Clear Cell Renal Cell Carcinoma: Machine Learning-Based Quantitative Computed Tomography Texture Analysis for Prediction of Fuhrman Nuclear Grade

Purpose: A relevant challenge for the improvement of clear cell renal cell carcinoma management could derive from the identification of novel molecular biomarkers that could greatly improve the diagnosis, prognosis, and treatment choice of these neoplasms. In this study, we investigate whether quantitative parameters obtained from computed tomography texture analysis may correlate with the expression of selected oncogenic microRNAs. Methods: In a retrospective single-center study, multiphasic computed tomography examination (with arterial, portal, and urographic phases) was performed on 20 patients with clear cell renal cell carcinoma and computed tomography texture analysis parameters such as entropy, kurtosis, skewness, mean, and standard deviation of pixel distribution were measured using multiple filter settings. These quantitative data were correlated with the expression of selected microRNAs (miR-21-5p, miR-210-3p, miR-185-5p, miR-221-3p, miR-145-5p). Both the evaluations (microRNAs and computed tomography texture analysis) were performed on matched tumor and normal corticomedullar tissues of the same patients cohort. Results: In this pilot study, we evidenced that computed tomography texture analysis has robust parameters (eg, entropy, mean, standard deviation) to distinguish normal from pathological tissues. Moreover, a higher coefficient of determination between entropy and miR-21-5p expression was evidenced in tumor versus normal tissue. Interestingly, entropy and miR-21-5p show promising correlation in clear cell renal cell carcinoma opening to a radiogenomic strategy to improve clear cell renal cell carcinoma management. Conclusion: In this pilot study, a promising correlation between microRNAs and computed tomography texture analysis has been found in clear cell renal cell carcinoma. A clear cell renal cell carcinoma can benefit from noninvasive evaluation of texture parameters in adjunction to biopsy results. In particular, a promising correlation between entropy and miR-21-5p was found.

Download Full-text

Fuhrman nuclear grade prediction of clear cell renal cell carcinoma: influence of volume of interest delineation strategies on machine learning-based dynamic enhanced CT radiomics analysis

European Radiology ◽

10.1007/s00330-021-08322-w ◽

2021 ◽

Author(s):

Shiwei Luo ◽

Ruili Wei ◽

Songlin Lu ◽

Shengsheng Lai ◽

Jialiang Wu ◽

...

Keyword(s):

Machine Learning ◽

Renal Cell Carcinoma ◽

Cell Carcinoma ◽

Renal Cell ◽

Clear Cell ◽

Nuclear Grade ◽

Cell Renal Cell Carcinoma ◽

Grade Prediction ◽

Volume Of Interest ◽

Enhanced Ct

Download Full-text

Preoperative Predicting the WHO/ISUP Nuclear Grade of Clear Cell Renal Cell Carcinoma by Computed Tomography-Based Radiomics Features

Journal of Personalized Medicine ◽

10.3390/jpm11010008 ◽

2020 ◽

Vol 11 (1) ◽

pp. 8

Author(s):

Claudia-Gabriela Moldovanu ◽

Bianca Boca ◽

Andrei Lebovici ◽

Attila Tamas-Szora ◽

Diana Sorina Feier ◽

...

Keyword(s):

Computed Tomography ◽

Renal Cell Carcinoma ◽

Renal Cell ◽

Clear Cell ◽

Predictive Ability ◽

Nuclear Grade ◽

Training Set ◽

Cell Renal Cell Carcinoma ◽

Validation Set ◽

Sensitivity Specificity

Nuclear grade is important for treatment selection and prognosis in patients with clear cell renal cell carcinoma (ccRCC). This study aimed to determine the ability of preoperative four-phase multiphasic multidetector computed tomography (MDCT)-based radiomics features to predict the WHO/ISUP nuclear grade. In all 102 patients with histologically confirmed ccRCC, the training set (n = 62) and validation set (n = 40) were randomly assigned. In both datasets, patients were categorized according to the WHO/ISUP grading system into low-grade ccRCC (grades 1 and 2) and high-grade ccRCC (grades 3 and 4). The feature selection process consisted of three steps, including least absolute shrinkage and selection operator (LASSO) regression analysis, and the radiomics scores were developed using 48 radiomics features (10 in the unenhanced phase, 17 in the corticomedullary (CM) phase, 14 in the nephrographic (NP) phase, and 7 in the excretory phase). The radiomics score (Rad-Score) derived from the CM phase achieved the best predictive ability, with a sensitivity, specificity, and an area under the curve (AUC) of 90.91%, 95.00%, and 0.97 in the training set. In the validation set, the Rad-Score derived from the NP phase achieved the best predictive ability, with a sensitivity, specificity, and an AUC of 72.73%, 85.30%, and 0.84. We constructed a complex model, adding the radiomics score for each of the phases to the clinicoradiological characteristics, and found significantly better performance in the discrimination of the nuclear grades of ccRCCs in all MDCT phases. The highest AUC of 0.99 (95% CI, 0.92–1.00, p < 0.0001) was demonstrated for the CM phase. Our results showed that the MDCT radiomics features may play a role as potential imaging biomarkers to preoperatively predict the WHO/ISUP grade of ccRCCs.

Download Full-text