Skip to main content
SpringerLink
Log in

Enhancing the prediction of symptomatic radiation pneumonitis for locally advanced non-small-cell lung cancer by combining 3D deep learning-derived imaging features with dose–volume metrics: a two-center study

  • Original Article
  • Published:
Strahlentherapie und Onkologie Aims and scope Submit manuscript

Abstract

Objective

This study aims to examine the ability of deep learning (DL)-derived imaging features for the prediction of radiation pneumonitis (RP) in locally advanced non-small-cell lung cancer (LA-NSCLC) patients.

Materials and methods

The study cohort consisted of 90 patients from the Fudan University Shanghai Cancer Center and 59 patients from the Affiliated Hospital of Jiangnan University. Occurrences of RP were used as the endpoint event. A total of 512 3D DL-derived features were extracted from two regions of interest (lung–PTV and PTV–GTV) delineated on the pre-radiotherapy planning CT. Feature selection was done using LASSO regression, and the classification models were built using the multilayered perceptron method. Performances of the developed models were evaluated by receiver operating characteristic curve analysis. In addition, the developed models were supplemented with clinical variables and dose–volume metrics of relevance to search for increased predictive value.

Results

The predictive model using DL features derived from lung–PTV outperformed the one based on features extracted from PTV–GTV, with AUCs of 0.921 and 0.892, respectively, in the internal test dataset. Furthermore, incorporating the dose–volume metric V30Gy into the predictive model using features from lung–PTV resulted in an improvement of AUCs from 0.835 to 0.881 for the training data and from 0.690 to 0.746 for the validation data, respectively (DeLong p < 0.05).

Conclusion

Imaging features extracted from pre-radiotherapy planning CT using 3D DL networks could predict radiation pneumonitis and may be of clinical value for risk stratification and toxicity management in LA-NSCLC patients.

Clinical relevance statement

Integrating DL-derived features with dose–volume metrics provides a promising noninvasive method to predict radiation pneumonitis in LA-NSCLC lung cancer radiotherapy, thus improving individualized treatment and patient outcomes.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CNN:

Convolutional neural networks

DL:

Deep learning

DLR:

Deep learning-based radiomics

GTV:

Gross tumor volume

IMRT:

Intensity-modulated radiotherapy

LA-NSCLC:

Locally advanced non-small-cell lung cancer

LASSO:

Least absolute shrinkage and selection operator

Lung–GTV:

Bilateral lung excluding GTV

Lung–PTV:

Bilateral lung excluding PTV

MLD:

Mean lung dose

MLP:

Multilayered perceptron

PTV:

Planning target volume

ResNet:

Residual deep neural network

ROC:

Receiver operating characteristic

ROI:

Region of interest

RP:

Radiation pneumonitis

RTOG:

Radiation Therapy Oncology Group

SBRT:

Stereotactic body radiotherapy

SCC:

Squamous cell carcinoma

SD:

Standard deviation

References

  1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A et al (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249. https://doi.org/10.3322/caac.21660

    Article  PubMed  Google Scholar 

  2. Miller M, Hanna N (2021) Advances in systemic therapy for non-small cell lung cancer. BMJ 375:n2363. https://doi.org/10.1136/bmj.n2363

    Article  PubMed  Google Scholar 

  3. Keffer S, Guy CL, Weiss E (2020) Fatal radiation pneumonitis: literature review and case series. Adv Radiat Oncol 5:238–249. https://doi.org/10.1016/j.adro.2019.08.010

    Article  PubMed  Google Scholar 

  4. Graham MV, Purdy JA, Emami B, Harms W, Bosch W, Lockett MA et al (1999) Clinical dose-volume histogram analysis for pneumonitis after 3D treatment for non-small cell lung cancer (NSCLC). Int J Radiat Oncol Biol Phys 45:323–329. https://doi.org/10.1016/s0360-3016(99)00183-2

    Article  CAS  PubMed  Google Scholar 

  5. Tsujino K, Hirota S, Endo M, Obayashi K, Kotani Y, Satouchi M et al (2003) Predictive value of dose-volume histogram parameters for predicting radiation pneumonitis after concurrent chemoradiation for lung cancer. Int J Radiat Oncol Biol Phys 55:110–115. https://doi.org/10.1016/s0360-3016(02)03807-5

    Article  PubMed  Google Scholar 

  6. Katsui K, Ogata T, Watanabe K, Katayama N, Soh J, Kuroda M et al (2019) Dose-volume parameters predict radiation pneumonitis after induction chemoradiotherapy followed by surgery for non-small cell lung cancer: a retrospective analysis. BMC Cancer 19:1144. https://doi.org/10.1186/s12885-019-6359-9

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Vogelius IR, Bentzen SM (2012) A literature-based meta-analysis of clinical risk factors for development of radiation induced pneumonitis. Acta Oncol 51:975–983. https://doi.org/10.3109/0284186X.2012.718093

