Download PDF
Semin Respir Crit Care Med 2023; 44(03): 362-369
DOI: 10.1055/s-0043-1767760
Review Article

Artificial Intelligence in Quantitative Chest Imaging Analysis for Occupational Lung Disease

Narufumi Suganuma
1   Department of Environmental Medicine, Kochi Medical School, Nankoku, Kochi, Japan
,
Shinichi Yoshida
2   School of Information, Kochi University of Technology, Nankoku, Kochi, Japan
,
Yuma Takeuchi
1   Department of Environmental Medicine, Kochi Medical School, Nankoku, Kochi, Japan
3   Department of Radiology, Kochi Medical School Hospital, Nankoku, Kochi, Japan
,
Yoshua K. Nomura
1   Department of Environmental Medicine, Kochi Medical School, Nankoku, Kochi, Japan
,
Kazuhiro Suzuki
4   Department of Radiology, School of Medicine, Juntendo University, Bunkyo City, Tokyo, Japan
› Author Affiliations
› Further Information
    Permissions and Reprints

Abstract

Occupational lung disease manifests complex radiologic findings which have long been a challenge for computer-assisted diagnosis (CAD). This journey started in the 1970s when texture analysis was developed and applied to diffuse lung disease. Pneumoconiosis appears on radiography as a combination of small opacities, large opacities, and pleural shadows. The International Labor Organization International Classification of Radiograph of Pneumoconioses has been the main tool used to describe pneumoconioses and is an ideal system that can be adapted for CAD using artificial intelligence (AI). AI includes machine learning which utilizes deep learning or an artificial neural network. This in turn includes a convolutional neural network. The tasks of CAD are systematically described as classification, detection, and segmentation of the target lesions. Alex-net, VGG16, and U-Net are among the most common algorithms used in the development of systems for the diagnosis of diffuse lung disease, including occupational lung disease. We describe the long journey in the pursuit of CAD of pneumoconioses including our recent proposal of a new expert system.

Keywords

computer-assisted diagnosis - artificial intelligence - convolutional neural network


Publication History

Article published online:
18 April 2023

© 2023. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA

 

