Diagnostic validation of a deep learning nodule detection algorithm in low-dose chest CT: determination of optimized dose thresholds in a virtual screening scenario.
Artificial intelligence
Computer-assisted diagnosis
Deep learning
Lung neoplasms
Radiographic phantoms
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
Jun 2022
Jun 2022
Historique:
received:
28
07
2021
accepted:
09
12
2021
revised:
06
12
2021
pubmed:
22
1
2022
medline:
25
5
2022
entrez:
21
1
2022
Statut:
ppublish
Résumé
This study was conducted to evaluate the effect of dose reduction on the performance of a deep learning (DL)-based computer-aided diagnosis (CAD) system regarding pulmonary nodule detection in a virtual screening scenario. Sixty-eight anthropomorphic chest phantoms were equipped with 329 nodules (150 ground glass, 179 solid) with four sizes (5 mm, 8 mm, 10 mm, 12 mm) and scanned with nine tube voltage/current combinations. The examinations were analyzed by a commercially available DL-based CAD system. The results were compared by a comparison of proportions. Logistic regression was performed to evaluate the impact of tube voltage, tube current, nodule size, nodule density, and nodule location. The combination with the lowest effective dose (E) and unimpaired detection rate was 80 kV/50 mAs (sensitivity: 97.9%, mean false-positive rate (FPR): 1.9, mean CTDIvol: 1.2 ± 0.4 mGy, mean E: 0.66 mSv). Logistic regression revealed that tube voltage and current had the greatest impact on the detection rate, while nodule size and density had no significant influence. The optimal tube voltage/current combination proposed in this study (80 kV/50 mAs) is comparable to the proposed combinations in similar studies, which mostly dealt with conventional CAD software. Modification of tube voltage and tube current has a significant impact on the performance of DL-based CAD software in pulmonary nodule detection regardless of their size and composition. • Modification of tube voltage and tube current has a significant impact on the performance of deep learning-based CAD software. • Nodule size and composition have no significant impact on the software's performance. • The optimal tube voltage/current combination for the examined software is 80 kV/50 mAs.
Identifiants
pubmed: 35059804
doi: 10.1007/s00330-021-08511-7
pii: 10.1007/s00330-021-08511-7
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4324-4332Commentaires et corrections
Type : ErratumIn
Informations de copyright
© 2022. The Author(s), under exclusive licence to European Society of Radiology.
Références
Siegel RL, Miller KD, Jemal A (2020) Cancer statistics, 2020. CA Cancer J Clin 70:7–30
doi: 10.3322/caac.21590
Aberle DR, Adams AM, Berg CD et al (2011) Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 365:395–409
doi: 10.1056/NEJMoa1102873
Becker N, Motsch E, Gross ML et al (2015) Randomized study on early detection of lung cancer with MSCT in Germany: results of the first 3 years of follow-up after randomization. J Thorac Oncol 10:890–896
doi: 10.1097/JTO.0000000000000530
de Koning HJ, van der Aalst CM, de Jong PA et al (2020) Reduced lung-cancer mortality with volume CT screening in a randomized trial. N Engl J Med 382:503–513
doi: 10.1056/NEJMoa1911793
Paci E, Puliti D, Lopes Pegna A et al (2017) Mortality, survival and incidence rates in the ITALUNG randomised lung cancer screening trial. Thorax 72:825–831
doi: 10.1136/thoraxjnl-2016-209825
Brenner DJ (2004) Radiation risks potentially associated with low-dose CT screening of adult smokers for lung cancer. Radiology 231:440–445
doi: 10.1148/radiol.2312030880
Huber A, Landau J, Ebner L et al (2016) Performance of ultralow-dose CT with iterative reconstruction in lung cancer screening: limiting radiation exposure to the equivalent of conventional chest X-ray imaging. Eur Radiol 26:3643–3652
doi: 10.1007/s00330-015-4192-3
Messerli M, Kluckert T, Knitel M et al (2016) Computer-aided detection (CAD) of solid pulmonary nodules in chest x-ray equivalent ultralow dose chest CT - first in-vivo results at dose levels of 0.13mSv. Eur J Radiol 85:2217–2224
doi: 10.1016/j.ejrad.2016.10.006
Neroladaki A, Botsikas D, Boudabbous S, Becker CD, Montet X (2013) Computed tomography of the chest with model-based iterative reconstruction using a radiation exposure similar to chest X-ray examination: preliminary observations. Eur Radiol 23:360–366
doi: 10.1007/s00330-012-2627-7
Kroft LJM, van der Velden L, Girón IH, Roelofs JJH, de Roos A, Geleijns J (2019) Added value of ultra–low-dose computed tomography, dose equivalent to chest X-ray radiography, for diagnosing chest pathology. J Thorac Imaging 34:179–186
doi: 10.1097/RTI.0000000000000404
