Abstract
Objectives
The aim of this study was to determine the invasiveness of ground-glass nodules (GGNs) using a 3D multi-task deep learning network.
Methods
We propose a novel architecture based on 3D multi-task learning to determine the invasiveness of GGNs. In total, 770 patients with 909 GGNs who underwent lung CT scans were enrolled. The patients were divided into the training (n = 626) and test sets (n = 144). In the test set, invasiveness was classified using deep learning into three categories: atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive pulmonary adenocarcinoma (IA). Furthermore, binary classifications (AAH/AIS/MIA vs. IA) were made by two thoracic radiologists and compared with the deep learning results.
Results
In the three-category classification task, the sensitivity, specificity, and accuracy were 65.41%, 82.21%, and 64.9%, respectively. In the binary classification task, the sensitivity, specificity, accuracy, and area under the ROC curve (AUC) values were 69.57%, 95.24%, 87.42%, and 0.89, respectively. In the visual assessment of GGN invasiveness of binary classification by the two thoracic radiologists, the sensitivity, specificity, and accuracy of the senior and junior radiologists were 58.93%, 90.51%, and 81.35% and 76.79%, 55.47%, and 61.66%, respectively.
Conclusions
The proposed multi-task deep learning model achieved good classification results in determining the invasiveness of GGNs. This model may help to select patients with invasive lesions who need surgery and the proper surgical methods.
Key Points
• The proposed multi-task model has achieved good classification results for the invasiveness of GGNs.
• The proposed network includes a classification and segmentation branch to learn global and regional features, respectively.
• The multi-task model could assist doctors in selecting patients with invasive lesions who need surgery and choosing appropriate surgical methods.
Similar content being viewed by others
Abbreviations
- 3D:
-
Three-dimension
- AAH:
-
Atypical adenomatous hyperplasia
- AIS:
-
Adenocarcinoma in situ
- AUC:
-
Area under the curve
- BN:
-
Batch normalization
- CNN:
-
Convolutional neural network
- CT:
-
Computed tomography
- GGN:
-
Ground-glass nodule
- GGO:
-
Ground-glass opacity
- GPU:
-
Graphics processing unit
- HIPAA:
-
Health Insurance Portability and Accountability Act
- IA:
-
Invasive pulmonary adenocarcinoma
- IRB:
-
Institutional review board
- LLL:
-
Left lower lobe
- LUL:
-
Left upper lobe
- MCC:
-
Matthews correlation coefficient
- MIA:
-
Minimally invasive adenocarcinoma
- pGGN:
-
Pure ground-glass nodule
- PSN:
-
Part-solid nodule
- PTNB:
-
Percutaneous transthoracic needle lung biopsies
- RLL:
-
Right lower lobe
- RML:
-
Right middle lobe
- ROC:
-
Receiver operating characteristic
- RUL:
-
Right upper lobe
- SGD:
-
Stochastic gradient descent
- VATS:
-
Video-assisted thoracoscopic surgery
- VGG:
-
Visual geometry group
- WHO:
-
World Health Organization
References
de Groot P, Munden RF (2012) Lung cancer epidemiology, risk factors, and prevention. Radiol Clin North Am 50:863–876
Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA Cancer J Clin 69:7–34
Goo JM, Park CM, Lee HJ (2011) Ground-glass nodules on chest CT as imaging biomarkers in the management of lung adenocarcinoma. AJR Am J Roentgenol 196:533–543
Hansell DM, Bankier AA, MacMahon H, McLoud TC, Muller NL, Remy J (2008) Fleischner Society: glossary of terms for thoracic imaging. Radiology 246:697–722
Travis WD, Brambilla E, Noguchi M et al (2011) International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society: international multidisciplinary classification of lung adenocarcinoma: executive summary. Proc Am Thorac Soc 8:381–385
Travis WD, Brambilla E, Nicholson AG et al (2015) The 2015 World Health Organization Classification of Lung Tumors: impact of genetic, clinical and radiologic advances since the 2004 classification. J Thorac Oncol 10:1243–1260
Van Schil PE, Asamura H, Rusch VW et al (2012) Surgical implications of the new IASLC/ATS/ERS adenocarcinoma classification. Eur Respir J 39:478–486
Howington JA, Blum MG, Chang AC, Balekian AA, Murthy SC (2013) Treatment of stage I and II non-small cell lung cancer: diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines. Chest 143:e278S–e313S
Mack MJ, Aronoff RJ, Acuff TE, Douthit MB, Bowman RT, Ryan WH (1992) Present role of thoracoscopy in the diagnosis and treatment of diseases of the chest. Ann Thorac Surg 54:403–408
Lee JW, Park CH, Lee SM, Jeong M, Hur J (2019) Planting seeds into the lung: image-guided percutaneous localization to guide minimally invasive thoracic surgery. Korean J Radiol 20:1498–1514
Shen D, Wu G, Suk HI (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Shin H-C, Roth HR, Gao M et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35:1285–1298
Sun W, Zheng B, Qian W (2017) Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis. Comput Biol Med 89:530–539
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
Dou Q, Chen H, Yu L, Qin J, Heng PA (2017) Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 64:1558–1567
