[1]董芳芬,陈群,李诺兮,等.基于深度学习的儿童肺炎检测模型建立及应用[J].中国医学物理学杂志,2022,39(12):1579-1584.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.020]
　DONG Fangfen,CHEN Qun,et al.Establishment and application of a deep learning-based model for pneumonia detection in children[J].Chinese Journal of Medical Physics,2022,39(12):1579-1584.[doi:DOI:10.3969/j.issn.1005-202X.2022.12.020]
点击复制

基于深度学习的儿童肺炎检测模型建立及应用()
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12期
页码:
1579-1584
栏目:
医学人工智能
出版日期:
2022-12-25

文章信息/Info

Title:
Establishment and application of a deep learning-based model for pneumonia detection in children
文章编号:
1005-202X（2022）12-1579-06
作者:
董芳芬1; 2; 陈群3; 李诺兮2; 徐本华1; 2; 李小波1; 2; 4
1.福建医科大学附属协和医院放疗科/福建省肿瘤智能影像与精准放疗重点实验室/福建省消化、血液系统与乳腺恶性肿瘤放射与治疗临床医学研究中心， 福建 福州 350001； 2.福建医科大学医学影像学院， 福建 福州 350004； 3.西北工业大学计算机学院， 陕西 西安 710072； 4.清华大学工程物理系， 北京 100084
Author(s):
DONG Fangfen1;  2;  CHEN Qun3;  LI Nuoxi2;  XU Benhua1;  2;  LI Xiaobo1;  2;  4
1. Department of Radiation Oncology, Fujian Medical University Union Hospital/Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors/Clinical Research Center for Radiology and Radiotherapy for Digestive, Hematological and Breast Malignancies of Fujian Province, Fuzhou 350001, China 2. School of Medical Imaging, Fujian Medical University, Fuzhou 350004, China 3. School of Computer Science, Northwestern Polytechnical University, Xian 710072, China 4. Department of Engineering Physics, Tsinghua University, Beijing 100084, China
关键词:
儿童; 肺炎; 深度学习; 神经网络
Keywords:
Keywords: children pneumonia deep learning neural network
分类号:
R318；R445.4
DOI:
DOI:10.3969/j.issn.1005-202X.2022.12.020
文献标志码:
A
摘要:
目的：基于深度学习根据儿童胸部X光正位数字影像构建肺炎自动判别模型，辅助临床诊断，提高影像诊断效率。方法：首先通过选取公开数据集5 856张儿童胸片（肺炎4 273张，正常1 583张），分为训练集、验证集和测试集，基于Resnet-50神经网络构建儿童肺炎自动判别模型，利用验证集选取最优模型，在测试集上做内部独立验证。进一步收集6家医疗单位共611张儿童胸片（肺炎300张，正常311张）进行外部验证，并根据验证结果对模型进行微调后再次测试，使模型更适合临床使用。结果：基于深度学习技术和公开数据集数据构建儿童肺炎自动判别模型，准确率为98.48%，精确率为99.54%，召回率为98.81%，F1-score为98.86%，AUC为0.999。外部验证初始结果准确率为59.90%，选用部分外部验证数据微调模型后，独立测试准确度提升至85.00%。结论：基于深度学习根据公开数据集构建肺炎自动判别模型具有可行性，准确率达98.48%，在实际临床使用时应根据具体使用条件选取适量数据集对模型进行微调。
Abstract:
Abstract: Objective To construct a deep learning-based model for automatically detecting pneumonia according to the digital ortho-images of childrens chest X-ray for assisting clinical diagnosis and improving the efficiency of image diagnosis. Methods A total of 5 856 pediatric chest radiographs, including 4 273 chest radiographs of pneumonia and 1 583 normal chest radiographs, were selected from the public data set and divided into training set, verification set and test set. A model for the automated pediatric pneumonia detection was constructed based on Resnet-50. The validation set was used for selecting the optimal model, and the test set for carrying out internal independent validation. In addition, 611 pediatric chest radiographs, including 300 chest radiographs of pneumonia and 311 normal chest radiographs, were further collected from 6 medical units for external validation, and the model was fine-tuned according to validation results and then tested again to make it more suitable for clinical application. Results An automated detection model for pediatric pneumonia was successfully constructed using deep learning technology and public data set. The accuracy, precision, recall, F1-score and AUC of the model were 98.48%, 99.54%, 98.81%, 98.86% and 0.999, respectively. After fine-tuning the model with some external validation data, the accuracy of the independent test was improved from 59.90% (preliminary external validation) to 85.00% (independent test). Conclusion It is feasible to construct an automated pneumonia detection model using deep learning and public data set, and the accuracy of the model can reach 98.48%. In practice, the model should be fine-tuned by selecting the appropriate data set according to the specific conditions.

