Research progress of imaging and AI-assisted diagnosis of pneumoconiosis

Abstract

Abstract: Occupational pneumoconiosis is the most serious occupational disease in China.Relevant literature reports that pneumoconiosis accounts for about 80% of all occupational disease reports.According to GBZ 70-2015 "diagnosis of occupational pneumoconiosis",the diagnosis of pneumoconiosis is mainly based on the dust exposure history,occupational health monitoring data and technical quality qualified X-ray posterior anterior chest film,with reference to pneumoconiosis standard film for diagnosis and staging.Chest X-ray is the most studied imaging technology in the diagnosis of pneumoconiosis in the past,and the technology in the early differential diagnosis of pneumoconiosis is relatively backward.With the progress of imaging technology and artificial intelligence technology,pneumoconiosis imaging research is gradually developing towards early and accurate diagnosis.Computed tomography（CT）,artificial intelligence assisted diagnosis,magnetic resonance imaging（MRI）,positron emission tomography X-ray computed tomography（PET-CT） assisted examination methods have become a hot spot in the research of pneumoconiosis assisted diagnosis in recent years.Through consulting and combing the literature,this paper reviews the relevant research content.This paper summarizes the advantages of various examination technologies and the problems existing in their application,and puts forward the possible challenges in the imaging and auxiliary diagnosis of pneumoconiosis in the future,so as to provide reference for the research direction of imaging and auxiliary diagnosis technology of pneumoconiosis in the future.

Key words: Pneumoconiosis, Imaging, Digital radiography, Computed tomography, Positron emission tomography computed tomography, Magnetic resonance imaging, Artificial intelligence aided diagnosis, Neural network

CLC Number:

R135.2

WANG Ningning, JIN Yi, WANG Chengxia, LIU Zhen, LIU Xiao, WANG Yanting. Research progress of imaging and AI-assisted diagnosis of pneumoconiosis. [J]OCCUPATION AND HEALTH, 2024, 40(6): 851-855.

