ISSN 1004-4140
CN 11-3017/P

基于注意力机制和迁移学习的COVID-19深度学习诊断方法

魏东旭, 阎丽华, 史军强

魏东旭, 阎丽华, 史军强. 基于注意力机制和迁移学习的COVID-19深度学习诊断方法[J]. CT理论与应用研究, 2021, 30(4): 477-486. DOI: 10.15953/j.1004-4140.2021.30.04.08
引用本文: 魏东旭, 阎丽华, 史军强. 基于注意力机制和迁移学习的COVID-19深度学习诊断方法[J]. CT理论与应用研究, 2021, 30(4): 477-486. DOI: 10.15953/j.1004-4140.2021.30.04.08
WEI Dongxu, YAN Lihua, SHI Junqiang. COVID-19 Deep Learning Diagnosis Method Based on Attention Mechanism and Transfer Learning[J]. CT Theory and Applications, 2021, 30(4): 477-486. DOI: 10.15953/j.1004-4140.2021.30.04.08
Citation: WEI Dongxu, YAN Lihua, SHI Junqiang. COVID-19 Deep Learning Diagnosis Method Based on Attention Mechanism and Transfer Learning[J]. CT Theory and Applications, 2021, 30(4): 477-486. DOI: 10.15953/j.1004-4140.2021.30.04.08

基于注意力机制和迁移学习的COVID-19深度学习诊断方法

详细信息
    作者简介:

    魏东旭,女,医学硕士,青岛妇女儿童医院住院医师,主要从事新生儿重症研究,E-mail:xuwdsjq@163.com;史军强*,男,理学博士,齐鲁工业大学(山东省科学院)山东省科学院海洋仪器仪表研究所助理研究员,主要从事数据同化和人工智能应用研究,E-mail:sjunq0@163.com。

  • 中图分类号: TP183

COVID-19 Deep Learning Diagnosis Method Based on Attention Mechanism and Transfer Learning

  • 摘要: 目的:结合2019新型冠状病毒(COVID-19)肺炎患者肺CT影像学特征,提出一种多级空间注意力机制(ML-SAM)下的肺CT图像自动诊断模型,探讨该模型在COVID-19辅助诊断上的价值。方法:收集目前公开的COVID-19患者肺CT数据样本,在深度迁移学习框架下引入空间注意力多级聚焦策略,将数据样本、注意力机制与深度迁移学习卷积神经网络相结合,构建可在肺CT图像上自动诊断COVID-19肺炎的融合模型。结果:本文建立的融合模型对肺CT图像具有较好的分类性能,模型对COVID-19的正确识别率可达95%,同时实现了弱监督条件下肺CT图像关键特征的有效聚焦和提取。结论:本文建立的融合模型可被放射科医生或医疗保健专业人员作为COVID-19爆发期间快速、有效筛查COVID-19病例的智能辅助工具。
    Abstract: Objective: This paper proposed a lung CT image automatic diagnosis model under multi level spatial attention mechanism (ML-SAM) associated with new coronavirus (COVID-19) infection in combination with the correcting CT imaging features. Methods: The published lung CT dataset samples of COVID-19 patients were collected and utilized to construct a fusion model by incorporating the attention mechanism and transfer learning strategy into the deep network. Results: The fusion model established in this paper realizes the rapid and effective auxiliary diagnosis of COVID-19. In the test dataset, the correct recognition rate of the model for COVID-19 can reach 95%. Conclusion: The deep transfer learning model established in this paper can be used by radiologists or health care professionals as an artificial intelligence tool to quickly and accurately screen COVID-19 cases during the outbreak of COVID-19.
  • [1]

    ROOSA K, LEE Y, LUO R, et al. Real-time forecasts of the 2019-nCoV epidemic in China from February 5th to February 24th, 2020[J]. Infectious Disease Modelling, 2020, 5:256-263.

    [2]

    LI Y, ZHANG H T, YANG X, et al. Prediction of criticality in patients with severe Covid-19 infection using three clinical features:A machine learning-based prognostic model with clinical data in Wuhan[J]. medRxiv preprint, 2020, DOI: 10.1101/2020.02.27.20028027.

    [3]

    MAHASE E. Coronavirus:Covid-19 has killed more people than SARS and MERS combined, despite lower case fatality rate[J]. British Medical Journal, 2020, 368:m641.

    [4]

    GUO H, ZHOU Y, LIU X, et al. The impact of the COVID-19 epidemic on the utilization of emergency dental services[J]. Journal of Dental Sciences, 2020, 15(4):564-567.

