广东工业大学学报 ›› 2024, Vol. 41 ›› Issue (01): 27-33.doi: 10.12052/gdutxb.230050

• 智慧医疗 • 上一篇    下一篇

基于切片关联信息的慢性阻塞性肺疾病CT诊断

梁宇辰1, 蔡念1, 欧阳文生1, 谢依颖1, 王平2   

  1. 1. 广东工业大学 信息工程学院, 广东 广州 510006;
    2. 广州医科大学附属第一医院 肝胆外科, 广东 广州 510120
  • 收稿日期:2023-03-16 出版日期:2024-01-25 发布日期:2024-01-31
  • 通信作者: 蔡念 (1976–)，男，教授，博士生导师，主要研究方向为机器视觉、机器学习、数字信号处理等，E-mail:cainian@gdut.edu.cn
  • 作者简介:梁宇辰 (1998–)，男，硕士研究生，主要研究方向为深度学习、医学图像处理等
  • 基金资助:
    国家自然科学基金资助项目 (82172019)；广州市科技计划项目 (202102010251)

CT Diagnosis of Chronic Obstructive Pulmonary Disease Based on Slice Correlation Information

Liang Yu-chen1, Cai Nian1, Ouyang Wen-sheng1, Xie Yi-ying1, Wang Ping2   

  1. 1. School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China;
    2. Department of Hepatobiliary Surgery, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China
  • Received:2023-03-16 Online:2024-01-25 Published:2024-01-31

HTML

PDF (PC)

609

摘要： 慢性阻塞性肺疾病(Chronic Obstructive Pulmonary Disease, COPD) 是一种常见的全球呼吸系统疾病，需要耗费医生大量的时间和精力对CT图像进行初步评估诊断。为了提高阅片效率，提出一种基于CT图像切片关联信息的深度网络，辅助诊断慢性阻塞性肺疾病。提出一种分组方式将网络分成若干个网络分支，每个网络分支能够提取局部CT图像切片内部关联信息，结合双向LSTM技术整合各网络分支信息以提取CT图像全局切片关联信息。为了进一步提升网络分支的局部特征提取能力，融入ConvNeXt提出增强的多头卷积注意力模块。对比实验结果表明，所提出的深度网络能够更好地对CT图像进行分类，辅助COPD诊断，其准确率达到92.15%，敏感度达到94.17%，特异性达到91.17%，AUC达到95.33%。

关键词: 慢性阻塞性肺疾病, 深度学习, 多头卷积注意力

Abstract: Chronic obstructive pulmonary disease (COPD) is a common respiratory disease of the world, and the doctors need a lot of time to read the abdominal CT images for COPD pre-evaluation. To improve the pre-evaluation efficiency, a deep network based on slice correlation information was proposed for COPD auxiliary diagnosis. First, by using a grouping approach, the architecture of the deep network is divided into several network branches, each of which aims to extract the local intra-slice association information of the CT images. Then, the outputs from multiple network branches are integrated via a BiLSTM to extract the global inter-slice association information between the adjacent CT slices. To further improve the ability of local feature extraction for each network branch, the enhanced multi-headed convolutional attention is designed by embedding the ConvNeXt into the existing multi-headed convolutional attention. Experimental results show that the proposed deep network achieves promising effectiveness for CT image classification on auiliarily diagnose of COPD, and the accuracy, sensitivity, specificity and AUC of the proposed network reach to approximately 92.15%, 94.17%, 91.17% and 95.33%, respectively.

Key words: chronic obstructive pulmonary disease (COPD), deep learning, multi-head convolutional attention

中图分类号: 