    Article  PubMed  PubMed Central  Google Scholar 

  8. Robnett TJ, Machtay M, Vines EF, McKenna MG, Algazy KM, McKenna WG (2000) Factors predicting severe radiation pneumonitis in patients receiving definitive chemoradiation for lung cancer. Int J Radiat Oncol Biol Phys 48:89–94. https://doi.org/10.1016/s0360-3016(00)00648-9

    Article  CAS  PubMed  Google Scholar 

  9. Hernando ML, Marks LB, Bentel GC, Zhou SM, Hollis D, Das SK et al (2001) Radiation-induced pulmonary toxicity: a dose-volume histogram analysis in 201 patients with lung cancer. Int J Radiat Oncol Biol Phys 51:650–659. https://doi.org/10.1016/s0360-3016(01)01685-6

    Article  CAS  PubMed  Google Scholar 

  10. Avanzo M, Stancanello J, Pirrone G, Sartor G (2020) Radiomics and deep learning in lung cancer. Strahlenther Onkol 196:879–887. https://doi.org/10.1007/s00066-020-01625-9

    Article  PubMed  Google Scholar 

  11. Kawahara D, Imano N, Nishioka R, Ogawa K, Kimura T, Nakashima T et al (2021) Prediction of radiation pneumonitis after definitive radiotherapy for locally advanced non-small cell lung cancer using multi-region radiomics analysis. Sci Rep 11:16232. https://doi.org/10.1038/s41598-021-95643-x

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  12. Krafft SP, Rao A, Stingo F, Briere TM, Court LE, Liao Z et al (2018) The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis. Med Phys 45:5317–5324. https://doi.org/10.1002/mp.13150

    Article  PubMed  Google Scholar 

  13. Huang B, Sollee J, Luo YH, Reddy A, Zhong Z, Wu J et al (2022) Prediction of lung malignancy progression and survival with machine learning based on pre-treatment FDG-PET/CT. EBioMedicine 82:104127. https://doi.org/10.1016/j.ebiom.2022.104127

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Kuker RA, Lehmkuhl D, Kwon D, Zhao W, Lossos IS, Moskowitz CH et al (2022) A deep learning-aided automated method for calculating metabolic tumor volume in diffuse large B‑cell lymphoma. Cancers. https://doi.org/10.3390/cancers14215221

    Article  PubMed  PubMed Central  Google Scholar 

  15. Yang F, Young LA, Johnson PB (2018) Quantitative radiomics: validating image textural features for oncological PET in lung cancer. Radiother Oncol 129:209–217. https://doi.org/10.1016/j.radonc.2018.09.009

    Article  PubMed  Google Scholar 

  16. Rich B, Huang J, Yang Y, Jin W, Johnson P, Wang L et al (2021) Radiomics predicts for distant metastasis in locally advanced human papillomavirus-positive oropharyngeal squamous cell carcinoma. Cancers. https://doi.org/10.3390/cancers13225689

    Article  PubMed  PubMed Central  Google Scholar 

  17. Yang F, Thomas MA, Dehdashti F, Grigsby PW (2013) Temporal analysis of intratumoral metabolic heterogeneity characterized by textural features in cervical cancer. Eur J Nucl Med Mol Imaging 40:716–727. https://doi.org/10.1007/s00259-012-2332-4

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Jiang W, Song Y, Sun Z, Qiu J, Shi L (2021) Dosimetric factors and radiomics features within different regions of interest in planning CT images for improving the prediction of radiation pneumonitis. Int J Radiat Oncol Biol Phys 110:1161–1170. https://doi.org/10.1016/j.ijrobp.2021.01.049

    Article  PubMed  Google Scholar 

  19. Chen S, Ma K, Zheng Y (2019) Med3D: transfer learning for 3D medical image analysis https://doi.org/10.48550/arXiv.1904.00625

    Book  Google Scholar 

  20. Meng Y, Yang H, Wang W, Tang X, Jiang C, Shen Y et al (2019) Excluding PTV from lung volume may better predict radiation pneumonitis for intensity modulated radiation therapy in lung cancer patients. Radiat Oncol 14:7. https://doi.org/10.1186/s13014-018-1204-x

    Article  PubMed  PubMed Central  Google Scholar 

  21. Okubo M, Itonaga T, Saito T, Shiraishi S, Mikami R, Nakayama H et al (2017) Predicting risk factors for radiation pneumonitis after stereotactic body radiation therapy for primary or metastatic lung tumours. Br J Radiol 90:20160508. https://doi.org/10.1259/bjr.20160508

    Article  PubMed  PubMed Central  Google Scholar 

  22. Kumar G, Rawat S, Puri A, Sharma MK, Chadha P, Babu AG et al (2012) Analysis of dose-volume parameters predicting radiation pneumonitis in patients with esophageal cancer treated with 3D-conformal radiation therapy or IMRT. Jpn J Radiol 30:18–24. https://doi.org/10.1007/s11604-011-0002-2

    Article  PubMed  Google Scholar 

  23. Sheng L, Cui X, Cheng L, Chen Y, Du X (2019) Risk factors of grade ≥ 2 radiation pneumonitis after gemcitabine induction chemotherapy for patients with non-small cell lung cancer. Radiat Oncol 14:229. https://doi.org/10.1186/s13014-019-1440-8

