Application value of pulmonary tuberculosis screening technology based on artificial intelligence in image diagnosis of primary hospital

doi:10.19871/j.cnki.xfcrbzz.2021.02.014

Abstract

Abstract: Objective To evaluate the performance of artificial intelligence system in detecting tuberculosis (TB) in primary hospital, and improve the level of tuberculosis screening in primary hospitals. Methods The chest X-ray images and clinical data of 11616 patients in the first people's Hospital of Kashgar region from March 2019 to July 2020 were collected, among which 10 399 cases were selected as the training set and 1217 cases were selected as the test set. There were 535 TB cases, 6972 normal cases and 2892 non-tuberculosis abnormal cases in the training set, and there were 305 TB cases, 840 normal cases and 72 cases of non-tuberculosis abnormal cases in the test set. ① Comparing TB detection performances of AI system and local radiologists.② Comparing the diagnostic efficiency of radiologists with AI assistance and radiologists without AI assistance. Results ① The sensitivity of intelligent diagnosis was 86.8%, which was higher than that of local junior radiologists (63.3%). There was significant difference between the two diagnostic methods (P<0.05). ② With AI-assisted diagnosis, the average diagnosis time of local primary radiologists decreased from (37.4±1.2) s to (14.0±4.3) s, The difference was statistically significant (P<0.05). Conclusions Based on artificial intelligence tuberculosis screening technology, the efficiency and effectiveness of tuberculosis imaging diagnosis can be improved, and it is helpful to the tuberculosis screening in remote areas or grass-roots hospitals.

Key words: Artificial intelligence, Diagnosis of tuberculosis, Radiologist, Chest X-ray, Convolutional neural network

Mayidili Nijiati, Alimujiang Abudukaiyoumu, Miriguli Damaola, Abudukeyoumujiang Abulizi, Tian Xuwei, Dai Guochao. Application value of pulmonary tuberculosis screening technology based on artificial intelligence in image diagnosis of primary hospital[J]. Electronic Journal of Emerging Infectious Diseases, 2021, 6(2): 138-142.

References

[1] 范琳, 刘一典, 肖和平. 国内《耐药结核病化学治疗指南(2019年)》与相关共识的特色及要点分析[J]. 中国防痨杂志, 2020, 42(2):91-94.
[2] QI YC, MA MJ, Li DJ, et al.Multidrug-Resistant and Extensively Drug-Resistant Tuberculosis in Multi-Ethnic Region, Xinjiang Uygur Autonomous Region, China[J]. PLoS ONE, 2012, 34(4):25-35.
[3] GUlSHAN V, PENG L, CORAM M, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs[J]. JAMA, 2016,316(22):2402-2410.
[4] 王宇. 全国第五次结核病流行病学抽样调查资料汇编[M]. 军事医学科学出版社, 2011.
[5] HWANG S, KIMH E, JIHOON JMD, et al.A novel approach for tuberculosis screening based on deep convolutional neural networks[C]. Medical Imaging: Computer-aided Diagnosis. International Society for Optics and Photonics, 2016, 36(5): 2751-2759.
[6] ASAD ZSM, SALMAN HS, BRAM VG, et al.Evaluation of the diagnostic accuracy of Computer-Aided Detection of tuberculosis on Chest radiography among private sector patients in Pakistan[J]. Sci Rep, 2018, 8(1):12339-12348.
[7] XIONG Y, BA X,HOU A, et al.Automatic detection of mycobacterium tuberculosis using artificial intelligence[J]. J Thorac Dis, 2018, 10(3):1936-1940.
[8] LAKHANI P, SUNDARAMB. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks[J]. Radiology, 2017, 284(2): 574-582.
[9] BECKER AS, BLUTHGEN C, PHI VAN VD, et al.Detection of tuberculosis patterns in digital photographs of chest X-ray images using deep learning: feasibility study[J]. Int J Tuberc Lung Dis, 2018, 22(3): 328-335.
[10] 周林, 刘二勇. "早诊断及规范治疗肺结核患者"是落实最新国家行业标准及技术规范的精髓[J]. 中国防痨杂志, 2020, 42(9):894-895.
[11] LIU L, CHENG J, QUAN Q, et al.A Survey on U-shaped networks in Medical Image Segmentations[J]. Neurocomputing, 2020, 27(8): 216-256.
[12] WU Z, SHEN C,HENGELA VD.Wider or Deeper: Revisiting the ResNet Model for Visual Recognition[J]. Pattern Recognition, 2016, 272(3):635-654.
[13] SZEGEDY C, VANHOUCKE V, LOFFE S, et al.Rethinking the Inception Architecture for Computer Vision[J]. Dig Liver Dis, 2016:2818-2826.
[14] LAKHANI P, SUNDARAM B.Deep Learning at Chest Radiography: AutomatedClassification of Pulmonary Tuberculosis by Using Convolutional Neural Networks[J]. Radiology, 2017, 284(2):574-582.
[15] 张广恩, 符彩云, 黄静静,等. 海南省结核分枝杆菌耐药影响因素分析[J]. 公共卫生与预防医学, 2017, 28(1):18-22.
[16] MELENDEZ J, SANCHEZCI,PHILIPSEN RHHM, et al.An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information[J]. Sci Rep, 2016, 6:25265.
[17] HOOG AH, MEME HK, VAN DEUTEKOM H, et al.High sensitivity of chest radiograph reading by clinical officers in a tuberculosis prevalence survey[J]. Int J Tuberc Lung Dis, 2011, 15(10):1308-1314.
[18] KRIZHEVSKY A, SUTSKEVER I, HINTON GE.ImageNet Classification with Deep Convolutional Neural Networks[C]. NIPS. Curran Associates Inc, 2012, 1097-1105.
[19] 国家感染性疾病临床医学研究中心, 深圳市第三人民医院,《中国防痨杂志》编辑委员会. 肺结核活动性判断规范及临床应用专家共识[J]. 中国防痨杂志, 2020, 42(4):301-307.
[20] CHUNLI Q, DEMIN Y, YONGHONG S, et al.Computer-aided detection in chest radiography based on artificial intelligence: A survey[J]. Biomed Eng Online, 2018, 17(1):1-23.
[21] 闫明艳, 陈根铭, 赖超, 等. 人工智能对肺结核患者病变检出及定性诊断价值研究[J/CD]. 新发传染病电子杂志, 2018, 3(4): 214-217.
[22] CAO XW, QIAN Y.Prediction of Multidrug-Resistant TB from CT Pulmonary Images Based on Deep Learning Techniques[J]. Mol Pharm, 2018, 15(10):4326-4335.
[23] LURE FYM, JAEGER S, ANTANI S, 等. 自动化显微镜检测和数字化胸片诊断系统在肺结核筛查中的应用[J/CD]. 新发传染病电子杂志, 2017, 2(1):5-9.
[24] BAR Y, DIAMANT I, WOLF L, et al.Deep learning with non-medical training used for chest pathology identification[C]. Medical Imaging 2015: Computer-Aided Diagnosis. International Society for Optics and Photonics, 2015: 94140V.
[25] HUA KL, HUS CH, HIDAYATIS C, et al.Computer-aided classification of lung nodules on computed tomography images via deep learning technique[J]. Onco Targets Ther, 2015, 8:2015-2022.
[26] HWANG S, KIM HE, JIHOONJ MD, et al.A novel approach for tuberculosis screening based on deep convolutional neural networks[C]. Medical Imaging: Computer-aided Diagnosis. International Society for Optics and Photonics, 2016:97852W.