Christe A, Charimo-Torrente J, Roychoudhury K, Vock P, Roos JE (2013) Accuracy of low-dose computed tomography (CT) for detecting and characterizing the most common CT-patterns of pulmonary disease. Eur J Radiol 82:e142-150
doi: 10.1016/j.ejrad.2012.09.025
Kang S, Kim TH, Shin JM et al (2020) Optimization of a chest computed tomography protocol for detecting pure ground glass opacity nodules: a feasibility study with a computer-assisted detection system and a lung cancer screening phantom. PLoS One 15:e0232688
doi: 10.1371/journal.pone.0232688
Solomon J, Mileto A, Nelson RC, Roy Choudhury K, Samei E (2016) Quantitative features of liver lesions, lung nodules, and renal stones at multi-detector row CT examinations: dependency on radiation dose and reconstruction algorithm. Radiology 279:185–194
doi: 10.1148/radiol.2015150892
Scholten ET, Horeweg N, de Koning HJ et al (2015) Computed tomographic characteristics of interval and post screen carcinomas in lung cancer screening. Eur Radiol 25:81–88
doi: 10.1007/s00330-014-3394-4
Torres EL, Fiorina E, Pennazio F et al (2015) Large scale validation of the M5L lung CAD on heterogeneous CT datasets. Med Phys 42:1477–1489
doi: 10.1118/1.4907970
Christe A, Leidolt L, Huber A et al (2013) Lung cancer screening with CT: evaluation of radiologists and different computer assisted detection software (CAD) as first and second readers for lung nodule detection at different dose levels. Eur J Radiol 82:e873-878
doi: 10.1016/j.ejrad.2013.08.026
Li L, Liu Z, Huang H, Lin M, Luo D (2019) Evaluating the performance of a deep learning-based computer-aided diagnosis (DL-CAD) system for detecting and characterizing lung nodules: comparison with the performance of double reading by radiologists. Thorac Cancer 10:183–192
doi: 10.1111/1759-7714.12931
Liang CH, Liu YC, Wu MT, Garcia-Castro F, Alberich-Bayarri A, Wu FZ (2020) Identifying pulmonary nodules or masses on chest radiography using deep learning: external validation and strategies to improve clinical practice. Clin Radiol 75:38–45
doi: 10.1016/j.crad.2019.08.005
Setio AA, Ciompi F, Litjens G et al (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35:1160–1169
doi: 10.1109/TMI.2016.2536809
Tandon YK, Bartholmai BJ, Koo CW (2020) Putting artificial intelligence (AI) on the spot: machine learning evaluation of pulmonary nodules. J Thorac Dis 12:6954–6965
doi: 10.21037/jtd-2019-cptn-03
Zhao Y, de Bock GH, Vliegenthart R et al (2012) Performance of computer-aided detection of pulmonary nodules in low-dose CT: comparison with double reading by nodule volume. Eur Radiol 22:2076–2084
doi: 10.1007/s00330-012-2437-y
Wielpütz MO, Wroblewski J, Lederlin M et al (2015) Computer-aided detection of artificial pulmonary nodules using an ex vivo lung phantom: influence of exposure parameters and iterative reconstruction. Eur J Radiol 84:1005–1011
doi: 10.1016/j.ejrad.2015.01.025
Blazis SP, Dickerscheid DBM, Linsen PVM, Martins Jarnalo CO (2021) Effect of CT reconstruction settings on the performance of a deep learning based lung nodule CAD system. Eur J Radiol 136:109526
doi: 10.1016/j.ejrad.2021.109526
Fu B, Wang G, Wu M et al (2020) Influence of CT effective dose and convolution kernel on the detection of pulmonary nodules in different artificial intelligence software systems: a phantom study. Eur J Radiol 126:108928
doi: 10.1016/j.ejrad.2020.108928
The, (2007) Recommendations of the International Commission on Radiological Protection. ICRP publication 103. Ann ICRP 37:1–332
Shrimpton PC, Hillier MC, Lewis MA, Dunn M (2006) National survey of doses from CT in the UK: 2003. Br J Radiol 79:968–980
doi: 10.1259/bjr/93277434
Ebner L, Roos JE, Christensen JD et al (2016) Maximum-intensity-projection and computer-aided-detection algorithms as stand-alone reader devices in lung cancer screening using different dose levels and reconstruction kernels. AJR Am J Roentgenol 207:282–288
doi: 10.2214/AJR.15.15588
Agresti A (2007) An introduction to categorical data analysis, 2nd edn. Wiley-Interscience, Hoboken, NJ
Ebner L, Bütikofer Y, Ott D et al (2015) Lung nodule detection by microdose CT versus chest radiography (standard and dual-energy subtracted). AJR Am J Roentgenol 204:727–735
doi: 10.2214/AJR.14.12921
Christe A, Szucs-Farkas Z, Huber A et al (2013) Optimal dose levels in screening chest CT for unimpaired detection and volumetry of lung nodules, with and without computer assisted detection at minimal patient radiation. PLoS One 8:e82919
doi: 10.1371/journal.pone.0082919
Hua KL, Hsu CH, Hidayati SC, Cheng WH, Chen YJ (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets Ther 8:2015–2022
Christe A, Torrente JC, Lin M et al (2011) CT screening and follow-up of lung nodules: effects of tube current-time setting and nodule size and density on detectability and of tube current-time setting on apparent size. AJR Am J Roentgenol 197:623–630
doi: 10.2214/AJR.10.5288