Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

  • Eui Jin Hwang (Department of Radiology, Seoul National University College of Medicine) ;
  • Chang Min Park (Department of Radiology, Seoul National University College of Medicine)
  • Received : 2019.11.03
  • Accepted : 2020.01.31
  • Published : 2020.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Chest X-ray radiography and computed tomography, the two mainstay modalities in thoracic radiology, are under active investigation with deep learning technology, which has shown promising performance in various tasks, including detection, classification, segmentation, and image synthesis, outperforming conventional methods and suggesting its potential for clinical implementation. However, the implementation of deep learning in daily clinical practice is in its infancy and facing several challenges, such as its limited ability to explain the output results, uncertain benefits regarding patient outcomes, and incomplete integration in daily workflow. In this review article, we will introduce the potential clinical applications of deep learning technology in thoracic radiology and discuss several challenges for its implementation in daily clinical practice.

Keywords

Acknowledgement

The present study was supported by the Seoul National University Hospital research fund (grant number: 03-2019-0190).

References

  1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436-444 https://doi.org/10.1038/nature14539
  2. LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998;86:2278-2324
  3. Hinton G, Deng L, Yu D, Dahl GE, Mohamed A, Jaitly N, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 2012;29:82-97 https://doi.org/10.1109/MSP.2012.2205597
  4. Hirschberg J, Manning CD. Advances in natural language processing. Science 2015;349:261-266 https://doi.org/10.1126/science.aaa8685
  5. Pendleton S, Andersen H, Du X, Shen X, Meghjani M, Eng Y, et al. Perception, planning, control, and coordination for autonomous vehicles. Machines 2017;5:6
  6. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019;25:44-56 https://doi.org/10.1038/s41591-018-0300-7
  7. Hinton G. Deep learning-a technology with the potential to transform health care. JAMA 2018;320:1101-1102 https://doi.org/10.1001/jama.2018.11100
  8. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. Imagenet large scale visual recognition challenge. Int J Computer Vision 2015;115:211-252 https://doi.org/10.1007/s11263-015-0816-y
  9. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. 26th conference on neural informatoin processing systems;2012 December 03-06;Lake Tahoe, USA
  10. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. The IEEE conference on computer vision and pattern recognition;2016 June 27-30;Las Vegas, USA
  11. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et a. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542:115-118 https://doi.org/10.1038/nature21056
  12. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016;316:2402-2410 https://doi.org/10.1001/jama.2016.17216
  13. Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 2017;318:2211-2223 https://doi.org/10.1001/jama.2017.18152
  14. Ehteshami Bejnordi B, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017;318:2199-2210 https://doi.org/10.1001/jama.2017.14585
  15. Rubin DL. Artificial intelligence in imaging: the radiologist's role. J Am Coll Radiol 2019;16:1309-1317 https://doi.org/10.1016/j.jacr.2019.05.036
  16. Sluimer IC, van Waes PF, Viergever MA, van Ginneken B. Computer-aided diagnosis in high resolution CT of the lungs. Med Phys 2003;30:3081-3090 https://doi.org/10.1118/1.1624771
  17. van Ginneken B. Fifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning. Radiol Phys Technol 2017;10:23-32 https://doi.org/10.1007/s12194-017-0394-5
