[1]李文,韩冬,郭佑民,等.基于密度分布特征的深度神经网络模型诊断COVID-19的价值[J].中国医学物理学杂志,2022,39(8):972-979.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.010]
　LI Wen,HAN Dong,GUO Youmin,et al.Diagnostic value of deep neural network model based on characteristics of density distribution in COVID-19[J].Chinese Journal of Medical Physics,2022,39(8):972-979.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.010]
点击复制

基于密度分布特征的深度神经网络模型诊断COVID-19的价值()
分享到：

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

卷:
39卷
期数:
2022年第8期
页码:
972-979
栏目:
医学影像物理
出版日期:
2022-08-04

文章信息/Info

Title:
Diagnostic value of deep neural network model based on characteristics of density distribution in COVID-19
文章编号:
1005-202X（2022）08-0972-08
作者:
李文1; 韩冬2; 郭佑民3; 任转勤1; 田宏哲1
1.宝鸡市中心医院医学影像科， 陕西 宝鸡 721008； 2.陕西中医药大学附属医院医学影像科， 陕西 咸阳 712021； 3.西安交通大学第一附属医院医学影像科， 陕西 西安 710061
Author(s):
LI Wen1;  HAN Dong2;  GUO Youmin3;  REN Zhuanqin1;  TIAN Hongzhe1
1.Department of Radiology, Baoji Central Hospital, Baoji 721008, China 2. Department of Radiology, Affiliated Hospital of Shaanxi University of Chinese Medicine, Xianyang 712021, China 3. Department of Radiology, the First Affiliated Hospital of Xian Jiaotong University, Xian 710061, China
关键词:
新型冠状病毒肺炎; 密度分布特征; CT图像特征; 深度神经网络
Keywords:
Keywords: corona virus disease 2019 characteristic of density distribution CT imaging feature deep neural network
分类号:
R318；R563.1
DOI:
DOI:10.3969/j.issn.1005-202X.2022.08.010
文献标志码:
A
摘要:
目的：评价基于密度分布特征（CDD）的深度神经网络（DNN）模型对新型冠状病毒肺炎（COVID-19）的诊断价值。方法：收集42例COVID-19病例和43例非COVID-19肺炎病例。将所有患者的211份胸部CT图像分为训练集（n=128）和验证集（n=83）。参考北美放射学会发布的COVID-19相关性肺炎的CT结构化报告，构建基于CT影像特征的DNN模型（DNN-CTIF）。根据胸部CT图像上肺炎CDD建立DNN-CDD模型。采用ROC曲线分析和决策曲线分析对两种模型进行评价。结果：DNN-CTIF模型的AUC在训练集为0.927，在验证集为0.829。DNN-CDD模型的AUC在训练集为0.965，在验证集为0.929。DNN-CDD模型在验证集的AUC高于DNN-CTIF模型（P=0.047）。决策曲线分析表明在0.04~1.00概率阈值范围内，DNN-CDD模型相比DNN-CTIF模型使患者的净获益更高。结论：DNN-CTIF和DNN-CDD模型对COVID-19均具有较好的诊断性能，其中DNN-CDD模型优于DNN-CTIF模型。
Abstract:
Abstract: Objective To evaluate the efficacy of a deep neural network (DNN) model based on characteristics of density distribution (CDD) in diagnosing corona virus disease 2019 (COVID-19). Methods A total of 42 cases of COVID-19 and 43 cases of non-COVID-19 pneumonia were enrolled in the study. The 211 chest CT images of these patients were divided into a training set (n=128) and a validation set (n=83). Referring to the CT structured report of COVID-19-related pneumonia issued by Radiological Society of North America, the CT imaging features (CTIF) based DNN model (DNN-CTIF) was constructed. Meanwhile, the DNN-CDD model was constructed based on the pneumonia CDD in the chest CT images. ROC curve analysis and decision curve analysis were used to evaluate the diagnostic performances of the two models. Results The AUC of DNN-CTIF model and DNN-CDD model was 0.927 and 0.965 in training set. The AUC of DNN-CDD model in validation set was significantly higher than that of DNN-CTIF model (0.829 vs 0.929, P=0.047). Moreover, the decision curve analysis showed that DNN-CDD model provided more net benefit than DNN-CTIF model in the range of 0.04-1.00 probability threshold.Conclusion Both DNN-CTIF and DNN-CDD models have good diagnostic performance for COVID-19, and DNN-CDD model is superior to DNN-CTIF model.

