feature extraction and detailed information loss in the existing chest X-ray image classification algorithms. A deformable interactive attention module is introduced to synergistically enhance features with different attributes through dual-path feature decoupling and interactive modulation mechanisms. Meanwhile, a multi-scale feature fusion module is constructed to integrate discriminative information across different abstraction levels, thereby improving the models ability to retain fine-grained details. Additionally, a weighted focal loss function is adopted to compensate for the limitations of traditional cross-entropy loss. Experiments on the ChestX-Ray14 dataset demonstrate that the proposed method achieves an average AUC of 0.851 for the classification of 14 diseases, exhibiting competitive performance compared with existing deep learning models. The proposed approach can improve classification accuracy, and provide robust technical support for the auxiliary diagnosis of chest X-rays.

相似文献/References:

[1]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
　[J].Chinese Journal of Medical Physics,2017,34(6):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[2]门阔,戴建荣. 利用深度反卷积神经网络自动勾画放疗危及器官[J].中国医学物理学杂志,2018,35(3):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
　MEN Kuo,DAI Jianrong. Automatic segmentation of organs at risk in radiotherapy using deep deconvolutional neural network[J].Chinese Journal of Medical Physics,2018,35(6):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
[3]邓金城,彭应林,刘常春,等. 深度卷积神经网络在放射治疗计划图像分割中的应用[J].中国医学物理学杂志,2018,35(6):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
　DENG Jincheng,PENG Yinglin,LIU Changchun,et al. Application of deep convolution neural network in radiotherapy planning image segmentation[J].Chinese Journal of Medical Physics,2018,35(6):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
[4]查雪帆,杨丰,吴俣南,等. 结合迁移学习与深度卷积网络的心电分类研究[J].中国医学物理学杂志,2018,35(11):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
　ZHA Xuefan,YANG Feng,WU Yunan,et al. ECG classification based on transfer learning and deep convolution neural network[J].Chinese Journal of Medical Physics,2018,35(6):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
[5]宫进昌,赵尚义,王远军. 基于深度学习的医学图像分割研究进展[J].中国医学物理学杂志,2019,36(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
　GONG Jinchang,ZHAO Shangyi,WANG Yuanjun.Research progress on deep learning-based medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(6):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
[6]安莹,黄能军,杨荣,等. 基于深度学习的心血管疾病风险预测模型[J].中国医学物理学杂志,2019,36(9):1103.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.021]
　AN Ying,HUANG Nengjun,YANG Rong,et al. Deep learning-based model for risk prediction of cardiovascular diseases[J].Chinese Journal of Medical Physics,2019,36(6):1103.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.021]
[7]徐航,随力,张靖雯,等.卷积神经网络在医学图像分割中的研究进展[J].中国医学物理学杂志,2019,36(11):1302.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.011]
　XU Hang,SUI Li,ZHANG Jingwen,et al.Progress on convolutional neural network in medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(6):1302.[doi:DOI:10.3969/j.issn.1005-202X.2019.11.011]
[8]张富利,崔德琪,王秋生,等.基于深度学习和图谱库方法自动勾画肿瘤放疗中危及器官的比较[J].中国医学物理学杂志,2019,36(12):1486.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.024]
　ZHANG Fuli,CUI Deqi,WANG Qiusheng,et al.Comparative study of deep learning- versus Atlas-based auto-segmentation of organs-at-risk in tumor radiotherapy[J].Chinese Journal of Medical Physics,2019,36(6):1486.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.024]
[9]温佳圆,林国钰,张逸文,等.应用深度学习网络实现肾小球滤过膜超微病理图像的语义分割[J].中国医学物理学杂志,2020,37(2):195.[doi:DOI:10.3969/j.issn.1005-202X.2020.02.012]
　WEN Jiayuan,LIN Guoyu,ZHANG Yiwen,et al.Semantic segmentation of ultrastructural pathological images of glomerular filtration membrane using deep learning network[J].Chinese Journal of Medical Physics,2020,37(6):195.[doi:DOI:10.3969/j.issn.1005-202X.2020.02.012]
[10]秦楠楠,薛旭东,吴爱林,等.基于U-net卷积神经网络的宫颈癌临床靶区和危及器官自动勾画的研究[J].中国医学物理学杂志,2020,37(4):524.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.023]
　QIN Nannan,XUE Xudong,WU Ailin,et al.Automatic segmentation of clinical target volumes and organs-at-risk in radiotherapy for cervical cancer using U-net convolutional neural network[J].Chinese Journal of Medical Physics,2020,37(6):524.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.023]

备注/Memo

备注/Memo:
【收稿日期】2025-12-19 【基金项目】甘肃省软科学专项（ 23JRZA484） 【作者简介】樊星佳，硕士研究生，研究方向：医学图像处理，E-mail: 2300620203@qq.com 【通信作者】李睿，高级工程师，研究方向：医疗信息化，E-mail:25515876@qq.com
更新日期/Last Update: 2026-06-26