Objective:
To investigate the natural history of persistent pulmonary pure ground-glass nodules (pGGNs) with deep learning-assisted nodule segmentation.
Methods:
Between January 2007 and October 2018, 110 pGGNs from 110 patients with 573 follow-up CT scans were included in this retrospective study. pGGN automatic segmentation was performed on initial and all follow-up CT scans using the Dr. Wise system based on convolution neural networks. Subsequently, pGGN diameter, density, volume, mass, volume doubling time (VDT), and mass doubling time (MDT) were calculated automatically. Enrolled pGGNs were categorized into growth, 52 (47.3%), and non-growth, 58 (52.7%), groups according to volume growth. Kaplan-Meier analyses with the log-rank test and Cox proportional hazards regression analysis were conducted to analyze the cumulative percentages of pGGN growth and identify risk factors for growth.
Results:
The mean follow-up period of the enrolled pGGNs was 48.7 ± 23.8 months. The median VDT of the 52 pGGNs having grown was 1448 (range, 339-8640) days, and their median MDT was 1332 (range, 290-38,912) days. The 12-month, 24.7-month, and 60.8-month cumulative percentages of pGGN growth were 10%, 25.5%, and 51.1%, respectively, and they significantly differed among the initial diameter, volume, and mass subgroups (all p < 0.001). The growth pattern of pGGNs may conform to the exponential model. Lobulated sign (p = 0.044), initial mean diameter (p < 0.001), volume (p = 0.003), and mass (p = 0.023) predicted pGGN growth.
Conclusions:
Persistent pGGNs showed an indolent course. Deep learning can assist in accurately elucidating the natural history of pGGNs. pGGNs with lobulated sign and larger initial diameter, volume, and mass are more likely to grow.
Key Points:
• The pure ground-glass nodule (pGGN) segmentation accuracy of the Dr. Wise system based on convolution neural networks (CNNs) was 96.5% (573/594). • The median volume doubling time (VDT) of 52 pure ground-glass nodules (pGGNs) having grown was 1448 days (range, 339-8640 days), and their median mass doubling time (MDT) was 1332 days (range, 290-38,912 days). The mean time to growth in volume was 854 ± 675 days (range, 116-2856 days). • The 12-month, 24.7-month, and 60.8-month cumulative percentages of pGGN growth were 10%, 25.5%, and 51.1%, respectively, and they significantly differed among the initial diameter, volume, and mass subgroups (all p values < 0.001). The growth pattern of pure ground-glass nodules may conform to exponential model.
Citing Articles
Minimally invasive biomarkers for triaging lung nodules-challenges and future perspectives.
Afridi W, Picos S, Bark J, Stamoudis D, Vasani S, Irwin D
Cancer Metastasis Rev. 2025; 44(1):29.
PMID: 39888565
PMC: 11785609.
DOI: 10.1007/s10555-025-10247-5.
Enhancing Diagnostic Accuracy of Lung Nodules in Chest Computed Tomography Using Artificial Intelligence: Retrospective Analysis.
Liu W, Wu Y, Zheng Z, Bittle M, Yu W, Kharrazi H
J Med Internet Res. 2025; 27:e64649.
PMID: 39869890
PMC: 11811665.
DOI: 10.2196/64649.
Multimodal integration to identify the invasion status of lung adenocarcinoma intraoperatively.
Tan X, Pan F, Zhan N, Wang S, Dong Z, Li Y
iScience. 2024; 27(12):111421.
PMID: 39687006
PMC: 11647133.
DOI: 10.1016/j.isci.2024.111421.
The effectiveness of deep learning model in differentiating benign and malignant pulmonary nodules on spiral CT.
Liu D, Zhao Y, Liu B
Technol Health Care. 2024; 32(6):5129-5140.
PMID: 39520159
PMC: 11613059.
DOI: 10.3233/THC-241079.
[Research Progress of Comprehensive Follow-up Management Strategy on the Natural History of Simultaneous, Persistent Multiple Pulmonary Ground-glass Nodules].
Huang C, Zhou Y, Fang Y, Liu Y, Wang L, Zhuo Y
Zhongguo Fei Ai Za Zhi. 2024; 27(9):691-696.
PMID: 39492584
PMC: 11534573.
DOI: 10.3779/j.issn.1009-3419.2024.106.25.
Prediction of benign and malignant ground glass pulmonary nodules based on multi-feature fusion of attention mechanism.
Deng H, Huang W, Zhou X, Zhou T, Fan L, Liu S
Front Oncol. 2024; 14:1447132.
PMID: 39445066
PMC: 11496306.
DOI: 10.3389/fonc.2024.1447132.
The value of non-enhanced CT 3D visualization in differentiating stage Ⅰ invasive lung adenocarcinoma between LPA and non-LPA.
