Solitary solid pulmonary nodules: a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas



To evaluate the differential diagnostic performance of a computed tomography (CT)-based deep learning nomogram (DLN) in identifying tuberculous granuloma (TBG) and lung adenocarcinoma (LAC) presenting as solitary solid pulmonary nodules (SSPNs).


Routine CT images of 550 patients with SSPNs were retrospectively obtained from two centers. A convolutional neural network was used to extract deep learning features from all lesions. The training set consisted of data for 218 patients. The least absolute shrinkage and selection operator logistic regression was used to create a deep learning signature (DLS). Clinical factors and CT-based subjective findings were combined in a clinical model. An individualized DLN incorporating DLS, clinical factors, and CT-based subjective findings was constructed to validate the diagnostic ability. The performance of the DLN was assessed by discrimination and calibration using internal (n = 140) and external validation cohorts (n = 192).


DLS, gender, age, and lobulated shape were found to be independent predictors and were used to build the DLN. The combination showed better diagnostic accuracy than any single model evaluated using the net reclassification improvement method (p < 0.05). The areas under the curve in the training, internal validation, and external validation cohorts were 0.889 (95% confidence interval [CI], 0.839–0.927), 0.879 (95% CI, 0.813–0.928), and 0.809 (95% CI, 0.746–0.862), respectively. Decision curve analysis and stratification analysis showed that the DLN has potential generalization ability.


The CT-based DLN can preoperatively distinguish between LAC and TBG in patients presenting with SSPNs.

Key Points

• The deep learning nomogram was developed to preoperatively differentiate TBG from LAC in patients with SSPNs.

• The performance of the deep learning feature was superior to that of the radiomics feature.

• The deep learning nomogram achieved superior performance compared to the deep learning signature, the radiomics signature, or the clinical model alone.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6



Area under the curve


Confidence interval


Convolutional neural network


Computed tomography


Decision curve analysis


Deep learning


Deep learning nomogram


Deep learning signature


Handcrafted radiomics


Lung adenocarcinoma


Least absolute shrinkage and selection operator


Negative probability value


Net reclassification index


Odds ratio


Positive probability value


Receiver operating characteristic


Region of interest


Solitary solid pulmonary nodules


Identifying tuberculous granuloma


  1. 1.

    Pagan A, Ramakrishnan L (2015) Immunity and immunopathology in the tuberculous granuloma. Cold Spring Harb Perspect Med.

  2. 2.

    Henschke CI, Salvatore M, Cham M et al (2018) Baseline and annual repeat rounds of screening: implications for optimal regimens of screening. Eur Radiol 28(3):1085–1094

    Article  PubMed Central  Google Scholar 

  3. 3.

    Ost D, Fein AM, Feinsilver SH (2003) Clinical practice. The solitary pulmonary nodule. N Engl J Med 348(25):2535–2542

    Article  PubMed Central  Google Scholar 

  4. 4.

    Wan Q, Deng YS, Lei Q et al (2019) Differentiating between malignant and benign solid solitary pulmonary lesions: are intravoxel incoherent motion and diffusion kurtosis imaging superior to conventional diffusion-weighted imaging? Eur Radiol 29(3):1607–1615

    Article  PubMed Central  Google Scholar 

  5. 5.

    Pretto MM, Alves BM, De MFPN et al (2016) Solitary pulmonary nodule and 18F-FDG PET/CT. Part 1: epidemiology, morphological evaluation and cancer probability. Radiol Bras 49(1):35–42

    Article  Google Scholar 

  6. 6.

    MacMahon H, Naidich DP, Goo JM et al (2017) Guidelines for management of incidental pulmonary nodules detected on CT images: from the Fleischner Society 2017. Radiology 284(1):228–243

    Article  PubMed Central  Google Scholar 

  7. 7.

    Patel VK, Naik SK, Naidich DP et al (2013) A practical algorithmic approach to the diagnosis and management of solitary pulmonary nodules part 2: pretest probability and algorithm. Chest 143(3):825–839

    Article  PubMed Central  Google Scholar 

  8. 8.

    Starnes SL, Reed MF, Meyer CA et al (2011) Can lung cancer screening by computed tomography be effective in areas with endemic histoplasmosis? J Thorac Cardiovasc Surg 141(3):688–693

    Article  PubMed Central  Google Scholar 

  9. 9.

