Texture Analysis of CT Images in Differential Diagnosis of Non-Small Cell Lung Cancer

Background. In current clinical practice, the information contained in computed tomography (CT) images of lung cancer is not used to its full extent – only a few semantic characteristics (e.g. size, contours, nature of contrast agent accumulation, etc.). Today, researchers are attempting to transform CT image data into quantitative indicators describing the shape and texture of lung cancer, as well as to link these indicators with clinical data. This approach is called “radiomics” and is a developing field in medicine.
Objective: to analyze publications on differential diagnosis of non-small cell lung cancer (NSCLC) using texture analysis as well as to assess the possibilities and prospects of this method in increasing information content of CT studies.
Material and methods. The literature review presents data obtained from available sources in PubMed, ScienceDirect and Google Scholar databases, published up to and including the end of 2024, found using the key words and phrases in Russian and English languages: “NSCLC”, “lung adenocarcinoma”, “squamous cell lung cancer”, “computed tomography”, “radiomics”, “texture analysis”, “differential diagnostics”.
Results. The literature review describes the methods of texture analysis at all stages. Based on the results of the studied scientific works, the authors conclude that the use of texture analysis allows non-invasively predicting the histological form of NSCLC with sensitivity 72–83%, specificity 67–92%, and accuracy 74–86%. Conclusion. The use of texture analysis, according to published studies, is a promising method for differential diagnosis of histological forms of NSCLC (up to AUC ~0.7–0.9), however, the difference in methods and the lack of standardization of texture analysis require additional research.

1. Global Cancer Observatory: Cancer Today. International Agency for Research on Cancer. 2024. URL: https://gco.iarc.who.int/today (дата обращения 12.10.2024).

2. Shakhzadova AO, Starinsky VV, Lisichnikova IV. Cancer care to the population of Russia in 2022. Siberian Journal of Oncology. 2023; 22(5): 5–13 (in Russ). https://doi.org/10.21294/1814-4861-2023-22-5-5-13.

3. Laktionov KK, Breder VV (Eds). Lung cancer. Мoscow: Granat; 2020: 151 pp (in Russ).

4. Socinski MA, Obasaju C, Gandara D, et al. Clinicopathologic features of advanced squamous NSCLC. J Thorac Oncol. 2016; 11(9): 1411–22. https://doi.org/10.1016/j.jtho.2016.05.024.

5. Laktionov KK, Artamonova EV, Borisova TN, et al. Malignant neoplasm of the bronchi and lung: Russian clinical guidelines. Journal of Modern Oncology. 2021; 23(3): 369–402 (in Russ). https://doi.org/10.26442/18151434.2021.3.201048.

6. Han R, Arjal R, Dong J, et al. Three dimensional texture analysis of noncontrast chest CT in differentiating solitary solid lung squamous cell carcinoma from adenocarcinoma and correlation to immunohistochemical markers. Thorac Cancer. 2020; 11(11): 3099–106. https://doi.org/10.1111/1759-7714.13592.

7. Sibileva OY, Romashkina NV. Lung cancer epidemiology and the role of molecular genetic testing in the therapy of the disease (literature review). Journal of New Medical Technologies. 2023; 30(2): 92–6 (in Russ). https://doi.org/10.24412/1609-2163-2023-2-92-96.

8. Novikova SV, Vazhenin AV, Tyukov YuA. Lung cancer: epidemiology, diagnosis and prevention (literature review). Continuous Medical Education and Science. 2024; 19(4): 22–7 (in Russ).

9. Barta JA, Powell CA, Wisnivesky JP. Global epidemiology of lung cancer. Ann Glob Health. 2019; 85(1): 8. https://doi.org/10.5334/aogh.2419.

10. Cheng TYD, Cramb SM, Baade PD, et al. The international epidemiology of lung cancer: latest trends, disparities, and tumor characteristics. J Thorac Oncol. 2016; 11(10): 1653–71. https://doi.org/10.1016/j.jtho.2016.05.021.

11. Lin HT, Liu FC, Wu CY, et al. Epidemiology and survival outcomes of lung cancer: a population-based study. Biomed Res Int. 2019; 4(1): 8148156. https://doi.org/10.1155/2019/8148156.

12. Basu S, Hall LO, Goldgof D, et al. Developing a classifier model for lung tumors in CT-scan images. In: 2011 IEEE International Conference on Systems, Man, and Cybernetics, Anchorage, AK, USA, 2011, pp. 1306–12. https://doi.org/10.1109/ICSMC.2011.6083840.