相似文献/References:

[1]杨勇,吴慕禹,苗丽霞,等.高压氧辅助治疗新型冠状病毒肺炎的介入时机及其临床疗效[J].中国医学物理学杂志,2020,37(5):641.[doi:10.3969/j.issn.1005-202X.2020.05.021]
　YANG Yong,WU Muyu,MIAO Lixia,et al.Timing of intervention and therapeutic efficacy of adjuvant hyperbaric oxygen therapy againstCOVID-19[J].Chinese Journal of Medical Physics,2020,37(8):641.[doi:10.3969/j.issn.1005-202X.2020.05.021]
[2]刘思远,张丽军,刘雷.人工智能在抗击新型冠状病毒肺炎疫情中的应用[J].中国医学物理学杂志,2020,37(8):1076.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.026]
　LIU Siyuan,ZHANG Lijun,LIU Lei.Application of artificial intelligence in fighting against COVID-19 pandemic[J].Chinese Journal of Medical Physics,2020,37(8):1076.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.026]
[3]邓灵波,周雯,赵双全,等.人工智能辅助诊断系统在新型冠状病毒肺炎诊断中的初步应用[J].中国医学物理学杂志,2020,37(12):1604.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.025]
　DENG Lingbo,ZHOU Wen,ZHAO Shuangquan,et al.Preliminary application of AI diagnosis system in the diagnosis of the novel coronavirus infected pneumonia[J].Chinese Journal of Medical Physics,2020,37(8):1604.[doi:DOI:10.3969/j.issn.1005-202X.2020.12.025]
[4]韩冬,于勇,贺太平,等.基于密度分布特征及机器学习诊断COVID-19相关性肺炎[J].中国医学物理学杂志,2021,38(3):387.[doi:DOI:10.3969/j.issn.1005-202X.2021.03.022]
　HAN Dong,YU Yong,HE Taiping,et al.Diagnosis of COVID-19 associated pneumonia based on density distribution features and machine learning[J].Chinese Journal of Medical Physics,2021,38(8):387.[doi:DOI:10.3969/j.issn.1005-202X.2021.03.022]
[5]王雁南,周俊林,刘建莉,等.多排螺旋CT低剂量扫描高分辨率重建在新型冠状病毒肺炎筛查中的应用[J].中国医学物理学杂志,2021,38(4):456.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.012]
　WANG Yannan,,et al.Application of low-dose multidetector CT scan and high-resolution reconstruction in COVID-19 pneumonia screening[J].Chinese Journal of Medical Physics,2021,38(8):456.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.012]
[6]蔡晓琼,郭晶磊,黄继汉,等.人工智能技术在新型冠状病毒肺炎中的应用[J].中国医学物理学杂志,2021,38(7):915.[doi:DOI:10.3969/j.issn.1005-202X.2021.07.024]
　CAI Xiaoqiong,GUO Jinglei,HUANG Jihan,et al.Advances in research on artificial intelligence technology in COVID-19[J].Chinese Journal of Medical Physics,2021,38(8):915.[doi:DOI:10.3969/j.issn.1005-202X.2021.07.024]
[7]顾国浩,龙英文,吉明明.U-Net改进及其在新冠肺炎图像分割的应用[J].中国医学物理学杂志,2022,39(8):1041.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.022]
　GU Guohao,LONG Yingwen,JI Mingming.Improved U-Net and its application in COVID-19 image segmentation[J].Chinese Journal of Medical Physics,2022,39(8):1041.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.022]

备注/Memo

备注/Memo:
【收稿日期】2022-03-10 【基金项目】陕西中医药大学学科创新团队建设项目（2019-QN09，2019-YS04） 【作者简介】李文，硕士，主治医师，研究方向：中枢神经系统及呼吸系统影像诊断，E-mail: 13892759171@163.com
更新日期/Last Update: 2022-09-05