Determination of the histological type of lung cancer based on radiomic analysis of computed tomography chest images

Lung cancer is one of the most common cancers. Bronchoscopy and transthoracic lung biopsy under the control of computed tomography (CT) are used for morphological verification of the tumor. Both of these technologies are invasive with certain risks and high costs. The accuracy of the morphologically verified diagnosis of lung cancer in Russia reaches an average of 88.2%. Treatment tactics, progression and prognosis of the disease depends on the histological type of lung cancer. The gold standard for lung cancer diagnosis is computed tomography of the chest. A developing area of CT image processing is radiomics, a mathematical analysis of data from radiation research methods that allows the detection of tissue texture features at a level inaccessible to the eye of a radiologist. The use of radiomics methods can contribute to the determination of the histotype of lung cancer even at the stage of diagnostic search.

Objective: to determine the most common histological types of lung cancer based on the textural analysis of CT-scans of the chest organs.

Materials and methods. The study included data from 200 patients treated at the RSCRR with histologically confirmed lung cancer, including 100 patients with small-cell lung cancer, 100 patients with non-small cell lung cancer (50 of them with adenocarcinoma and 50 with squamous cell carcinoma). 107 radiomic features were calculated for each tumor. Machine learning models were built in the Python 3.10 programming language using specialized libraries. To select the most effective models, standard machine learning metrics were used: precision, recall, accuracy, f1-measure and the area under the receiver operating characteristic curve (ROC-AUC).

Results. Several machine learning models were developed, the best metrics were gradient boosting for differentiating non-small cell lung cancer and small-cell lung cancer with ROC-AUC 0.973 and a random forest based on three trees for differentiating adenocarcinoma and squamous cell carcinoma with ROC-AUC 0.833.

Conclusion. Classification models developed by us have high metrics of diagnostic accuracy, which allows us to discourse about the applicability of radiomics features for differentiating various types of lung cancer at the stage of diagnostic search, as well as in situations where it is impossible to obtain material for histological examination.

1. Russian clinical guidelines “Malignant neoplasm of bronchi and lung”, 2021. (In Russian)

2. Singh G., Singh A., Dave R. An Update on WHO Classification of Thoracic Tumours 2021-Newly Described Entities and Terminologies. J. Clin. Diagn. Res. 2023; 17 (6): EE01–EE05. https://www.doi.org/10.7860/JCDR/2023/62583/18076

3. Lung cancer / Eds by K.K. Laktionov, V.V. Breder. M.: “GARNET”, 2020. (In Russian)

4. Sokolov V.V., Sokolov D.V., Pirogov S.S. et al. Modern bronchoscopic diagnosis of early central lung cancer (literature review). Medical Council. 2016; 15: 62–66. http://doi.org/10.21518/2079-701X-2016-15-62-66 (In Russian)

5. Allakhverdiev A.K., Laktionov K.K., Polotsky B.E. et al. Modern possibilities of videothoracoscopy in the practice of thoracic oncology. Bulletin of the Moscow Oncological Society. 2009; 6–8 (559). (In Russian)

6. Burdyukov M.S., Yurichev I.N., Nechipai A.M. et al. The role of fine needle puncture under the control of endoscopic ultrasonography in the morphological verification of lung cancer. Clinical and Experimental Surgery. 2015; 4: 63–72. (In Russian)

7. Tang Y., Tian S., Chen H. et al. Transbronchial lung cryobiopsy for peripheral pulmonary lesions. A narrative review. Pulmonology. 2024; 30 (5): 475–484. http://doi.org/10.1016/j.pulmoe.2023.08.010

8. Lee J.H., Saxena A., Giaccone G. Advancements in small cell lung cancer. Semin. Cancer Biol. 2023; 93: 123–128. http://doi.org/10.1016/j.semcancer.2023.05.008

9. Megyesfalvi Z., Gay C.M., Popper H. et al. Clinical insights into small cell lung cancer: Tumor heterogeneity, diagnosis, therapy, and future directions. CA Cancer J. Clin. 2023; 73 (6): 620–652. http://doi.org/10.3322/caac.21785