  18. van Ginneken B, ter Haar Romeny BM, Viergever MA. Computer-aided diagnosis in chest radiography: a survey. IEEE Trans Med Imaging 2001;20:1228-1241 https://doi.org/10.1109/42.974918
  19. Goo JM. A computer-aided diagnosis for evaluating lung nodules on chest CT: the current status and perspective. Korean J Radiol 2011;12:145-155 https://doi.org/10.3348/kjr.2011.12.2.145
  20. Kiraly AP, Odry BL, Godoy MC, Geiger B, Novak CL, Naidich DP. Computer-aided diagnosis of the airways: beyond nodule detection. J Thorac Imaging 2008;23:105-113 https://doi.org/10.1097/RTI.0b013e318174e8f5
  21. van Ginneken B, Hogeweg L, Prokop M. Computer-aided diagnosis in chest radiography: beyond nodules. Eur J Radiol 2009;72:226-230 https://doi.org/10.1016/j.ejrad.2009.05.061
  22. Sluimer I, Schilham A, Prokop M, van Ginneken B. Computer analysis of computed tomography scans of the lung: a survey. IEEE Trans Med Imaging 2006;25:385-405 https://doi.org/10.1109/TMI.2005.862753
  23. van Rikxoort EM, van Ginneken B. Automated segmentation of pulmonary structures in thoracic computed tomography scans: a review. Phys Med Biol 2013;58:R187-R220 https://doi.org/10.1088/0031-9155/58/17/R187
  24. Pande T, Cohen C, Pai M, Ahmad Khan F. Computer-aided detection of pulmonary tuberculosis on digital chest radiographs: a systematic review. Int J Tuberc Lung Dis 2016;20:1226-1230 https://doi.org/10.5588/ijtld.15.0926
  25. Schalekamp S, van Ginneken B, Karssemeijer N, Schaefer-Prokop CM. Chest radiography: new technological developments and their applications. Semin Respir Crit Care Med 2014;35:3-16 https://doi.org/10.1055/s-0033-1363447
  26. Lee SM, Seo JB, Yun J, Cho YH, Vogel-Claussen J, Schiebler ML, et al. Deep learning applications in chest radiography and computed tomography: current state of the art. J Thorac Imaging 2019;34:75-85 https://doi.org/10.1097/RTI.0000000000000387
  27. Hwang EJ, Park S, Jin KN, Kim JI, Choi SY, Lee JH, et al. Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs. JAMA Netw Open 2019;2:e191095
  28. Hwang EJ, Park S, Jin KN, Kim JI, Choi SY, Lee JH, et al. Development and validation of a deep learning-based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs. Clin Infect Dis 2019;69:739-747 https://doi.org/10.1093/cid/ciy967
  29. Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017;284:574-582 https://doi.org/10.1148/radiol.2017162326
  30. Nam JG, Park S, Hwang EJ, Lee JH, Jin KN, Lim KY, et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 2019;290:218-228 https://doi.org/10.1148/radiol.2018180237
  31. Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 2018;15:e1002686
  32. Taylor AG, Mielke C, Mongan J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: a retrospective study. PLoS Med 2018;15:e1002697
  33. Austin JH, Romney BM, Goldsmith LS. Missed bronchogenic carcinoma: radiographic findings in 27 patients with a potentially resectable lesion evident in retrospect. Radiology 1992;182:115-122 https://doi.org/10.1148/radiology.182.1.1727272
  34. Gavelli G, Giampalma E. Sensitivity and specificity of chest X-ray screening for lung cancer: review article. Cancer 2000;89:2453-2456 https://doi.org/10.1002/1097-0142(20001201)89:11+<2453::AID-CNCR21>3.0.CO;2-M
  35. Lee KH, Goo JM, Park CM, Lee HJ, Jin KN. Computer-aided detection of malignant lung nodules on chest radiographs: effect on observers' performance. Korean J Radiol 2012;13:564-571 https://doi.org/10.3348/kjr.2012.13.5.564
  36. De Boo DW, Uffmann M, Weber M, Bipat S, Boorsma EF, Scheerder MJ, et al. Computer-aided detection of small pulmonary nodules in chest radiographs: an observer study. Acad Radiol 2011;18:1507-1514 https://doi.org/10.1016/j.acra.2011.08.008
  37. de Hoop B, De Boo DW, Gietema HA, van Hoorn F, Mearadji B, Schijf L, et al. Computer-aided detection of lung cancer on chest radiographs: effect on observer performance. Radiology 2010;257:532-540 https://doi.org/10.1148/radiol.10092437