    [5]

    JIANG F, DENG L, ZHANG L, et al. Review of the clinical characteristics of coronavirus disease 2019(COVID-19)[J]. Journal of General Internal Medicine, 2020, 35(5):1545-1549.

    [6]

    WANG D, HU B, HU C, et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus infected pneumonia in Wuhan, China[J]. The Journal of the American Medical Association, 2020, 323(11):1061-1069.

    [7]

    World Health Organization. COVID-19 weekly epidemiological update[R]. Geneva:WHO, 2021.

    [8]

    XU X, JIANG X, MA C, et al. Deep learning system to screen coronavirus disease 2019 pneumonia[J]. arXiv:2002.09334, 2020.

    [9]

    HUANG P, LIU T Z, HUANG L S, et al. Use of chest CT in combination with negative RT-PCR assay for the 2019 novel coronavirus but high clinical suspicion[J]. Radiology, 2020, 295:22-23.

    [10]

    TAO A, YANG Z, HOU H, et al. Correlation of chest CT and RT-PCR testing in coronavirus disease 2019(COVID-19) in China:A report of 1014 cases[J]. Radiology, 2020, 296(2):E32-E40.

    [11]

    ABBAS A, ABDELSAMEA M M, GABER M M. Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network[J]. Applied Intelligence, 2021, 51(2):854-864.

    [12]

    MAGHDID H S, ASAAD A T, GHAFOOR K Z, et al. Diagnosing COVID-19 pneumonia from X-ray and CT images using deep learning and transfer learning algorithms[J]. arXiv:2004.00038, 2020.

    [13]

    NARIN A, KAYA C, PAMUK Z. Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks[J]. arXiv:2003.10849, 2020.

    [14]

    KASSANI S H, KASSASNI P H, WESOLOWSKI M J, et al. Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images:A machine learning-based approach[J]. arXiv:2004.10641, 2020.

    [15]

    HEMDAN E D, SHOUMAN M A, KARAR M E. COVIDX-Net:A framework of deep learning classifiers to diagnose COVID-19 in X-ray images[J]. arXiv:2003.11055, 2020.

    [16]

    YANG X, HE X, ZHAO J, et al. COVID-CT-dataset:A CT scan dataset about COVID-19[J]. arXiv:2003.13865, 2020.

    [17]

    HUANG L, PAN W, ZHANG Y, et al. Data augmentation for deep learning-based radio modulation classification[J]. IEEE Access, 2020, 8:1498-1506.

    [18]

    PAN S J, QIANG Y. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.

    [19]

    TAJBAKHSH N, SHIN J Y, GURUDU S R, et al. Convolutional neural networks for medical image analysis:Full training or fine tuning?[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1299-1312.

    [20]

    FU J, ZHENG H, TAO M. Look closer to see better:Recurrent attention convolutional neural network for fine-grained image recognition[C]//2017 IEEE Conference on Computer Vision & Pattern Recognition. IEEE, 2017:4438-4446.

    [21]

    SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409.1556, 2014.

    [22]

    JIA D, WEI D, SOCHER R, et al. ImageNet:A large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009:248-255.

    [23]

    GULLI A, PAL S. Deep learning with keras-implement neural networks with keras on theano and tensorflow[M]. Birmingham:Packt Publishing, 2017.

    [24]

    PLAWIAK P. Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system[J]. Expert Systems with Applications, 2018, 92:334-349.

    [25]

    LECUN Y, BENGIO Y, Hinton G. Deep learning[J]. Nature, 2015, 521:436-444.

    [26]

    XU Y, JIA Z, AI Y, et al. Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation[C]//2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2015:947-951.

  • 期刊类型引用(3)

    1. 裴雷,赵期康,王海,荣万水,尚存海. CTA在急性肠梗阻患者中的应用及诊断价值分析. 河北医科大学学报. 2022(01): 31-34 . 百度学术
    2. 马周鹏,陈炳叶,傅其添,付文兵,林观生. 3种不同肠道准备方法在CT小肠造影中的应用研究. CT理论与应用研究. 2019(03): 323-330 . 本站查看
    3. 符熙,何伟红,谢乐,方挺松,陈少銮,梁振华. 64排螺旋CT后处理技术对回盲部病变的诊断价值. CT理论与应用研究. 2019(04): 499-504 . 本站查看

    其他类型引用(0)

计量
  • 文章访问数:  263
  • HTML全文浏览量:  29
  • PDF下载量:  40
  • 被引次数: 3
出版历程
  • 收稿日期:  2021-04-21
  • 网络出版日期:  2021-09-23

目录

    /

    返回文章
    返回
    x 关闭 永久关闭