13. Yu D, Zang Y, Dong D, et al. Developing a radiomics framework for classifying non-small cell lung carcinoma subtypes. In: Medical Imaging 2017: Computer-Aided Diagnosis. 2017; 10134: 570–6. https://doi.org/10.1117/12.2253923.

14. 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 Techol. 2018; 11(1): 27–35. https://doi.org/10.1007/s12194-017-0433-2.

15. 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): 2772–8. https://doi.org/10.1007/s00330-017-5221-1.

16. Bashir U, Kawa B, Siddique M, et al. Non-invasive classification of non-small cell lung cancer: a comparison between random forest models utilising radiomic and semantic features. Br J Radiol. 2019; 92(1099): 20190159. https://doi.org/10.1259/bjr.20190159.

17. Digumarthy SR, Padole AM, Gullo RL, et al. Can CT radiomic analysis in NSCLC predict histology and EGFR mutation status? Medicine. 2019; 98(1): e13963. https://doi.org/10.1097/MD.0000000000013963.

18. Linning E, Lu L, Li L, et al. Radiomics for classification of lung cancer histological subtypes based on nonenhanced computed tomography. Acad Radiol. 2019; 26(9): 1245–52. https://doi.org/10.1016/j.acra.2018.10.013.

19. Linning E, Lu 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): 300–6. https://doi.org/10.1097/RCT.0000000000000836.

20. Liu H, Jing B, Han W, et al. A comparative texture analysis based on NECT and CECT images to differentiate lung adenocarcinoma from squamous cell carcinoma. J Med Syst. 2019; 43(3): 59. https://doi.org/10.1007/s10916-019-1175-y.

21. Brunese L, Mercaldo F, Reginelli A, Santone A. Lung cancer detection and characterisation through genomic and radiomic biomarkers. In: 2020 International Joint Conference on Neural Networks. Piscataway. IEEE. 2020; 4408–15. https://doi.org/10.1109/ijcnn48605.2020.9206797.

22. Tomori Y, Yamashiro T, Tomita H, et al. CT radiomics analysis of lung cancers: differentiation of squamous cell carcinoma from adenocarcinoma, a correlative study with FDG uptake. Eur J Radiol. 2020; 128: 109032. https://doi.org/10.1016/j.ejrad.2020.109032.

23. Vuong D, Tanadini-Lang S, Wu Z, et al. Radiomics feature activation maps as a new tool for signature interpretability. Front Oncol. 2020; 10: 578895. https://doi.org/10.3389/fonc.2020.578895.

24. 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. https://doi.org/10.3389/fonc.2021.658887.

25. Marentakis P, Karaiskos P, Kouloulias V, et al. Lung cancer histology classification from CT images based on radiomics and deep learning models. Med Biol Eng Comput. 2021; 59(1): 215–26. https://doi.org/10.1007/s11517-020-02302-w.

26. Yamada M, Arimura H, Ninomiya K, Soufi M. Automated classification of histological subtypes of NSCLC using support vector machines with radiomic features. In: International Forum on Medical Imaging in Asia. 2019; 11050: 109–12. https://doi.org/10.1117/12.2521511.

27. Guo Y, Song Q, Jiang M, et al. Histological subtypes classification of lung cancers on CT images using 3D deep learning and radiomics. Acad Radiol. 2021; 28(9): e258–66. https://doi.org/10.1016/j.acra.2020.06.010.

28. Khodabakhshi Z, Mostafaei S, Arabi H, et al. Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature. Comput Biol Med. 2021; 136: 104752. https://doi.org/10.1016/j.compbiomed.2021.104752.

29. Selvam M, Sadanandan A, Chandrasekharan A, et al. Radiomics for differentiating adenocarcinoma and squamous cell carcinoma in non-small cell lung cancer beyond nodule morphology in chest CT. Sci Rep. 2024; 14(1): 32088. https://doi.org/10.1038/s41598-024-83786-6.

30. 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): 3091–100. https://doi.org/10.1002/mp.13551.

31. Wu W, Parmar C, Grossmann P, et al. Exploratory study to identify radiomics classifiers for lung cancer histology. Front Oncol. 2016; 6: 71. https://doi.org/10.3389/fonc.2016.00071.

32. Alvarez-Jimenez C, Sandino AA, Prasanna P, et al. Identifying cross-scale associations between radiomic and pathomic signatures of non-small cell lung cancer subtypes: preliminary results. Cancers. 2020; 12(12): 3663. https://doi.org/10.3390/cancers12123663.