  38. Kligerman S, Cai L, White CS. The effect of computer-aided detection on radiologist performance in the detection of lung cancers previously missed on a chest radiograph. J Thorac Imaging 2013;28:244-252 https://doi.org/10.1097/RTI.0b013e31826c29ec
  39. Lodwick GS, Keats TE, Dorst JP. The coding of Roentgen images for computer analysis as applied to lung cancer. Radiology 1963;81:185-200 https://doi.org/10.1148/81.2.185
  40. Kakeda S, Moriya J, Sato H, Aoki T, Watanabe H, Nakata H, et al. Improved detection of lung nodules on chest radiographs using a commercial computer-aided diagnosis system. AJR Am J Roentgenol 2004;182:505-510 https://doi.org/10.2214/ajr.182.2.1820505
  41. Shiraishi J, Abe H, Li F, Engelmann R, MacMahon H, Doi K. Computer-aided diagnosis for the detection and classification of lung cancers on chest radiographs ROC analysis of radiologists' performance. Acad Radiol 2006;13:995-1003 https://doi.org/10.1016/j.acra.2006.04.007
  42. van Beek EJ, Mullan B, Thompson B. Evaluation of a real-time interactive pulmonary nodule analysis system on chest digital radiographic images: a prospective study. Acad Radiol 2008;15:571-575 https://doi.org/10.1016/j.acra.2008.01.018
  43. Cha MJ, Chung MJ, Lee JH, Lee KS. Performance of deep learning model in detecting operable lung cancer with chest radiographs. J Thorac Imaging 2019;34:86-91 https://doi.org/10.1097/RTI.0000000000000388
  44. Heo SJ, Kim Y, Yun S, Lim SS, Kim J, Nam CM, et al. Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers' health examination data. Int J Environ Res Public Health 2019;16:250
  45. Harris M, Qi A, Jeagal L, Torabi N, Menzies D, Korobitsyn A, et al. A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest X-rays for pulmonary tuberculosis. PLoS One 2019;14:e0221339
  46. Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 2018;15:e1002683
  47. Park S, Lee SM, Kim N, Choe J, Cho Y, Do KH, et al. Application of deep learning-based computer-aided detection system: detecting pneumothorax on chest radiograph after biopsy. Eur Radiol 2019;29:5341-5348 https://doi.org/10.1007/s00330-019-06130-x
  48. Lee H, Mansouri M, Tajmir S, Lev MH, Do S. A deep-learning system for fully-automated Peripherally Inserted Central Catheter (PICC) tip detection. J Digit Imaging 2018;31:393-402 https://doi.org/10.1007/s10278-017-0025-z
  49. Lakhani P. Deep convolutional neural networks for endotracheal tube position and X-ray image classification: challenges and opportunities. J Digit Imaging 2017;30:460-468 https://doi.org/10.1007/s10278-017-9980-7
  50. Singh V, Danda V, Gorniak R, Flanders A, Lakhani P. Assessment of critical feeding tube malpositions on radiographs using deep learning. J Digit Imaging 2019;32:651-655 https://doi.org/10.1007/s10278-019-00229-9
  51. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. The IEEE conference on computer vision and pattern recognition;2017 July 21-26;Honolulu, USA
  52. Yao L, Poblenz E, Dagunts D, Covington B, Bernard D, Lyman K. Learning to diagnose from scratch by exploiting dependencies among labels [updated Feb 2018]. Cornell University, 2017. Available at: https://arxiv.org/abs/1710.10501. Accessed January 8, 2020
  53. Baltruschat IM, Nickisch H, Grass M, Knopp T, Saalbach A. Comparison of deep learning approaches for multi-label chest X-ray classification. Sci Rep 2019;9:6381
  54. Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. The thirty-third AAAI conference on artificial intelligence (AAAI-19);2019 January 27-February 1;Honolulu, USA
  55. Johnson AEW, Pollard TJ, Greenbaum NR, Lungren MP, Deng C, Peng Y, et al. MIMIC-CXR-JPG: a large publicly available database of labeled chest radiographs [updated Nov 2019]. Cornell University, 2019. Available at: https://arxiv.org/abs/1901.07042. Accessed January 8, 2020