Zhao W, Yang J, Sun Y et al (2018) 3D deep learning from CT scans predicts tumor invasiveness of subcentimeter pulmonary adenocarcinomas. Cancer Res 78:6881–6889
Wang S, Wang R, Zhang S et al (2018) 3D convolutional neural network for differentiating pre-invasive lesions from invasive adenocarcinomas appearing as ground-glass nodules with diameters </=3 cm using HRCT. Quant Imaging Med Surg 8:491–499
Gong J, Liu J, Hao W et al (2020) A deep residual learning network for predicting lung adenocarcinoma manifesting as ground-glass nodule on CT images. Eur Radiol 30:1847–1855
Qi LL, Wu BT, Tang W et al (2020) Long-term follow-up of persistent pulmonary pure ground-glass nodules with deep learning-assisted nodule segmentation. Eur Radiol 30:744–755
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. ICML 2015:448–456 https://arxiv.org/abs/1502.03167
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. IEEE Conf Comput Vis Pattern Recog (CVPR):2261–2269. https://doi.org/10.1109/CVPR.2017.243
Milletari F, Navab N, Ahmadi S (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. Fourth Int Conf 3D Vis (3DV):565–571. https://doi.org/10.1109/3DV.2016.79
Paszke A, Gross S, Massa F et al (2019) PyTorch: an imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, pp 8024-8035. ArXiv abs/1912:01703
Wang L, Yang Y, Min R, Chakradhar S (2017) Accelerating deep neural network training with inconsistent stochastic gradient descent. Neural Netw 93:219–229
Travis WD, Brambilla E, Noguchi M et al (2011) International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma. J Thorac Oncol 6:244–285
Zhang Y, Tang J, Xu J, Cheng J, Wu H (2017) Analysis of pulmonary pure ground-glass nodule in enhanced dual energy CT imaging for predicting invasive adenocarcinoma: comparing with conventional thin-section CT imaging. J Thorac Dis 9:4967–4978
Ding H, Shi J, Zhou X et al (2017) Value of CT characteristics in predicting invasiveness of adenocarcinoma presented as pulmonary ground-glass nodules. Thorac Cardiovasc Surg 65:136–141
Wu F, Tian SP, Jin X et al (2017) CT and histopathologic characteristics of lung adenocarcinoma with pure ground-glass nodules 10 mm or less in diameter. Eur Radiol 27:4037–4043
Zhang Y, Shen Y, Qiang JW, Ye JD, Zhang J, Zhao RY (2016) HRCT features distinguishing pre-invasive from invasive pulmonary adenocarcinomas appearing as ground-glass nodules. Eur Radiol 26:2921–2928
Yue X, Liu S, Liu S et al (2018) HRCT morphological characteristics distinguishing minimally invasive pulmonary adenocarcinoma from invasive pulmonary adenocarcinoma appearing as subsolid nodules with a diameter of </=3 cm. Clin Radiol 73:411.e7–411.e15
Zhan Y, Peng X, Shan F et al (2019) Attenuation and morphologic characteristics distinguishing a ground-glass nodule measuring 5-10 mm in diameter as invasive lung adenocarcinoma on thin-slice CT. AJR Am J Roentgenol 213:W162–W170
Congedo MT, Iezzi R, Nachira D et al (2019) Uniportal VATS coil-assisted resections for GGOs. J Oncol 2019:5383086. https://doi.org/10.1155/2019/5383086
Fan L, Fang M, Li Z et al (2019) Radiomics signature: a biomarker for the preoperative discrimination of lung invasive adenocarcinoma manifesting as a ground-glass nodule. Eur Radiol 29:889–897
Gao C, Xiang P, Ye J, Pang P, Wang S, Xu M (2019) Can texture features improve the differentiation of infiltrative lung adenocarcinoma appearing as ground glass nodules in contrast-enhanced CT? Eur J Radiol 117:126–131
Yang Y, Wang WW, Ren Y et al (2019) Computerized texture analysis predicts histological invasiveness within lung adenocarcinoma manifesting as pure ground-glass nodules. Acta Radiol 60:1258–1264
Berenguer R, Pastor-Juan MDR, Canales-Vazquez J et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288:407–415
Yang Y, Li K, Sun D et al (2019) Invasive pulmonary adenocarcinomas versus preinvasive lesions appearing as pure ground-glass nodules: differentiation using enhanced dual-source dual-energy CT. AJR Am J Roentgenol 213:W114–W122
Funding
This study has received funding from Shanghai Shenkang Project (No. 16CR3024A), Shanghai Science and Technology Committee (No. 17441902700); Shanghai Science and Technology Committee (No. 18511102900, No. 18511102901); the Beijing Postdoctoral Research Foundation ZZ2019-88 and the National Natural Science Foundation of China (No. 81871508; No. 61572300; No. 61773246); and Taishan Scholar Program of Shandong Province of China (No. TSHW201502038); major program of Shandong Province Natural Science Foundation (No. ZR2018ZB0419).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Jiejun Cheng.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Informed consent
Written informed consent was waived by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained.
Methodology
• retrospective
• diagnostic study
• performed at one institution
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yu, Y., Wang, N., Huang, N. et al. Determining the invasiveness of ground-glass nodules using a 3D multi-task network. Eur Radiol 31, 7162–7171 (2021). https://doi.org/10.1007/s00330-021-07794-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-021-07794-0