  • References

  • 1 Hoy RF, Jeebhay MF, Cavalin C. et al. Current global perspectives on silicosis-convergence of old and newly emergent hazards. Respirology 2022; 27 (06) 387-398
    CrossrefPubMedGoogle Scholar
  • 2 Algranti E, Bedrikow B, Ribeiro FSN, Handar Z. . National Program for the Elimination of Silicosis, Brazil (NPES-B). Accessed March 9, 2023 at: https://www.researchgate.net/profile/Fatima-Ribeiro/publication/242664709_NATIONAL_PROGRAM_FOR_THE_ELIMINATION_OF_SILICOSIS_BRAZIL_NPES-B/links/544610030cf2d62c304d94d9/NATIONAL-PROGRAM-FOR-THE-ELIMINATION-OF-SILICOSIS-BRAZIL-NPES-B.pdf
    PubMed
  • 3 ILO. . Guidelines for the use of the ILO International Classification of Radiograph of Pneumoconioses, Revised edition 2011. Occupational Safety and Health Series No 22 (Rev 2011). Geneva: International Labour Office; 2011
  • 4 Akima R, J-P NA, Ito K. et al. Perceptual and objective physical quality of chest images: a comparison between digital radiographic chest images processed for cancer screening and pneumoconiosis screening in Japan. Ind Health 2022 (e-pub ahead of print). doi: DOI: 10.2486/indhealth.2022-0046.
    CrossrefPubMedGoogle Scholar
  • 5 Hirano M, Mbelambela EP, Eitoku M. et al. Risk assessment of farmers handling pelleted seeds containing crystalline silica and attapulgite. J Occup Health 2021; 63 (01) e12304
    CrossrefPubMedGoogle Scholar
  • 6 Tamura A, Funakoshi M, J-P NA. et al. Potential asbestos exposure among patients with primary lung cancer in Japan. J Occup Health 2018; 60 (03) 236-245
    CrossrefPubMedGoogle Scholar
  • 7 ILO. . Guidelines for the use of the ILO International Classification of Radiographs of Pneumoconioses - Revised edition 2022. Geneva: International Labour Office; 2023
  • 8 Suzuki K, Otsuka Y, Nomura Y, Kumamaru KK, Kuwatsuru R, Aoki S. Development and validation of a modified three-dimensional U-Net deep-learning model for automated detection of lung nodules on chest CT images from the lung image database consortium and Japanese datasets. Acad Radiol 2022; 29 (Suppl 2): S11-S17
    CrossrefPubMedGoogle Scholar
  • 9 Soffer S, Morgenthau AS, Shimon O. et al. Artificial intelligence for interstitial lung disease analysis on chest computed tomography: a systematic review. Acad Radiol 2022; 29 (suppl 2): S226-S235
    CrossrefPubMedGoogle Scholar
  • 10 Office IL. . Silicosis: Records of the International Conference held at Johannesburg 13–27 August 1930. STUDIES AND REPORTS: Series F (Industrial Hygiene) No 13. London: P. S. KING & SONS Ltd.; 1930:690
    PubMed
  • 11 Ngatu NR, Suzuki S, Kusaka Y, Shida H, Akira M, Suganuma N. Effect of a two-hour training on physicians' skill in interpreting Pneumoconiotic chest radiographs. J Occup Health 2010; 52 (05) 294-301
    CrossrefPubMedGoogle Scholar
  • 12 Halldin CN, Blackley DJ, Petsonk EL, Laney AS. Pneumoconioses radiographs in a large population of U.S. coal workers: variability in A reader and B reader classifications by using the International Labour Office classification. Radiology 2017; 284 (03) 870-876
    CrossrefPubMedGoogle Scholar
  • 13 Morgan RH. Proficiency examination of physicians for classifying pneumoconiosis chest films. AJR Am J Roentgenol 1979; 132 (05) 803-808
    CrossrefPubMedGoogle Scholar
  • 14 Attfield MD, Wagner GR. A report on a workshop on the National Institute for Occupational Safety and Health B reader certification program. J Occup Med 1992; 34 (09) 875-878
    PubMedGoogle Scholar
  • 15 Wagner GR, Attfield MD, Kennedy RD, Parker JE. The NIOSH B reader certification program. An update report. J Occup Med 1992; 34 (09) 879-884
    PubMedGoogle Scholar
  • 16 Nogami S, J-P NA, Nogami M. et al. Radiographic diagnosis of Pneumoconioses by AIR Pneumo-trained physicians: comparison with low-dose thin-slice computed tomography. J Occup Health 2020; 62 (01) e12141
    CrossrefPubMedGoogle Scholar
  • 17 J-P NA, Susanto AD, Samoedro E. et al. Inter-observer agreement and accuracy in classifying radiographs for pneumoconiosis among Asian physicians taking AIR Pneumo certification examination. Ind Health 2022; 60 (05) 459-469
    PubMedGoogle Scholar
  • 18 Zhou H, Kusaka Y, Tamura T. et al. Proficiency in reading pneumoconiosis radiographs examined by the 60-film set with 4-factor structuring 8-index. Ind Health 2012; 50 (02) 142-146
    CrossrefPubMedGoogle Scholar
  • 19 Zhou H, Kusaka Y, Tamura T. et al. The 60-film set with 8-index for examining physicians' proficiency in reading pneumoconiosis chest X-rays. Ind Health 2012; 50 (02) 84-94
    CrossrefPubMedGoogle Scholar
  • 20 Tamura T, Kusaka Y, Suganuma N. et al. Assessment of physicians' proficiency in reading chest radiographs for pneumoconiosis, based on a 60-film examination set with two factors constituting eight indices. Ind Health 2018; 56 (05) 382-393