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Saha A, Beasley M, Hatton N et al (2021) Clinical and dosimetric predictors of radiation pneumonitis in early-stage lung cancer treated with Stereotactic ablative radiotherapy (SABR)—an analysis of UK’s largest cohort of lung SABR patients. Radiother Oncol 156:153–159. https://doi.org/10.1016/j.radonc.2020.12.015

    Article  CAS  PubMed  Google Scholar 

  25. Chetan MR, Gleeson FV (2021) Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives. Eur Radiol 31:1049–1058. https://doi.org/10.1007/s00330-020-07141-9

    Article  PubMed  Google Scholar 

  26. Cunliffe A, Armato SG 3rd, Castillo R, Pham N, Guerrero T et al (2015) Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. Int J Radiat Oncol Biol Phys 91:1048–1056. https://doi.org/10.1016/j.ijrobp.2014.11.030

    Article  PubMed  PubMed Central  Google Scholar 

  27. Moran A, Daly ME, Yip SSF, Yamamoto T (2017) Radiomics-based assessment of radiation-induced lung injury after stereotactic body radiotherapy. Clin Lung Cancer 18:e425–e431. https://doi.org/10.1016/j.cllc.2017.05.014

    Article  CAS  PubMed  Google Scholar 

  28. Liang B, Tian Y, Chen X, Yan H, Yan L, Zhang T et al (2019) Prediction of radiation pneumonitis with dose distribution: a convolutional neural network (CNN) based model. Front Oncol 9:1500. https://doi.org/10.3389/fonc.2019.01500

    Article  PubMed  Google Scholar 

  29. Kapoor R, Sleeman W, Palta J, Weiss E (2023) 3D deep convolution neural network for radiation pneumonitis prediction following stereotactic body radiotherapy. J Appl Clin Med Phys 24:e13875. https://doi.org/10.1002/acm2.13875

    Article  PubMed  Google Scholar 

  30. Shah AA, Malik HAM, Muhammad A, Alourani A, Butt ZA (2023) Deep learning ensemble 2D CNN approach towards the detection of lung cancer. Sci Rep 13:2987. https://doi.org/10.1038/s41598-023-29656-z

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  31. Huang Y, Feng A, Lin Y, Gu H, Chen H, Wang H et al (2022) Radiation pneumonitis prediction after stereotactic body radiation therapy based on 3D dose distribution: dosiomics and/or deep learning-based radiomics features. Radiat Oncol 17:188. https://doi.org/10.1186/s13014-022-02154-8

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Funding

1. Translational Medicine Project of Wuxi Commission of Health (grant no. ZH202101). 2. Top Talent Support Program for young and middle-aged people of Wuxi Health Committee (grant no. HB2023059). 3. Wuxi Translational Medical Research Institute Project Plan (grant no. LCYJ202339).

Author information

Authors and Affiliations

  1. Department of Radiation Oncology, Affiliated Hospital of Jiangnan University, 1000 Hefeng Road, 214122, Wuxi, Jiangsu, China

    Yan Kong, Mingming Su, Yan Zhu, Xuan Li, Jinmeng Zhang, Jialiang Zhou & Jianfeng Huang

  2. Department of Medical Oncology, Affiliated Huishan Hospital of Xinglin College, Nantong University, Wuxi Huishan District People’s Hospital, 214187, Wuxi, Jiangsu, China

    Mingming Su & Xuan Li

  3. Department of Radiation Oncology, Fudan University Shanghai Cancer Center, 270 Dongan Road, Xuhui, 200032, Shanghai, China

    Jinmeng Zhang, Jianjiao Ni, Xi Yang & Zhengfei Zhu

  4. Department of Oncology, Shanghai Medical College, Fudan University, 200032, Shanghai, China

    Jinmeng Zhang, Jianjiao Ni, Xi Yang & Zhengfei Zhu

  5. Department of Diagnostic and Interventional Radiology, University of Tsukuba, 305-8577, Ibaraki, Japan

    Wenchao Gu

  6. Department of Radiation Oncology, University of Miami, 33136, Miami, FL, USA

    Fei Yang

Authors
  1. Yan Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingming Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yan Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jinmeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wenchao Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Fei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jialiang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jianjiao Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Xi Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Zhengfei Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Jianfeng Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhengfei Zhu or Jianfeng Huang.

Ethics declarations

Conflict of interest

Y. Kong, M. Su, Y. Zhu, X. Li, J. Zhang, W. Gu, F. Yang, J. Zhou, J. Ni, X. Yang, Z. Zhu, and J. Huang declare that they have no competing interests.

Additional information

Publisher’s Note

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

The authors Yan Kong and Mingming Su have contributed equally to this work and share first authorship.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kong, Y., Su, M., Zhu, Y. et al. Enhancing the prediction of symptomatic radiation pneumonitis for locally advanced non-small-cell lung cancer by combining 3D deep learning-derived imaging features with dose–volume metrics: a two-center study. Strahlenther Onkol (2024). https://doi.org/10.1007/s00066-024-02221-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00066-024-02221-x

Keywords

Search

Navigation