  56. Bustos A, Pertusa A, Salinas JM, de la Iglesia-Vaya M. PadChest: a large chest X-ray image dataset with multi-label annotated reports [updated Feb 2019]. Cornell University, 2019. Available at: https://arxiv.org/abs/1901.07441. Accessed January 8, 2020
  57. Hwang EJ, Nam GJ, Lim WH, Park SJ, Jeong YS, Kang JH, et al. Deep learning for chest radiograph diagnosis in the emergency department. Radiology 2019;293:573-580 https://doi.org/10.1148/radiol.2019191225
  58. World Health Organization. Systematic screening for active tuberculosis: principles and recommendations. Geneva: WHO Document Production Services, 2013
  59. den Boon S, White NW, van Lill SW, Borgdorff MW, Verver S, Lombard CJ, et al. An evaluation of symptom and chest radiographic screening in tuberculosis prevalence surveys. Int J Tuberc Lung Dis 2006;10:876-882
  60. van't Hoog AH, Meme HK, Laserson KF, Agaya JA, Muchiri BG, Githui WA, et al. Screening strategies for tuberculosis prevalence surveys: the value of chest radiography and symptoms. PLoS One 2012;7:e38691
  61. World Health Organization. Chest radiography in tuberculosis detection: summary of current WHO recommendations and guidance on programmatic approaches. Geneva: World Health Organization, 2016
  62. Santosh KC, Antani S. Automated chest X-ray screening: can lung region symmetry help detect pulmonary abnormalities? IEEE Trans Med Imaging 2018;37:1168-1177 https://doi.org/10.1109/TMI.2017.2775636
  63. Black WC, Gareen IF, Soneji SS, Sicks JD, Keeler EB, Aberle DR, et al. Cost-effectiveness of CT screening in the National Lung Screening Trial. N Engl J Med 2014;371:1793-1802 https://doi.org/10.1056/NEJMoa1312547
  64. National Lung Screening Trial Research Team, Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, et al. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011;365:395-409 https://doi.org/10.1056/NEJMoa1102873
  65. Tanoue LT, Tanner NT, Gould MK, Silvestri GA. Lung cancer screening. Am J Respir Crit Care Med 2015;191:19-33 https://doi.org/10.1164/rccm.201410-1777CI
  66. Moyer VA; U.S. Preventive Services Task Force. Screening for lung cancer: U.S. Preventive Services Task Force recommendation statement. Ann Intern Med 2014;160:330-338
  67. Fintelmann FJ, Bernheim A, Digumarthy SR, Lennes IT, Kalra MK, Gilman MD, et al. The 10 pillars of lung cancer screening: rationale and logistics of a lung cancer screening program. Radiographics 2015;35:1893-1908 https://doi.org/10.1148/rg.2015150079
  68. Smieliauskas F, MacMahon H, Salgia R, Shih YC. Geographic variation in radiologist capacity and widespread implementation of lung cancer CT screening. J Med Screen 2014;21:207-215 https://doi.org/10.1177/0969141314548055
  69. Setio AAA, Traverso A, de Bel T, Berens MSN, Bogaard CVD, Cerello P, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. Med Image Anal 2017;42:1-13 https://doi.org/10.1016/j.media.2017.06.015
  70. LUng nodule analysis 2016. LUNA16 Web site. https://luna16.grand-challenge.org/. Published 2016. Accessed October 10, 2019
  71. Ciompi F, Chung K, van Riel SJ, Setio AAA, Gerke PK, Jacobs C, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning. Sci Rep 2017;7:46479
  72. Shen W, Zhou M, Yang F, Yu D, Dong D, Yang C, et al. Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification. Pattern Recognit 2017;61:663-673 https://doi.org/10.1016/j.patcog.2016.05.029
  73. Causey JL, Zhang J, Ma S, Jiang B, Qualls JA, Politte DG, et al. Highly accurate model for prediction of lung nodule malignancy with CT scans. Sci Rep 2018;8:9286
  74. Nishio M, Sugiyama O, Yakami M, Ueno S, Kubo T, Kuroda T, et al. Computer-aided diagnosis of lung nodule classification between benign nodule, primary lung cancer, and metastatic lung cancer at different image size using deep convolutional neural network with transfer learning. PLoS One 2018;13:e0200721