Chen J, Zeng X, Li F, Peng J
Eur J Radiol Open. 2024; 13:100600.
PMID: 39351522
PMC: 11440297.
DOI: 10.1016/j.ejro.2024.100600.
Image quality and detection efficacy of zero echo time magnetic resonance imaging on Lung-RADS 2 pulmonary ground-glass nodules in comparison to thin-slice fat-saturated T2-weighted imaging.
Zou Q, Wan Q, Liu J, Liu W, Ding R, Fang H
J Thorac Dis. 2024; 16(8):5167-5179.
PMID: 39268111
PMC: 11388255.
DOI: 10.21037/jtd-24-414.
Evaluating artificial intelligence's role in lung nodule diagnostics: A survey of radiologists in two pilot tertiary hospitals in China.
Liu W, Wu Y, Zheng Z, Yu W, Bittle M, Kharrazi H
J Clin Imaging Sci. 2024; 14:31.
PMID: 39246733
PMC: 11380818.
DOI: 10.25259/JCIS_72_2024.
Construction and validation of a risk score system for diagnosing invasive adenocarcinoma presenting as pulmonary pure ground-glass nodules: a multi-center cohort study in China.
Meng Q, Zheng C, Guo L, Gao P, Liu W, Ge H
Quant Imaging Med Surg. 2024; 14(7):4864-4877.
PMID: 39022278
PMC: 11250337.
DOI: 10.21037/qims-24-170.
A case of lung metastasis from gastric cancer presenting as ground-glass opacity dominant nodules.
Niimi T, Samejima J, Koike Y, Miyoshi T, Tane K, Aokage K
J Cardiothorac Surg. 2024; 19(1):365.
PMID: 38915083
PMC: 11194956.
DOI: 10.1186/s13019-024-02860-2.
Prediction of the stage shift growth of early-stage lung adenocarcinomas by volume-doubling time.
Tang E, Wu Y, Chen C, Wu F
Quant Imaging Med Surg. 2024; 14(6):3983-3996.
PMID: 38846271
PMC: 11151246.
DOI: 10.21037/qims-23-1759.
Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis.
Quanyang W, Yao H, Sicong W, Linlin Q, Zewei Z, Donghui H
Cancer Med. 2024; 13(7):e7140.
PMID: 38581113
PMC: 10997848.
DOI: 10.1002/cam4.7140.
Deep learning-assisted development and validation of an algorithm for predicting the growth of persistent pure ground-glass nodules.
Tang Y, Li M, Lin B, Tao X, Shi Z, Jin X
Transl Lung Cancer Res. 2024; 12(12):2494-2504.
PMID: 38205216
PMC: 10775010.
DOI: 10.21037/tlcr-23-666.
Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images.
Zhang R, Wei Y, Wang D, Chen B, Sun H, Lei Y
Eur Radiol. 2023; 34(7):4218-4229.
PMID: 38114849
DOI: 10.1007/s00330-023-10518-1.
Developing a multi-institutional nomogram for assessing lung cancer risk in patients with 5-30 mm pulmonary nodules: a retrospective analysis.
Jiang Y, Deng T, Huang Y, Ren B, He L, Pang M
PeerJ. 2023; 11:e16539.
PMID: 38107565
PMC: 10725170.
DOI: 10.7717/peerj.16539.
Two-stage minimally invasive pulmonary resections with intraoperative localization technique for bilateral multiple primary lung cancers: A case report.
Huang C, Tong H
Thorac Cancer. 2023; 15(2):192-197.
PMID: 38018514
PMC: 10788464.
DOI: 10.1111/1759-7714.15183.
Tumor blood vessel in 3D reconstruction CT imaging as an risk indicator for growth of pulmonary nodule with ground-glass opacity.
Xue W, Kong L, Zhang X, Xin Z, Zhao Q, He J
J Cardiothorac Surg. 2023; 18(1):333.
PMID: 37968739
PMC: 10647107.
DOI: 10.1186/s13019-023-02423-x.
Baseline whole-lung CT features deriving from deep learning and radiomics: prediction of benign and malignant pulmonary ground-glass nodules.
Huang W, Deng H, Li Z, Xiong Z, Zhou T, Ge Y
Front Oncol. 2023; 13:1255007.
PMID: 37664069
PMC: 10470826.
DOI: 10.3389/fonc.2023.1255007.
Managing Persistent Subsolid Nodules in Lung Cancer: Education, Decision Making, and Impact of Interval Growth Patterns.
Liu Y, Liang C, Wu Y, Chen C, Tang E, Wu F
Diagnostics (Basel). 2023; 13(16).
PMID: 37627933
PMC: 10453827.
DOI: 10.3390/diagnostics13162674.