You are here

Article Text

Article menu
Download PDFPDF
Lung cancer
Original research
Radiomics analysis to predict pulmonary nodule malignancy using machine learning approaches
  1. Matthew T Warkentin1,2,
  2. Hamad Al-Sawaihey1,
  3. Stephen Lam3,4,
  4. Geoffrey Liu2,5,
  5. Brenda Diergaarde6,7,
  6. Jian-Min Yuan7,8,
  7. David O Wilson9,
  8. Sukhinder Atkar-Khattra4,
  9. Benjamin Grant5,
  10. Yonathan Brhane1,
  11. Elham Khodayari-Moez1,
  12. Kiera R Murison1,
  13. Martin C Tammemagi10,
  14. Kieran R Campbell1,11,
  15. Rayjean J Hung1,2
  1. 1 Prosserman Centre for Population Health Research, Lunenfeld-Tanenbaum Research Institute, Sinai Health, Toronto, Ontario, Canada
  2. 2 Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada
  3. 3 Department of Medicine, University of British Columbia, Vancouver, British Columbia, Canada
  4. 4 Department of Integrative Oncology, British Columbia Cancer Research Institute, Vancouver, British Columbia, Canada
  5. 5 Department of Medical Oncology and Hematology, Princess Margaret Hospital Cancer Centre, Toronto, Ontario, Canada
  6. 6 Department of Human Genetics, University of Pittsburgh School of Public Health, Pittsburgh, Pennsylvania, USA
  7. 7 Cancer Epidemiology and Prevention Program, UPMC Hillman Cancer Center, Pittsburgh, Pennsylvania, USA
  8. 8 Department of Epidemiology, University of Pittsburgh School of Public Health, Pittsburgh, Pennsylvania, USA
  9. 9 Department of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
  10. 10 Cancer Control and Evidence Integration, Cancer Care Ontario, Toronto, Ontario, Canada
  11. 11 Department of Molecular Genetics, University of Toronto, Toronto, Ontario, Canada
  1. Correspondence to Dr Rayjean J Hung, Prosserman Centre for Population Health Research, Lunenfeld-Tanenbaum Research Institute, Sinai Health, Toronto, Canada; Rayjean.Hung{at}lunenfeld.ca

Abstract

Background Low-dose CT screening can reduce lung cancer-related mortality. However, most screen-detected pulmonary abnormalities do not develop into cancer and it often remains challenging to identify malignant nodules, particularly among indeterminate nodules. We aimed to develop and assess prediction models based on radiological features to discriminate between benign and malignant pulmonary lesions detected on a baseline screen.

Methods Using four international lung cancer screening studies, we extracted 2060 radiomic features for each of 16 797 nodules (513 malignant) among 6865 participants. After filtering out low-quality radiomic features, 642 radiomic and 9 epidemiological features remained for model development. We used cross-validation and grid search to assess three machine learning (ML) models (eXtreme Gradient Boosted Trees, random forest, least absolute shrinkage and selection operator (LASSO)) for their ability to accurately predict risk of malignancy for pulmonary nodules. We report model performance based on the area under the curve (AUC) and calibration metrics in the held-out test set.

Results The LASSO model yielded the best predictive performance in cross-validation and was fit in the full training set based on optimised hyperparameters. Our radiomics model had a test-set AUC of 0.93 (95% CI 0.90 to 0.96) and outperformed the established Pan-Canadian Early Detection of Lung Cancer model (AUC 0.87, 95% CI 0.85 to 0.89) for nodule assessment. Our model performed well among both solid (AUC 0.93, 95% CI 0.89 to 0.97) and subsolid nodules (AUC 0.91, 95% CI 0.85 to 0.95).

Conclusions We developed highly accurate ML models based on radiomic and epidemiological features from four international lung cancer screening studies that may be suitable for assessing indeterminate screen-detected pulmonary nodules for risk of malignancy.

  • lung cancer
  • clinical epidemiology
  • imaging/CT MRI etc

Data availability statement

Data are available on reasonable request. All data used in the present study may be made available on reasonable request to the Integrative Analysis of Lung Cancer Etiology and Risk (INTEGRAL) programme on approval by the Data Access Committee. The model reported in the study and example code are publicly available on GitHub (https://github.com/mattwarkentin/INTEGRAL-Radiomics).

https://doi.org/10.1136/thorax-2023-220226

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available on reasonable request. All data used in the present study may be made available on reasonable request to the Integrative Analysis of Lung Cancer Etiology and Risk (INTEGRAL) programme on approval by the Data Access Committee. The model reported in the study and example code are publicly available on GitHub (https://github.com/mattwarkentin/INTEGRAL-Radiomics).

    View Full Text

    Footnotes

    • Twitter @mattwrkntn

    • Contributors MTW: conceptualisation, methodology, formal analysis, writing–original draft, writing–review and editing. HA-S: methodology, data curation. SL: investigation, data curation, writing–review and editing. GL: investigation, data curation, writing–review and editing. BD, J-MY and DOW: investigation, data curation, writing–review and editing. SA-K, BG, YB, EK-M and KRM: writing–review and editing. MT: writing–review and editing. KRC: methodology, writing–original draft, writing–review and editing. RJH: conceptualisation, methodology, investigation, writing–original draft, writing–review and editing, funding acquisition. RJH is responsible for the overall conduct of the study.

    • Funding This work was supported by Canadian Institutes of Health Research (FDN 167273) and the National Institutes of Health (U19 CA203654).

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

    Linked Articles