  75. Data science bowl 2017. Kaggle Web site. https://www.kaggle.com/c/data-science-bowl-2017. Published May, 2017. Accessed October 10, 2019
  76. Hosny A, Parmar C, Coroller TP, Grossmann P, Zeleznik R, Kumar A, et al. Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med 2018;15:e1002711
  77. Ardila D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 2019;25:954-961 https://doi.org/10.1038/s41591-019-0447-x
  78. Anthimopoulos M, Christodoulidis S, Ebner L, Christe A, Mougiakakou S. Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans Med Imaging 2016;35:1207-1216 https://doi.org/10.1109/TMI.2016.2535865
  79. Kim GB, Jung KH, Lee Y, Kim HJ, Kim N, Jun S, et al. Comparison of shallow and deep learning methods on classifying the regional pattern of diffuse lung disease. J Digit Imaging 2018;31:415-424 https://doi.org/10.1007/s10278-017-0028-9
  80. Gao M, Bagci U, Lu L, Wu A, Buty M, Shin HC, et al. Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks. Comput Methods Biomech Biomed Eng Imaging Vis 2018;6:1-6 https://doi.org/10.1080/21681163.2015.1124249
  81. Walsh SLF, Calandriello L, Silva M, Sverzellati N. Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. Lancet Respir Med 2018;6:837-845 https://doi.org/10.1016/S2213-2600(18)30286-8
  82. Raghu G, Collard HR, Egan JJ, Martinez FJ, Behr J, Brown KK, et al. An official ATS/ERS/JRS/ALAT statement: idiopathic pulmonary fibrosis: evidence-based guidelines for diagnosis and management. Am J Respir Crit Care Med 2011;183:788-824 https://doi.org/10.1164/rccm.2009-040GL
  83. Lynch DA, Sverzellati N, Travis WD, Brown KK, Colby TV, Galvin JR, et al. Diagnostic criteria for idiopathic pulmonary fibrosis: a Fleischner Society white paper. Lancet Respir Med 2018;6:138-153 https://doi.org/10.1016/S2213-2600(17)30433-2
  84. Christe A, Peters AA, Drakopoulos D, Heverhagen JT, Geiser T, Stathopoulou T, et al. Computer-aided diagnosis of pulmonary fibrosis using deep learning and CT images. Invest Radiol 2019;54:627-632 https://doi.org/10.1097/RLI.0000000000000574
  85. Gonzalez G, Ash SY, Vegas-Sanchez-Ferrero G, Onieva Onieva J, Rahaghi FN, Ross JC, et al. Disease staging and prognosis in smokers using deep learning in chest computed tomography. Am J Respir Crit Care Med 2018;197:193-203 https://doi.org/10.1164/rccm.201705-0860OC
  86. Lu MT, Ivanov A, Mayrhofer T, Hosny A, Aerts HJWL, Hoffmann U. Deep learning to assess long-term mortality from chest radiographs. JAMA Netw Open 2019;2:e197416
  87. Wang S, Shi J, Ye Z, Dong D, Yu D, Zhou M, et al. Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning. Eur Respir J 2019;53:1800986
  88. Kim SS, Jin GY, Li YZ, Lee JE, Shin HS. CT quantification of lungs and airways in normal Korean subjects. Korean J Radiol 2017;18:739-748 https://doi.org/10.3348/kjr.2017.18.4.739
  89. Lynch DA, Al-Qaisi MA. Quantitative computed tomography in chronic obstructive pulmonary disease. J Thorac Imaging 2013;28:284-290 https://doi.org/10.1097/RTI.0b013e318298733c
  90. Nambu A, Zach J, Schroeder J, Jin G, Kim SS, Kim YI, et al. Quantitative computed tomography measurements to evaluate airway disease in chronic obstructive pulmonary disease: relationship to physiological measurements, clinical index and visual assessment of airway disease. Eur J Radiol 2016;85:2144-2151 https://doi.org/10.1016/j.ejrad.2016.09.010
  91. Bartholmai BJ, Raghunath S, Karwoski RA, Moua T, Rajagopalan S, Maldonado F, et al. Quantitative computed tomography imaging of interstitial lung diseases. J Thorac Imaging 2013;28:298-307 https://doi.org/10.1097/RTI.0b013e3182a21969
  92. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5:4006
  93. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. The IEEE conference on computer vision and pattern recognition (CVPR);2015 June 7-12;Boston, USA