References

[1] 李涛. 新时期职业病防治形势分析及对策建议[J].中国职业医学,2018,45(5):537-542.
[2] 王朝军,赵元生,马霞,等.煤工尘肺合并肺癌CT动态观察的征象分析[J].山西医药杂志,2018,47(5):511-513.
[3] HENNIGS S P,GARMER M,JAEGER H J,et al.Digital chest radiography with a large-area flat-panel silicon X-ray detector:clinical comparison with conventional radiography[J].Eur Radiol,2001,11:1688-1696.
[4] TAKASHIMA Y,SUGANUMA N,SAKURAZAWA H,et al.A flat-panel detector digital radiography and a storage phosphor computed radiography:Screening for pneumoconioses[J].J Occup Health,2007,49(1):39-45.
[5] FINK C,HALLSCHEIDT P J,NOELDGE G,et al.Clinical comparative study with a large-area amorphous silicon flat-panel detector:Image quality and visibility of anatomic structures on chest radiography[J].Am J Roentgenol,2002,178(2):481-486.
[6] 张云亭,袁聿德.医学影像检查技术学[M].北京:人民卫生出版社,2005:422-581.
[7] 陈钧强,蒋兆强,周斌,等.数字化X线摄影图像后处理参数调整在建立尘肺病诊断参考片中的作用[J].中华劳动卫生职业病杂志,2012 30(1):3-7.
[8] 刘亚,胡茂能,徐婷婷,等.胸部数字摄影窗口技术在尘肺诊断中的应用价值[J].安徽医学,2018,39(9):1060-1063.
[9] 盛炳镛,毛翎周,韶炜,等.尘肺病诊断中数字化X线摄影图像后处理的优化[J].中华劳动卫生职业病杂志,2013,31(11):825-829.
[10] 曾刘桃,陈钧强,蒋兆强,等.尘肺病影像学诊断的研究进展[J].预防医学,2021,33(12):1236-1239.
[11] 中华人民共和国国家卫生和计划生育委员会.职业性尘肺病的诊断:GBZ 70—2015[S].北京:中国标准出版社,2016:10-11.
[12] 王宁宁,王成霞,王小娟,等.尘肺病DR等大胸片打印方法研究[J].健康世界,2020(8):255-256.
[13] 贾守勤,赵斌,尚延海,等.常规DR胸片对肺结节漏诊原因的分析[J].医学与哲学,2009,30(4):25-34.
[14] ŞENER M U,ŞIMSEK C,ÖZKARA Ş,et al.Comparison of the international classification of high-resolution computed tomography for occupational and environmental respiratory diseases with the international labor organization international classification of radiographs of pneumoconiosis[J].Ind health,2019,57(4):495-502.
[15] 中华预防医学会劳动卫生与职业病分会职业性肺部疾病学组.尘肺病治疗中国专家共识(2018年版)[J].环境与职业医学,2018,35(8):677-689.
[16] 中华预防医学会职业病分会尘肺病影像学组.尘肺病胸部CT规范化检查技术专家共识(2020年版)[J].环境与职业医学,2020,37(10):943-949.
[17] SERGIACOMI G,CICCIO C,BOI L,et al.Ground-glass opacity:High-resolution computed tomography and 64-multi-slice computed tomography findings comparison[J].Eur J Radiol,2010,74(3):479-483.
[18] 张永林,茹晋丽,薛雁山,等.多层螺旋CT扫描冠状位图像重建诊断肺间质性病变的价值[J].中国医学影像学杂志,2005,13(2):148-149.
[19] SOYDAN L.The Role of high-resolution computed tomography in the evaluation of pneumoconiosis[J].Haydarpasanumune Med,2021,61(2):234-240.
[20] HERING K G,TUENGERTHAL S,KRAUS T.Standardisierte CT/HRCT-Klassifikation der bundesrepublik deutschland frarbeits-und umweltbedingte thoraxerkrankungen[J].Der Radiologe,2004,5(44):500-512.
[21] SAKAI M,MURAYAMA S,GIBO M,et al.Can maximum intensity projection images with multidetector-row computed tomography help to differentiate between the micronodular distribution of focal and diffuse infiltrative lung diseases?[J].J Comput Assist Tomo,2005,29(5):588-591.
[22] 王成霞,柳澄,孙炳欣,等.CT最大密度投影厚度与方位对显示尘肺小结节的优化选择研究[J].中国医疗设备,2021,36(10):52-55.
[23] 王旭,李宝平,曾庆玉,等.煤工尘肺肺内结节的病理与64排螺旋CT影像表现[J].中华劳动卫生职业病杂志,2014,32(9):668-673.
[24] 王睿,李靖,方梦捷,等.基于能谱CT的影像组学术前预测进展期胃癌淋巴结转移的价值[J].中华医学杂志,2020,100(21):1617-1622.
[25] 陈步东,贺文,李剑颖,等.双能能谱CT定量检测尘肺SiO₂[J].中国医学影像术,2011,27(12):2393-2397.
[26] HUANG W Y,MUO C H,LIN C Y,et al.Paediatric head CT scan and subsequent risk of malignancy and benign brain tumour:A nation-wide population-based cohort study[J].Brit J Cancer,2014,110(9):2354-2360.
[27] LUAN F J,ZHANG J,MAK K C,et al.Low radiation X-rays:Benefiting people globally by reducing cancer risks[J].Int J Med Sci,2021, 18(1):73-80.
[28] LEE J Y,CHUNG M J,CHIN A Y,et al.Ultra-low-dose MDCT of the chest:Influence on automated lung nodule detection[J].Korean J Radiol,2008,9(2):95-101.
