A new approach to identifying reproducible and accurate radiomic features based on computed tomography data

Purpose of the study: The aim of this study is to identify radiomic features that are invariant to segmentation variability, and to evaluate their ability to differentiate between benign and malignant lesions.

Materials and methods. 64 CT studies from the LIDC/IDRI database were selected to search for features invariant to segmentation variability. The existing segmentations of 64 LIDC/IDRI studies was supplemented with segmentations by radiologists from the Moscow Center for Diagnostics and Telemedicine, performed using a semi-automatic method (3D sphere). For the first 10 studies, manual segmentation (contour brush) was also additionally performed to compare the time of segmentation. On an unrelated WORC GIST dataset, segmentation-invariant features were evaluated in terms of “benign lesion-malignant lesion.”

Results. The study identified 7 radiomic features invariant to segmentation variability for computed tomography studies that showed discriminatory ability for the binary classification task “benign formation-malignant formation” on different dataset.

Conclusion. The identified features can be taken into account in the further development of the radiomic model. Semi-automatic annotation can significantly reduce the time required to obtain a mask of the region of interest for further radiomic analysis.

1. Bray F., Laversanne M., Sung H. et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 2024; 74 (3): 229–263. https://doi.org/10.3322/caac.21834

2. Zheng X., He B., Hu Y. et al. Diagnostic accuracy of deep learning and radiomics in lung cancer staging: a systematic review and meta-analysis. Frontiers in Public Health. 2022; 10: 938113. https://doi.org/10.3389/fpubh.2022.938113

3. Chen M., Copley S. J., Viola P. et al. Radiomics and artificial intelligence for precision medicine in lung cancer treatment. Semin. Cancer Biol. 2023; 93: 97–113. https://doi.org/10.1016/j.semcancer.2023.05.004

4. Certificate for state registration of computer software No. 2023618319, the Russian Federation. Modul' ocenki diagnosticheskogo kachestva komp'yuternoj tomografii organov grudnoj kletki [Software module for assessing the diagnostic quality of chest computed tomography images]: No. 2023617139 : submitted 13.04.2023 : published 21.04.2023 / Yu.A. Vasilev, A.V. Vladzymyrskyy, O.V. Omelyanskaya [et al.]; submitter Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department (In Russian)

5. Kontrol' i standartizaciya dannyh pri kolichestvennoj komp'yuternoj tomografii : Metodicheskie rekomendacii [Curation and standardization of data in quantitative computed tomography: Best practices] / K.A. Sergunova, A.V. Petraikin, A.V. Smirnov [et al.]. – State Budget-Funded Health Care Institution of the City of Moscow "Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department", 2019. 28 p. (Luchshie praktiki luchevoj i instrumental'noj diagnostiki [Best practices in medical imaging]; 71). (In Russian)

6. Fusco R., Granata V., Simonetti I. et al. An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies. Curr. Oncol. 2024; 31 (1): 403–424. https://doi.org/10.3390/curroncol31010027

7. Artificial intelligence in radiology: Per Aspera Ad Astra Vasilev Y.A., Vladzymyrskyy A.V. (Eds.) [Iskusstvennyy intellekt v luchevoy diagnostike: Per Aspera Ad Astra]. M.: Izdatelskie resheniya, 2025. 491 p. (In Russian)

8. Park C.M. Can Artificial Intelligence Fix the Reproducibility Problem of Radiomics? Radiology. 2019; 292 (2): 374–375. https://doi.org/10.1148/radiol.2019191154

9. Wu L., Lou X., Kong N. et al. Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? A systematic review. Eur. Radiol. 2023; 33 (3): 2105–2117. https://doi.org/10.1007/s00330-022-09174-8

10. Kodenko M.R., Vladzimirskij A.V., Omelyanskaya O.V. et al. Optimization of opportunistic computed tomography screening for abdominal aortic aneurysms using artificial intelligence: prospects and challenges (literature review). Complex problems of cardiovascular diseases. 2024; 13(4): 204–213. https://doi.org/10.17802/2306-1278-2024-13-4-204-213 (In Russian)