  • TP391
[1] MARKELIĆ I, HLAPČIĆ I, ČERI A, et al. Activation of NLRP3 inflammasome in stable chronic obstructive pulmonary disease [J]. Scientific Reports, 2022, 12(1): 7544.
[2] VESTBO J, HURD S S, AGUSTÍ A G, et al. Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary [J]. American Journal of Respiratory and Critical Care Medicine, 2013, 187(4): 347-365.
[3] MATHERS C D, LONCAR D. Projections of global mortality and burden of disease from 2002 to 2030 [J]. PLoS Medicine, 2006, 3(11): e442.
[4] 周祖东. 慢性阻塞性肺疾病急性加重期的临床治疗分析[J]. 中外医疗, 2020, 39(36): 67-69.
ZHOU Z D. Analysis of clinical treatment in acute exacerbation of chronic obstructive pulmonary disease [J]. China & Foreign Medical Treatment, 2020, 39(36): 67-69.
[5] LYNCH D A, AUSTIN J H M, HOGG J C, et al. CT-definable subtypes of chronic obstructive pulmonary disease: a statement of the Fleischner society [J]. Radiology, 2015, 277(1): 192-205.
[6] GALBÁN C J, HAN M K, BOES J L, et al. Computed tomography-based biomarker provides unique signature for diagnosis of COPD phenotypes and disease progression [J]. Nature Medicine, 2012, 18(11): 1711-1715.
[7] LYNCH D A, MOORE C M, WILSON C, et al. CT-based visual classification of emphysema: association with mortality in the COPDGene study [J]. Radiology, 2018, 288(3): 859-866.
[8] SHAH V, KENIYA R, SHRIDHARANI A, et al. Diagnosis of COVID-19 using CT scan images and deep learning techniques [J]. Emergency Radiology, 2021, 28(3): 497-505.
[9] POLAT Ö, ŞALK İ, DOĞAN Ö T. Determination of COPD severity from chest CT images using deep transfer learning network [J]. Multimedia Tools and Applications, 2022, 81(15): 21903-21917.
[10] MONDOÑEDO J R, SATO S, OGUMA T, et al. CT imaging-based low-attenuation super clusters in three dimensions and the progression of emphysema [J]. Chest, 2019, 155(1): 79-87.
[11] XU C, QI S, FENG J, et al. DCT-MIL: deep CNN transferred multiple instance learning for COPD identification using CT images [J]. Physics in Medicine & Biology, 2020, 65(14): 145011.
[12] AHMED J, VESAL S, DURLAK F, et al. COPD classification in CT images using a 3D convolutional neural network[C]// Bildverarbeitung für die Medizin 2020. Berlin: Springer, 2020: 39-45.
[13] VARCHAGALL M, NETHRAVATHI N P, CHANDRAMMA R, et al. Using deep learning techniques to evaluate lung cancer using CT images [J]. SN Computer Science, 2023, 4(2): 173.
[14] KIENZLE D, LORENZ J, SCHÖN R, et al. COVID detection and severity prediction with 3D-ConvNeXt and custom pretrainings[C]//Computer Vision–ECCV. Tel Aviv: Springer, 2022: 500-516.
[15] WU Y, DU R, FENG J, et al. Deep CNN for COPD identification by multi-view snapshot integration of 3D airway tree and lung field [J]. Biomedical Signal Processing and Control, 2023, 79: 104162.
[16] KOLLIAS D, ARSENOS A, SOUKISSIAN L, et al. MIA-COV19D: COVID-19 detection through 3-D chest CT image analysis[C]// International Conference on Computer Vision. Montreal: IEEE/CVF, 2021: 537-544.
[17] HUMPHRIES S M, NOTARY A M, CENTENO J P, et al. Deep learning enables automatic classification of emphysema pattern at CT [J]. Radiology, 2020, 294(2): 434-444.
[18] LIN H, ZHANG S, LI Q, et al. A new method for heart rate prediction based on LSTM-BiLSTM-Att [J]. Measurement, 2023, 207: 112384.
[19] FRIEDMAN P J. Imaging studies in emphysema [J]. Proceedings of the American Thoracic Society, 2008, 5(4): 494-500.
[20] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale [EB/OL]. arXiv: 2010.11929 (2021-01-03) [2023-03-15]. https://doi.org/10.48550/arXiv.2010.11929.
[21] LIU Z, MAO H, WU C Y, et al. A convnet for the 2020s[C]//Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE/CVF , 2022: 11976-11986.
[22] LI J, XIA X, LI W, et al. Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios [EB/OL]. arXiv: 2207.05501 (2022-08-16) [2023-03-15]. https://doi.org/10.48550/arXiv.2207.05501.
[23] WANG W, XIE E, LI X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]// International Conference on Computer Vision. Montreal: IEEE/CVF, 2021: 568-578.
[1] 吴菊华, 李俊锋, 陶雷. 基于知识图谱嵌入与深度学习的药物不良反应预测[J]. 广东工业大学学报, 2024, 41(01): 19-26,40.
[2] 温雯, 刘莹, 蔡瑞初, 郝志峰. 面向多粒度交通流预测的时空深度回归模型[J]. 广东工业大学学报, 2023, 40(04): 1-8.
[3] 钟耿君, 李东. 基于通道分离机制的双分支点云处理网络[J]. 广东工业大学学报, 2023, 40(04): 18-23.
[4] 金宇凯, 李志生, 欧耀春, 张华刚, 曾江毅, 陈搏超. 基于多阶段聚类的PM2.5质量浓度预测及对比研究[J]. 广东工业大学学报, 2023, 40(03): 17-24.
[5] 吴俊贤, 何元烈. 基于通道注意力的自监督深度估计方法[J]. 广东工业大学学报, 2023, 40(02): 22-29.
[6] 刘冬宁, 王子奇, 曾艳姣, 文福燕, 王洋. 基于复合编码特征LSTM的基因甲基化位点预测方法[J]. 广东工业大学学报, 2023, 40(01): 1-9.
[7] 徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(01): 56-60,76.
[8] 刘洪伟, 林伟振, 温展明, 陈燕君, 易闽琦. 基于MABM的消费者情感倾向识别模型——以电影评论为例[J]. 广东工业大学学报, 2022, 39(06): 1-9.
[9] 章云, 王晓东. 基于受限样本的深度学习综述与思考[J]. 广东工业大学学报, 2022, 39(05): 1-8.
[10] 郑佳碧, 杨振国, 刘文印. 基于细粒度混杂平衡的营销效果评估方法[J]. 广东工业大学学报, 2022, 39(02): 55-61.
[11] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[12] 赖峻, 刘震宇, 刘圣海. 基于全局数据混洗的小样本数据预测方法[J]. 广东工业大学学报, 2021, 38(03): 17-21.
[13] 岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(04): 35-41.
[14] 曾碧, 任万灵, 陈云华. 基于CycleGAN的非配对人脸图片光照归一化方法[J]. 广东工业大学学报, 2018, 35(05): 11-19.
[15] 陈旭, 张军, 陈文伟, 李硕豪. 卷积网络深度学习算法与实例[J]. 广东工业大学学报, 2017, 34(06): 20-26.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发