Texture analysis of CT- and MR-Images in the differential diagnosis of renal cell carcinoma: a review

Abstract

INTRODUCTION: Renal cell carcinoma (RCC) is a heterogeneous group of diseases. The most common type of RCC is clear cell RCC. Tumor biopsy is the «gold» standard for verifying the diagnosis, however, it can be unsatisfactory due to the characteristic heterogeneity of the RCC structure. Non-invasive diagnostic methods — computed tomography and magnetic resonance imaging — in combination with the use of texture analysis can potentially provide a large amount of information about the structure of the kidney tumor and the presumed degree of its differentiation (grade).OBJECTIVE: Тo analyze publications devoted to texture analysis in RCC, the possibilities and prospects of using this method to increase the information content of CT and MR studies.MATERIALS AND METHODS: Our review presents data obtained from available sources PubMed, Scopus and Web of Science, published up to March 2022 inclusive, found using the keywords: renal cell carcinoma, CT, MRI, texture analysis, radiomics in Russian and English.RESULTS: The literature review describes the methods of texture analysis: selection of the region of interest, modality and contrast phase of the study, diagnostic aim. Based on the results of published scientific papers, the authors conclude that the use of texture analysis makes it possible to predict the grade of RCC with high sensitivity, specificity and accuracy, as well as to make a differential diagnosis of RCC with other kidney neoplasias, primarily lipid poor angiomyolipomas.CONCLUSION: The use of texture analysis based on published materials is extremely promising for non-invasive prediction of RCC grade and its differential diagnosis, however, the difference in methods and the lack of standardization of texture analysis requires additional research.