11. Woznicki P., Laqua F. C., Al-Haj A. et al. Addressing challenges in radiomics research: systematic review and repository of open-access cancer imaging datasets. Insights Imaging. 2023; 14 (1): 216. https://doi.org/10.1186/s13244-023-01556-w

12. Fedorov A., Hancock M., Clunie D. et al. DICOM re‐encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules. Med. Physics. 2020; 47 (11): 5953–5965 https://doi.org/10.1002/mp.14445

13. Armato III S.G., McLennan G., Bidaut L. et al. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans. Med. Physics. 2011; 38 (2): 915–931. https://doi.org/10.1118/1.3528204

14. Starmans M.P.A., Timbergen M.J.M., Vos M. et al. The WORC database: MRI and CT scans, segmentations, and clinical labels for 930 patients from six radiomics studies. Oncology. 2021: 2021–2008. https://doi.org/10.1101/2021.08.19.21262238

15. Pyradiomics documentation. Available at https://pyradiomics.readthedocs.io/en/latest/ (Accessed on 26 August 2025).

16. Van Griethuysen J.J., Fedorov A., Parmar C. et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77 (21): e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339

17. IBSI 1 – IBSI – Image Biomarker Standardisation Initiative Available at https://theibsi.github.io/ibsi1/ (Accessed on 26 August 2025).

18. IBSI 2 – IBSI – Image Biomarker Standardisation Initiative Available at https://theibsi.github.io/ibsi2/ (Accessed on 26 August 2025).

19. Shur J.D., Doran S.J., Kumar S. et al. Radiomics in Oncology: A Practical Guide. RadioGraphics. 2021; 41 (6): 1717–1732. https://doi.org/10.1148/rg.2021210037

20. Rizzo S., Botta F., Raimondi S. et al. Radiomics: the facts and the challenges of image analysis. Eur. Radiol. 2018; 2 (1): 36. https://doi.org/10.1186/s41747-018-0068-z

21. Zwanenburg A., Vallières M., Abdalah M.A. et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020; 295 (2): 328–338. https://doi.org/10.1148/radiol.2020191145

22. Liu J., Corti A., Corino V.D., Mainardi L. Lung nodule classification using radiomics model trained on degraded SDCT images. Comput. Methods Programs Biomed. 2024; 257: 108474. https://doi.org/10.1016/j.cmpb.2024.108474

23. Liu C., He Y., Luo J. The influence of image selection and segmentation on the extraction of lung cancer imaging radiomics features using 3D-Slicer software. BMC Cancer. 2025; 25 (1): 728. https://doi.org/10.1186/s12885-025-14094-z

24. Wu L., Lou X., Kong N. et al. Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? A systematic review. Eur. Radiol. 2023; 33 (3): 2105–2117. https://doi.org/10.1007/s00330-022-09174-8

25. Zhang Y., Feng H., Zhao Y., Zhang S. Exploring the Application of the Artificial-Intelligence-Integrated Platform 3D Slicer in Medical Imaging Education. Diagnostics. 2024; 14 (2): 146. https://doi.org/10.3390/diagnostics14020146

26. Amla Z., Khehra P. S., Mathialagan A., Lugez E. Review of the free research software for computer-assisted interventions. J. Imaging Inform. Med. 2024; 37 (1), 386–401. https://doi.org/10.1007/s10278-023-00912-y

27. Vasilev Yu.A., Romanenko M.O., Kodenko M.R. et al. Manual segmentation methods of biparametric prostate MRI: which should be preferred for texture analysis? Bulletin of Russian Scientific Center of Roentgenoradiology. 2025; 2025(4):24–37. https://doi.org/10.24412/1999-7264-2025-4-24-37 (In Russian)