  94. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, eds. Medical image computing and computer-assisted intervention-MICCAI 2015, 3rd ed. Basel: Springer Nature, 2015:234-241
  95. Dong X, Lei Y, Wang T, Thomas M, Tang L, Curran WJ, et al. Automatic multiorgan segmentation in thorax CT images using U-net-GAN. Med Phys 2019;46:2157-2168 https://doi.org/10.1002/mp.13458
  96. Park B, Park H, Lee SM, Seo JB, Kim N. Lung segmentation on HRCT and volumetric CT for diffuse interstitial lung disease using deep convolutional neural networks. J Digit Imaging 2019;32:1019-1026 https://doi.org/10.1007/s10278-019-00254-8
  97. Park J, Yun J, Kim N, Park B, Cho Y, Park HJ, et al. Fully automated lung lobe segmentation in volumetric chest CT with 3D U-net: validation with intra- and extra-datasets. J Digit Imaging 2020;33:221-230 https://doi.org/10.1007/s10278-019-00223-1
  98. Yun J, Park J, Yu D, Yi J, Lee M, Park HJ, et al. Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net. Med Image Anal 2019;51:13-20 https://doi.org/10.1016/j.media.2018.10.006
  99. Aresta G, Jacobs C, Araujo T, Cunha A, Ramos I, van Ginneken B, et al. iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network. Sci Rep 2019;9:11591
  100. Wang S, Zhou M, Liu Z, Liu Z, Gu D, Zang Y, et al. Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal 2017;40:172-183 https://doi.org/10.1016/j.media.2017.06.014
  101. Kim H, Park CM, Lee M, Park SJ, Song YS, Lee JH, et al. Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors: analysis of intra- and inter-reader variability and inter-reconstruction algorithm variability. PLoS One 2016;11:e0164924
  102. Kim H, Goo JM, Ohno Y, Kauczor HU, Hoffman EA, Gee JC, et al. Effect of reconstruction parameters on the quantitative analysis of chest computed tomography. J Thorac Imaging 2019;34:92-102 https://doi.org/10.1097/RTI.0000000000000389
  103. Chen B, Barnhart H, Richard S, Colsher J, Amurao M, Samei E. Quantitative CT: technique dependence of volume estimation on pulmonary nodules. Phys Med Biol 2012;57:1335-1348 https://doi.org/10.1088/0031-9155/57/5/1335
  104. Berenguer R, Pastor-Juan MDR, Canales-Vazquez J, Castro-Garcia M, Villas MV, Mansilla Legorburo F, et al. Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 2018;288:407-415 https://doi.org/10.1148/radiol.2018172361
  105. Meyer M, Ronald J, Vernuccio F, Nelson RC, Ramirez-Giraldo JC, Solomon J, et al. Reproducibility of CT radiomic features within the same patient: influence of radiation dose and CT reconstruction settings. Radiology 2019;293:583-591 https://doi.org/10.1148/radiol.2019190928
  106. Yip SS, Aerts HJ. Applications and limitations of radiomics. Phys Med Biol 2016;61:R150-R166 https://doi.org/10.1088/0031-9155/61/13/R150
  107. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Advances in neural information processing systems 27 (NIPS 2014);2014 December 8-13;Montreal, Canada
  108. Lee SM, Lee JG, Lee G, Choe J, Do KH, Kim N, et al. CT image conversion among different reconstruction kernels without a sinogram by using a convolutional neural network. Korean J Radiol 2019;20:295-303 https://doi.org/10.3348/kjr.2018.0249
  109. Choe J, Lee SM, Do KH, Lee G, Lee JG, Lee SM, et al. Deep learning-based image conversion of CT reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses. Radiology 2019;292:365-373 https://doi.org/10.1148/radiol.2019181960
  110. Park S, Lee SM, Do KH, Lee JG, Bae W, Park H, et al. Deep learning algorithm for reducing CT slice thickness: effect on reproducibility of radiomic features in lung cancer. Korean J Radiol 2019;20:1431-1440 https://doi.org/10.3348/kjr.2019.0212
  111. Singh S, Khawaja RD, Pourjabbar S, Padole A, Lira D, Kalra MK. Iterative image reconstruction and its role in cardiothoracic computed tomography. J Thorac Imaging 2013;28:355-367 https://doi.org/10.1097/RTI.0000000000000054