    CrossrefPubMedGoogle Scholar
  • 21 Suganuma N, Kusaka Y, Hering KG. et al; International CT Classification Study Group. Selection of reference films based on reliability assessment of a classification of high-resolution computed tomography for pneumoconioses. Int Arch Occup Environ Health 2006; 79 (06) 472-476
    CrossrefPubMedGoogle Scholar
  • 22 Suganuma N, Kusaka Y, Hering KG. et al. Reliability of the proposed international classification of high-resolution computed tomography for occupational and environmental respiratory diseases. J Occup Health 2009; 51 (03) 210-222
    CrossrefPubMedGoogle Scholar
  • 23 Şener MU, Şimşek C, Özkara Ş, Evran H, Bursali İ, Gökçek A. 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. Ind Health 2019; 57 (04) 495-502
    CrossrefPubMedGoogle Scholar
  • 24 Kraus T, Raithel HJ, Hering KG. Evaluation and classification of high-resolution computed tomographic findings in patients with pneumoconiosis. Int Arch Occup Environ Health 1996; 68 (04) 249-254
    CrossrefPubMedGoogle Scholar
  • 25 Ledley RS, Huang HK, Rotolo LS. A texture analysis method in classification of coal workers' pneumoconiosis. Comput Biol Med 1975; 5 (1–2): 53-67
    CrossrefPubMedGoogle Scholar
  • 26 Jagoe JR, Paton KA. Reading chest radiographs for pneumoconiosis by computer. Br J Ind Med 1975; 32 (04) 267-272
    PubMedGoogle Scholar
  • 27 Buchanan B, Feigenbaum E. DENDRAL and Meta-DENDRAL: roots of knowledge systems and expert system applications. Artif Intell 1993; 59: 233-240
    CrossrefPubMedGoogle Scholar
  • 28 Fagan LM, Shortliffe EH, Buchanan B. G, Computer-Based Medical Decision Making: From Mycin to VM. Automedica (NY) 1980; 3: 97-106
    PubMedGoogle Scholar
  • 29 Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986; 323: 533-536
    CrossrefPubMedGoogle Scholar
  • 30 Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks, Proceedings of the 25th International Conference on Neural Information Processing Systems. (NIPS'12) 2012; 1: 1097-1105
    PubMedGoogle Scholar
  • 31 Dhawan AP, Juvvadi S. Knowledge-based analysis and understanding of medical images. Comput Methods Programs Biomed 1990; 33 (04) 221-239
    CrossrefPubMedGoogle Scholar
  • 32 Faust O, Acharya UR, Tamura T. Formal design methods for reliable computer-aided diagnosis: a review. IEEE Rev Biomed Eng 2012; 5: 15-28
    CrossrefPubMedGoogle Scholar
  • 33 Lucas C, Mortezaie G. . Analysis of mammographic microcalcifications using gray-level images and neural networks. Paper presented at: IEE Seminar on Appropriate Medical Technology for Developing Countries (Ref No 2002/057), London, United Kingdom. 2002:11/1–11/4
    PubMed
  • 34 Simonyan K, Zisserman A. . Very deep convolutional networks for large-scale image recognition. Paper presented at: ICLR; 2015; Accessed March 10, 2023 at: https://www.robots.ox.ac.uk/~vgg/publications/2015/Simonyan15/simonyan15.pdf
    PubMed
  • 35 Ronneberger O, Fischer P, Brox T. . U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF, eds. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science. New York, NY: Springer International Publishing; 2015:234–241
  • 36 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015. Switzerland: Springer, Cham; 2015
    Google Scholar
  • 37 Okumura E, Kawashita I, Ishida T. Computerized analysis of pneumoconiosis in digital chest radiography: effect of artificial neural network trained with power spectra. J Digit Imaging 2011; 24 (06) 1126-1132
    CrossrefPubMedGoogle Scholar
  • 38 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. Radiological Phys Technol 2014; 7 (02) 217-227
    CrossrefPubMedGoogle Scholar
  • 39 Okumura E, Kawashita I, Ishida T. Computerized classification of pneumoconiosis on digital chest radiography artificial neural network with three stages. J Digit Imaging 2017; 30 (04) 413-426
    CrossrefPubMedGoogle Scholar
  • 40 Yu P, Xu H, Zhu Y, Yang C, Sun X, Zhao J. An automatic computer-aided detection scheme for pneumoconiosis on digital chest radiographs. J Digit Imaging 2011; 24 (03) 382-393
    CrossrefPubMedGoogle Scholar
  • 41 Zhu B, Luo W, Li B. et al. The development and evaluation of a computerized diagnosis scheme for pneumoconiosis on digital chest radiographs. Biomed Eng Online 2014; 13: 141
    CrossrefPubMedGoogle Scholar
  • 42 Zhu B, Chen H, Chen B, Xu Y, Zhang K. Support vector machine model for diagnosing pneumoconiosis based on wavelet texture features of digital chest radiographs. J Digit Imaging 2014; 27 (01) 90-97
    CrossrefPubMedGoogle Scholar
  • 43 Yu AC, Mohajer B, Eng J. External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 2022; 4 (03) e210064
    CrossrefPubMedGoogle Scholar