    MacMahon H, Austin JH, Gamsu G et al (2005) Guidelines for management of small pulmonary nodules detected on CT scans: a statement from the Fleischner Society. Radiology 237(2):395–400

    Article  Google Scholar 

  10. 10.

    Winer-Muram HT (2006) The solitary pulmonary nodule. Radiology 239(1):34–49

    Article  PubMed Central  Google Scholar 

  11. 11.

    Brandman S, Ko JP (2011) Pulmonary nodule detection, characterization, and management with multi-detector computed tomography. J Thorac Imaging 26(2):90–105

    Article  PubMed Central  Google Scholar 

  12. 12.

    Jin-Yu L, Xiao-Wen H, Hang-Tong H et al (2017) Predicting malignancy in thyroid nodules: radiomics score versus 2017 American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Thyroid.

  13. 13.

    He L, Huang Y, Ma Z, Liang C, Liang C, Liu Z (2016) Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule. Sci Rep.

  14. 14.

    Chia-Hung C, Chih-Kun C, Chih-Yen T et al (2018) Radiomic features analysis in computed tomography images of lung nodule classification. PLoS One.

  15. 15.

    Sun Y, Li C, Jin L et al (2020) Radiomics for lung adenocarcinoma manifesting as pure ground-glass nodules: invasive prediction. Eur Radiol.

  16. 16.

    Tu W, Li Z, Wang Y et al (2019) The “solid” component within subsolid nodules: imaging definition, display, and correlation with invasiveness of lung adenocarcinoma, a comparison of CT histograms and subjective evaluation. Eur Radiol 29(4):1703–1713

    Article  PubMed Central  Google Scholar 

  17. 17.

    Poplin R, Varadarajan AV, Blumer K et al (2018) Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng 2(3):158–164

    Article  Google Scholar 

  18. 18.

    Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118

    CAS  Article  Google Scholar 

  19. 19.

    Ting DSW, Cheung CY-L, Lim G et al (2017) Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318(22):2211–2223

    Article  PubMed Central  Google Scholar 

  20. 20.

    Lakhani P, Sundaram B (2017) Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284(2):574–582

    Article  PubMed Central  Google Scholar 

  21. 21.

    Wang S, Zhou M, Liu Z et al (2017) Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal 40:172–183

    Article  PubMed Central  Google Scholar 

  22. 22.

    De Jay N, Papillon-Cavanagh S, Olsen C, El-Hachem N, Bontempi G, Haibe-Kains B (2013) mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics 29(18):2365–2368

    Article  Google Scholar 

  23. 23.

    Selvaraju RR, Cogswell M, Das A et al (2019) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis.

  24. 24.

    Kotikalapudi R keras-vis. Accessed 2017

  25. 25.

    Hawkins S, Wang H, Liu Y et al (2016) Predicting malignant nodules from screening CT scans. J Thorac Oncol 11(12):2120–2128

    Article  PubMed Central  Google Scholar 

  26. 26.

    Xu DM, van Klaveren RJ, de Bock GH et al (2008) Limited value of shape, margin and CT density in the discrimination between benign and malignant screen detected solid pulmonary nodules of the NELSON trial. Eur J Radiol 68(2):347–352

    Article  PubMed Central  Google Scholar 

Download references


This study received funding from the National Natural Science Foundation of China (81960324, 61967004) and the incubation project of 1000 Young and Middle-Aged Key Teachers in Guangxi Universities (2018GXQGFB160).

Author information



Corresponding authors

Correspondence to WanSheng Long or XueGuo Liu.

Ethics declarations


The scientific guarantor of this publication is WanSheng Long.

Conflict of interest

The authors declare that they have no conflict of interest.

Statistics and biometry

Bao Feng kindly provided statistical advice for this manuscript.

Bao Feng and YeHang Chen have significant statistical expertise.

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.


• Retrospective

• Diagnostic or prognostic study

• Multicenter study

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material


(DOCX 2078 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Feng, B., Chen, X., Chen, Y. et al. Solitary solid pulmonary nodules: a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas. Eur Radiol (2020).

Download citation


  • Tuberculosis
  • Lung adenocarcinoma
  • Solitary pulmonary nodule
  • Deep learning