  112. Padole A, Ali Khawaja RD, Kalra MK, Singh S. CT radiation dose and iterative reconstruction techniques. AJR Am J Roentgenol 2015;204:W384-W392 https://doi.org/10.2214/AJR.14.13241
  113. Geyer LL, Schoepf UJ, Meinel FG, Nance JW Jr, Bastarrika G, Leipsic JA, et al. State of the art: iterative CT reconstruction techniques. Radiology 2015;276:339-357 https://doi.org/10.1148/radiol.2015132766
  114. GE gets FDA nod for deep-learning CT reconstruction. AuntMinnie. com Web site. https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=125242/. Published April 22, 2019. Accessed October 22, 2019
  115. Canon gets FDA nod for AI-powered CT reconstruction. AuntMinnie. com Web site. https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=125783/. Published June 18, 2019. Accessed October 22, 2019
  116. Ahn SY, Chae KJ, Goo JM. The potential role of grid-like software in bedside chest radiography in improving image quality and dose reduction: an observer preference study. Korean J Radiol 2018;19:526-533 https://doi.org/10.3348/kjr.2018.19.3.526
  117. Bossuyt PM, Irwig L, Craig J, Glasziou P. Comparative accuracy: assessing new tests against existing diagnostic pathways. BMJ 2006;332:1089-1092 https://doi.org/10.1136/bmj.332.7549.1089
  118. Tang A, Tam R, Cadrin-Chenevert A, Guest W, Chong J, Barfett J, et al. Canadian association of radiologists white paper on artificial intelligence in radiology. Can Assoc Radiol J 2018;69:120-135 https://doi.org/10.1016/j.carj.2018.02.002
  119. Zaharchuk G, Gong E, Wintermark M, Rubin D, Langlotz CP. Deep learning in neuroradiology. AJNR Am J Neuroradiol 2018;39:1776-1784 https://doi.org/10.3174/ajnr.A5543
  120. Titano JJ, Badgeley M, Schefflein J, Pain M, Su A, Cai M, et al. Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat Med 2018;24:1337-1341 https://doi.org/10.1038/s41591-018-0147-y
  121. Prevedello LM, Erdal BS, Ryu JL, Little KJ, Demirer M, Qian S, et al. Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology 2017;285:923-931 https://doi.org/10.1148/radiol.2017162664
  122. Annarumma M, Withey SJ, Bakewell RJ, Pesce E, Goh V, Montana G. Automated triaging of adult chest radiographs with deep artificial neural networks. Radiology 2019;291:196-202 https://doi.org/10.1148/radiol.2018180921
  123. Obuchowski NA, Bullen JA. Statistical considerations for testing an AI algorithm used for prescreening lung CT images. Contemp Clin Trials Commun 2019;16:100434
  124. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol 2017;18:570-584 https://doi.org/10.3348/kjr.2017.18.4.570
  125. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer 2018;18:500-510 https://doi.org/10.1038/s41568-018-0016-5
  126. Choo J, Liu S. Visual analytics for explainable deep learning. IEEE Comput Graph Appl 2018;38:84-92 https://doi.org/10.1109/MCG.2018.042731661
  127. Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. Cornell University, 2015. Available at: https://arxiv.org/abs/1512.04150. Accessed January 8, 2020
  128. Kim DW, Jang HY, Kim KW, Shin Y, Park SH. Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers. Korean J Radiol 2019;20:405-410 https://doi.org/10.3348/kjr.2019.0025
  129. Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 2018;286:800-809 https://doi.org/10.1148/radiol.2017171920
  130. Doi K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007;31:198-211 https://doi.org/10.1016/j.compmedimag.2007.02.002
  131. Le AH, Liu B, Huang HK. Integration of computer-aided diagnosis/detection (CAD) results in a PACS environment using CAD-PACS toolkit and DICOM SR. Int J Comput Assist Radiol Surg 2009;4:317-329 https://doi.org/10.1007/s11548-009-0297-y
  132. Kim M, Park J, Kim KH, Hwang EJ, Park CM, Park S. Development of a deep learning-based algorithm for independent detection of chest abnormalities on chest radiographs. 105th scientific assembly and annual meeting, Radiological Society of North America;2019 December 01-06;Chicago, USA