P.V. Bochkarev¹, I.A. Kuznetsov², E.S. Sirota³

1–3 Design Information Technologies Center Russian Academy of Sciences (DITC RAS) (Odintsovo, Moscow Region, Russia)    

3 I.M. Sechenov First Moscow State Medical University (Moscow, Russia)

A retrospective study examines the possibility of using radiomics in patients with localized neoplasms of the renal parenchyma, which makes it possible to extract, analyze and interpret the quantitative characteristics of 3D models of the pathological process. Visual analysis of DICOM data from multislice computed tomography with contrast (MSCT) does not allow to fully identify the morphological nature of the kidney tumor.

The article presents the quantitative characteristics of texture analysis in patients with benign and malignant neoplasms of the renal parenchyma.

Determination of the phenotype of the image of benign and malignant localized neoplasms of the renal parenchyma using texture analysis of 3D models of the pathological process.

Data describing patterns for 3 morphological forms of cancer (clear cell, papillary, chromophobic) and 2 benign tumors (angiomyolipoma, oncocytoma) of the renal parenchyma were obtained.

The use of the obtained phenotypes of images of renal parenchyma neoplasms for non-invasive diagnostics of morphology based on texture analysis of 3D models of the pathological process in patients with localized renal parenchymal neoplasms.

Bochkarev P.V., Kuznetsov I.A., Sirota E.S. Possibilities of texture analysis of 3D tumor models in patients with localized neoplasms of the renal parenchyma (pilot study). Technologies of Living Systems. 2021. V. 18. № 2. DOI: https://doi.org/10.18127/j20700997-202102-03  (in Russian).

1. Korotaeva A.A., Apanovich N.V., Braga E.A., Matveev V.B., Karpukhin A.V. Sovremennye dostizheniya v immunoterapii raka pochki. 2019. Т. 15. № 4. С. 30–38. DOI: 10.17650/1726 (in Russian).
2. Ouzaid I. Kidney cancer. Prog. en Urol. – FMC. 2017. V. 22. № 6. P. F43–F45. DOI: 10.1016/j.fpurol.2017.04.004
3. Johnson D.C. et al. Preoperatively misclassified, surgically removed benign renal masses: a systematic review of surgical series and United States population level burden estimate. J. Urol. 2015. V. 193. № 1. Р. 30–35. DOI: 10.1016/j.juro.2014.07.102
4. Hollingsworth J.M., Miller D.C., Daignault S., Hollenbeck B.K. Rising incidence of small renal masses: a need to reassess treatment effect. J. Natl. Cancer Inst. 2006. V. 98. № 18. Р. 1331–1334. DOI: 10.1093/jnci/djj362
5. Decastro G.J., McKiernan J.M. Epidemiology, clinical staging, and presentation of renal cell carcinoma. Urol. Clin. North Am. 2008.  V. 35. № 4. P. 581–592. DOI: 10.1016/j.ucl.2008.07.005
6. Frank I., Blute M.L., Cheville J.C., Lohse C.M., Weaver A.L., Zincke H. Solid renal tumors: an analysis of pathological features related to tumor size. J. Urol. 2003. V. 170. № 6. Pt 1. P. 2217–2220. DOI: 10.1097/01.ju.0000095475.12515.5e
7. Liu Z. et al. The applications of radiomics in precision diagnosis and treatment of oncology: Opportunities and challenges. Theranostics. 2019. V. 9. № 5. P. 1303–1322. DOI: 10.7150/thno.30309
8. Gill T.S. et al. Juxtatumoral perinephric fat analysis in clear cell renal cell carcinoma. Abdom. Radiol. 2019. V. 44. № 4. P. 1470–1480. DOI: 10.1007/s00261-018-1848-x
9. Kocak B. et al. Textural differences between renal cell carcinoma subtypes: Machine learning-based quantitative computed tomography texture analysis with independent external validation. Eur. J. Radiol. 2018. V. 107. P. 149–157. DOI: 10.1016/j.ejrad.2018.08.014
10. Varghese B.A. et al. Differentiation of predominantly solid enhancing lipid-poor renal cell masses by use of contrast-enhanced CT: Evaluating the role of texture in tumor subtyping. Am. J. Roentgenol. 2018. V. 211. № 6. P. W288–W296. DOI: 10.2214/AJR.18.19551 11. Deng Y. et al. CT texture analysis in the differentiation of major renal cell carcinoma subtypes and correlation with Fuhrman grade. Eur. Radiol. 2019. V. 29. № 12. P. 6922–6929. DOI: 10.1007/s00330-019-06260-2
11. Kocak B., Durmaz E.S., Ates E., Ulusan M.B. Radiogenomics in clear cell renal cell carcinoma: Machine learning–based highdimensional quantitative CT texture analysis in predicting PBRM1 mutation status. Am. J. Roentgenol. 2019. V. 212. № 3. P. W55– W63. DOI: 10.2214/AJR.18.20443
12. Lubner M.G., Smith A.D., Sandrasegaran K., Sahani D.V., Pickhardt P.J. CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges. Radiographics. 2017. V. 37(5). P. 1483-1503. DOI: 10.1148/rg.2017170056