10. Lagkueva I.D., Chernichenko N.V., Kotlyarov P.M. et al. Diagnosis and differential diagnosis of focal lung formations. Pulmonology. 2024; 34 (4): 533–543. http://doi.org/10.18093/0869-0189-2024-34-4-533-543 (In Russian)

11. Haga A., Takahashi W., Aoki S. et al. Classification of early stage non-small cell lung cancers on computed tomographic images into histological types using radiomic features: interobserver delineation variability analysis. Radiol. Phys. Technol. 2018; 11: 27–35. https://doi.org/10.1007/s12194-017-0433-2

12. Yan M., Wang W. A non-invasive method to diagnose lung adenocarcinoma [published correction appears in Front. Oncol. 2020; 10: 1515. http://doi.org/10.3389/fonc.2020.01515]. Front. Oncol. 2020; 10: 602. http://doi.org/10.3389/fonc.2020.00602

13. Chen B.T., Chen Z., Ye N. et al. Differentiating Peripherally-Located Small Cell Lung Cancer From Non-small Cell Lung Cancer Using a CT Radiomic Approach. Front. Oncol. 2020; 10: 593. http://doi.org/10.3389/fonc.2020.00593

14. Wang J., Zhong F., Xiao F. et al. CT radiomics model combined with clinical and radiographic features for discriminating peripheral small cell lung cancer from peripheral lung adenocarcinoma. Front. Oncol. 2023; 13: 1157891. http://doi.org/10.3389/fonc.2023.1157891

15. Linning E., Lin L., Li L. et al. Radiomics for Classifying Histological Subtypes of Lung Cancer Based on Multiphasic Contrast-Enhanced Computed Tomography. J. Comput. Assist. Tomogr. 2019; 43 (2): 300–306. http://doi.org/10.1097/RCT.0000000000000836

16. Li H., Gao L., Ma H. et al. Radiomics-Based Features for Prediction of Histological Subtypes in Central Lung Cancer. Front. Oncol. 2021; 11: 658887. http://doi.org/10.3389/fonc.2021.658887

17. Qi J., Deng Z., Sun G. et al. One-step algorithm for fast-track localization and multi-category classification of histological subtypes in lung cancer. Eur. J. Radiol. 2022; 154: 110443. http://doi.org/10.1016/j.ejrad.2022.110443

18. Shah R.P., Selby H.M., Mukherjee P. et al. Machine Learning Radiomics Model for Early Identification of Small-Cell Lung Cancer on Computed Tomography Scans. JCO Clin. Cancer. Inform. 2021; 5: 746–757. http://doi.org/10.1200/CCI.21.00021

19. Liang B., Tong C., Nong J., Zhang Y. Histological subtype classification of non-small cell lung cancer with radiomics and 3D convolutional neural networks. J. Imaging Inform. Med. 2024. http://doi.org/10.1007/s10278-024-01152-4

20. Chen Z., Yi L., Peng Z. et al. Development and validation of a radiomic nomogram based on pretherapy dual-energy CT for distinguishing adenocarcinoma from squamous cell carcinoma of the lung. Front. Oncol. 2022; 12: 949111. http://doi.org/10.3389/fonc.2022.949111

21. Zhu X., Dong D., Chen Z. et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur. Radiol. 2018; 28 (7): 2772–2778. http://doi.org/10.1007/s00330-017-5221-1

22. Kuang B., Zhang J., Zhang M. et al. Advancing NSCLC pathological subtype prediction with interpretable machine learning: a comprehensive radiomics-based approach. Front. Med. (Lausanne). 2024; 11: 1413990. http://doi.org/10.3389/fmed.2024.1413990

23. Patil R., Mahadevaiah G., Dekker A. An approach toward automatic classification of tumor histopathology of non-small cell lung cancer based on radiomic features. Tomography. 2016; 2 (4): 374–377. http://doi.org/10.18383/j.tom.2016.00244

24. Liu J., Cui J., Liu F. et al. Multi-subtype classification model for non-small cell lung cancer based on radiomics: SLS model. Med Phys. 2019; 46 (7): 3091–3100. http://doi.org/10.1002/mp.13551

25.

26.