相似文献/References:

[1]胡立伟,钟玉敏.3D打印技术在儿童先天性心脏病诊断及治疗中的应用进展[J].中国医学物理学杂志,2015,32(04):514.[doi:10.3969/j.issn.1005-202X.2015.04.014]
[2]阮德斌,陈勇,赵剑波,等.透视引导儿童右锁骨下静脉穿刺置管方法[J].中国医学物理学杂志,2015,32(06):874.[doi:doi:10.3969/j.issn.1005-202X.2015.06.024]
　[J].Chinese Journal of Medical Physics,2015,32(12):874.[doi:doi:10.3969/j.issn.1005-202X.2015.06.024]
[3]杨玉刚,齐洪志,许林,等.适形与调强射野衔接技术在儿童全中枢神经系统放疗中的应用价值[J].中国医学物理学杂志,2016,33(7):678.[doi:10.3969/j.issn.1005-202X.2016.07.007]
　[J].Chinese Journal of Medical Physics,2016,33(12):678.[doi:10.3969/j.issn.1005-202X.2016.07.007]
[4]张立敏,王艳秋,王文瑶,等.二维纵向应变及应变率技术评价室间隔缺损修补术后室间隔功能变化[J].中国医学物理学杂志,2016,33(8):805.[doi:10.3969/j.issn.1005-202X.2016.08.010]
　[J].Chinese Journal of Medical Physics,2016,33(12):805.[doi:10.3969/j.issn.1005-202X.2016.08.010]
[5]姚小芬,钟玉敏,胡立伟,等. 三维打印技术在狭颅症矫治手术中的应用[J].中国医学物理学杂志,2017,34(4):423.[doi:DOI:10.3969/j.issn.1005-202X.2017.04.020]
[6]陆敏达,张财源,侯亮,等. 儿童胰腺实性假乳头状瘤多排螺旋CT表现[J].中国医学物理学杂志,2018,35(8):909.[doi:DOI:10.3969/j.issn.1005-202X.2018.08.009]
　LU Minda,ZHANG Caiyuan,HOU Liang,et al. Multidetector computed tomography features of solid pseudopapillary tumor of pancreas in children[J].Chinese Journal of Medical Physics,2018,35(12):909.[doi:DOI:10.3969/j.issn.1005-202X.2018.08.009]
[7]欧阳荣珍,孙爱敏,王谦,等. 基于3D打印技术构建仿真儿童CT增强腹部体模的测试研究[J].中国医学物理学杂志,2019,36(3):307.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.012]
　OUYANG Rongzhen,SUN Aimin,WANG Qian,et al. Testing research on a realistic pediatric abdominal phantom with CT enhancement constructed with 3D printing technology[J].Chinese Journal of Medical Physics,2019,36(12):307.[doi:DOI:10.3969/j.issn.1005-202X.2019.03.012]
[8]申严,杨普查,卓宋明.床旁超声联合支气管镜在被动卧床肺炎患者住院管理评估指标中的价值[J].中国医学物理学杂志,2019,36(8):933.[doi:DOI:10.3969/j.issn.1005-202X.2019.08.014]
　SHEN Yan,YANG Pucha,ZHUO Songming.Value of bedside ultrasound combined with bronchoscopy in the index evaluation of inpatient management for bedridden patients with pneumonia[J].Chinese Journal of Medical Physics,2019,36(12):933.[doi:DOI:10.3969/j.issn.1005-202X.2019.08.014]
[9]袁世俊,李金凝,彭海腾,等.肝脏间叶性错构瘤的病理与CT表现[J].中国医学物理学杂志,2019,36(9):1029.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.007]
　YUAN Shijun,LI Jinning,PENG Haiteng,et al.Pathological and CT manifestations of mesenchymal hamartoma of the liver[J].Chinese Journal of Medical Physics,2019,36(12):1029.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.007]
[10]陈静,于勇,段海峰,等.基于定量CT对新型冠状病毒肺炎肺部改变的纵向研究[J].中国医学物理学杂志,2020,37(4):445.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.009]
　CHEN Jing,YU Yong,DUAN Haifeng,et al.Longitudinal study of lung changes induced by COVID-19 based on quantitative CT[J].Chinese Journal of Medical Physics,2020,37(12):445.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.009]

备注/Memo

备注/Memo:
【收稿日期】2022-06-08 【基金项目】福建省科技厅（高校产学研）项目（2020Y4010） 【作者简介】董芳芬，硕士研究生，技师，主要研究方向：医学物理与智能影像，E-mail: 944866709@qq.com 【通信作者】李小波，副主任医师，主要研究方向：医学物理与智能影像，E-mail: lixiaobo2004@126.com；徐本华，主任医师，主要研究方向：肿瘤智能影像与精准放疗，E-mail: benhuaxu@163.com
更新日期/Last Update: 2022-12-23