[29] HAYASHI H,ASHIZAWA K,TAKAHASHI M,et al.The diagnosis of early pneumoconiosis in dust-exposed workers:Comparison of chest radiography and computed tomography[J].Acta Radiol,2022,63(7):909-913.
[30] GUNEYLI S,TOR M,HASSOY H,et al.Spin-echo and diffusion-weighted MRI in differentiation between progressive massive fibrosis and lung cancer[J].Diagninterv Radiol,2021,27(4):469-475.
[31] HEKIMOGLU K,SANCAK T,TOR M,et al.Fast MRI evaluation of pulmonary progressive massive fibrosis with VIBE and HASTE sequences:Comparison with CT[J].Diagninterv Radiol,2010,16:30-37.
[32] OHNO Y,NISHIO M,KOYAMA H,et al.Pulmonary MR imaging with ultra-short TEs:Utility for disease severity assessment of connective tissue disease patients[J].Eur J Radiol,2013,82(8):1359-1365.
[33] OHNO Y,NISHIO M,KOYAMA H,et al.Pulmonary 3 T MRI with ultrashort TEs:Influence of ultrashort echo time interval on pulmonary functional and clinical stage assessments of smokers[J].J Magn Reason Imaging,2014,39(4):988-997.
[34] MA W,SHEIKH K,SVENNINGSEN S,et al.Ultra-short echo-time pulmonary MRI:Evaluation and reproducibility in COPD subjects with and without bronchiectasis[J].J Magn Reason Imaging,2015,41(5):1465-1474.
[35] 钱根年. 分子影像设备PET/CT成像系统的技术进展[J].功能与分子医学影像学,2019,8(1):1579-1582.
[36] SURTI S,KUHN A,WERNER M E,et al.Performance of Philips Gemini TF PET/CT scanner with special consideration for its time-of-flight imaging capabilities[J].J Nucl Med,2007,48(3):471-480.
[37] 王艳丽,张华,崔新建,等.18F-FDG PET/CT在鉴别尘肺病大阴影良恶性的应用价值[J].中华劳动卫生职业病杂志,2014,3(3):186-189.
[38] KANEGAE K,NAKANO I,KIMURA K,et al.Comparison of MET-PET and FDG-PET for differentiation between benign lesions and lung cancer in pneumoconiosis[J].Ann Nucl Med,2007,21:331-337.
[39] JE S K,IM AHN M,Park Y H,et al.Detection of a small lung cancer hidden in pneumoconiosis with progressive massive fibrosis using F-18 fluorodeoxyglucose PET/CT[J].Clinnucl Med,2007,32(3):247-248.
[40] ÖZKAN M,AYAN A,ARIK D,et al.FDG PET findings in a case with acute pulmonary silicosis[J].Ann Nucl Med,2009,23:883-886.
[41] CHUNG S Y,LEE J H,KIM T H,et al.18 F-FDG PET imaging of progressive massive fibrosis[J].Ann Nucl Med,2010,24:21-27.
[42] KAILASAM S P,SATHIK M M.A novel hybrid feature extraction model for classification on pulmonary nodules[J].Asian Pac J Cancer Prev,2019,20(2):457-468.
[43] KHAN S A,NAZIR M,KHAN M A,et al.Lungs nodule detection framework from computed tomography images using support vector machine[J].Microsc Res Techniq,2019,82(8):1256-1266.
[44] OKUMURA E,KAWASHITA I,ISHIDA T.Development of CAD based on ANN analysis of power spectra for pneumoconiosis in chest radiographs:Effect of three new enhancement methods[J].Radiolphys Technol,2014,7:217-227.
[45] ANNARUMMA M,WITHEY S J,BAKEWELL R J,et al.Automated triaging of adult chest radiographs with deep artificial neural networks[J].Radiology,2019,291(1):196-202.
[46] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C].//Proceedings of the IEEE conference on computer vision and pattern recognition,2015:3431-3440.
[47] 邓奎,陈汉华.基于深度学习与传统图像技术的尘肺辅助诊断[D].武汉:华中科技大学,2017.
[48] 张兰兰,张宇.基于迁移学习的尘肺病胸片分析与识别[D].武汉:华中科技大学,2020.
[49] 王峥,钱青俊,张建芳,等.计算机辅助诊断在尘肺病诊断中应用价值[J].中国职业医学,2020,47(4):428-431.
[50] 张敏,陈钧强.人工智能技术在尘肺病诊断中的应用研究进展[J].环境与职业医学,2020,37(2):192-196.
[51] 中国生物医学工程学会医学人工智能分会胸部影像及职业病标准组.尘肺病数据标注规范与质量控制专家共识(2020年版)[J].环境与职业医学,2020,37(6):523-529.