33. Yang F, Chen W, Wei H, et al. Machine learning for histologic subtype classification of non-small cell lung cancer: a retrospective multicenter radiomics study. Front Oncol. 2021; 10: 608598. https://doi.org/10.3389/fonc.2020.608598.

34. Hershman M, Yousefi B, Serletti L, et al. Impact of interobserver variability in manual segmentation of nonsmall cell lung cancer (NSCLC) applying low-rank radiomic representation on computed tomography. Cancers. 2021; 13(23): 5985. https://doi.org/10.3390/cancers13235985.

35. Chen X, Fang M, Dong D, et al. A radiomics signature in preoperative predicting degree of tumor differentiation in patients with non-small cell lung cancer. Acad Radiol. 2018; 25(12): 1548–55. https://doi.org/10.1016/j.acra.2018.02.019.

36. Gharraf HS, Mehana SM, ElNagar MA. Role of CT in differentiation between subtypes of lung cancer; is it possible? Egypt J Bronchol. 2020; 14: 1–7. https://doi.org/10.1186/s43168-020-00027-w.

37. Zhang S (Ed). Diagnostic imaging of lung cancers. Springer; 2024: 3–49. https://doi.org/10.1007/978-981-99-6815-2_1.

38. Tang X, Wu J, Liang J, et al. The value of combined PET/MRI, CT and clinical metabolic parameters in differentiating lung adenocarcinoma from squamous cell carcinoma. Front Oncol. 2022; 12: 991102. https://doi.org/10.3389/fonc.2022.991102.

39. Miles KA. How to use CT texture analysis for prognostication of non-small cell lung cancer. Cancer Imaging. 2016; 16: 10. https://doi.org/10.1186/s40644-016-0065-5.

40. Hassani C, Varghese BA, Nieva J, Duddalwar V. Radiomics in pulmonary lesion imaging. Am J Roentgenol. 2019; 212(3): 497–504. https://doi.org/10.2214/AJR.18.20623.

41. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016; 278(2): 563–77. https://doi.org/10.1148/radiol.2015151169.

42. Ji Y, Qiu Q, Fu J, et al. Stage-specific PET radiomic prediction model for the histological subtype classification of non-smallcell lung cancer. Cancer Manag Res. 2021; 13: 307–17. https://doi.org/10.2147/CMAR.S287128.

43. Ge G, Zhang J. Feature selection methods and predictive models in CT lung cancer radiomics. J Appl Clin Med Phys. 2023; 24(1): e13869. https://doi.org/10.1002/acm2.13869.

44. Yip SSF, Liu Y, Parmar C, et al. Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer. Sci Rep. 2017; 7(1): 3519. https://doi.org/10.1038/s41598-017-02425-5.

45. 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): 374–7. https://doi.org/10.18383/j.tom.2016.00244.

46. Varghese BA, Cen SY, Hwang DH, Duddalwar VA. Texture analysis of imaging: what radiologists need to know. Am J Roentgenol. 2019; 212(3): 520–8. https://doi.org/10.2214/AJR.18.20624.

47. Wu YJ, Wu FZ, Yang SC, et al. Radiomics in early lung cancer diagnosis: from diagnosis to clinical decision support and education. Diagnostics. 2022; 12(5): 1064. https://doi.org/10.3390/diagnostics12051064.

48. Fornacon-Wood I, Faivre-Finn C, O'Connor JPB, Price GJ. Radiomics as a personalized medicine tool in lung cancer: separating the hope from the hype. Lung Cancer. 2020; 146: 197–208. https://doi.org/10.1016/j.lungcan.2020.05.028.

49. Ganeshan B, Abaleke S, Young RCD, et al. Texture analysis of non-small cell lung cancer on unenhanced computed tomography: initial evidence for a relationship with tumour glucose metabolism and stage. Cancer Imaging. 2010; 10(1): 137–43. https://doi.org/10.1102/1470-7330.2010.0021.

50. Zhao B, Tan Y, Tsai WY, et al. Reproducibility of radiomics for deciphering tumor phenotype with imaging. Sci Rep. 2016; 6(1): 23428. https://doi.org/10.1038/srep23428.

51. Raptis S, Ilioudis C, Theodorou K. Uncovering the diagnostic power of radiomic feature significance in automated lung cancer detection: an integrative analysis of texture, shape, and intensity contributions. BioMedInformatics. 2024; 4(4): 2400–25. https://doi.org/10.3390/biomedinformatics4040129.

52. Han F, Wang H, Zhang G, et al. Texture feature analysis for computer-aided diagnosis on pulmonary nodules. J Digit Imaging. 2015; 28(1): 99–115. https://doi.org/10.1007/s10278-014-9718-8.