Advances and controversies in grading and staging of renal cell carcinoma

Multiphase comparative study for WHO/ISUP nuclear grading diagnostic model based on enhanced CT images of clear cell renal cell carcinoma

To compare and analyze the diagnostic value of different enhancement stages in distinguishing low and high nuclear grade clear cell renal cell carcinoma (ccRCC) based on enhanced computed tomography (CT) images by building machine learning classifiers. A total of 51 patients (Dateset1, including 41 low-grade and 10 high-grade) and 27 patients (Independent Dateset2, including 16 low-grade and 11 high-grade) with pathologically proven ccRCC were enrolled in this retrospective study. Radiomic features were extracted from the corticomedullary phase (CMP), nephrographic phase (NP), and excretory phase (EP) CT images, and selected using the recursive feature elimination cross-validation (RFECV) algorithm, the group differences were assessed using T-test and Mann-Whitney U test for continuous variables. The support vector machine (SVM), random forest (RF), XGBoost (XGB), VGG11, ResNet18, and GoogLeNet classifiers are established to distinguish low-grade and high-grade ccRCC. The classifiers based on CT images of NP (Dateset1, RF: AUC = 0.82 ± 0.05, ResNet18: AUC = 0.81 ± 0.02; Dateset2, XGB: AUC = 0.95 ± 0.02, ResNet18: AUC = 0.87 ± 0.07) obtained the best performance and robustness in distinguishing low-grade and high-grade ccRCC, while the EP-based classifier performance in poorer results. The CT images of enhanced phase NP had the best performance in diagnosing low and high nuclear grade ccRCC. Firstorder_Kurtosis and firstorder_90Percentile feature play a vital role in the classification task.

Radiomics Machine Learning Analysis of Clear Cell Renal Cell Carcinoma for Tumour Grade Prediction Based on Intra-Tumoural Sub-Region Heterogeneity

BACKGROUND

Renal cancers are among the top ten causes of cancer-specific mortality, of which the ccRCC subtype is responsible for most cases. The grading of ccRCC is important in determining tumour aggressiveness and clinical management.

OBJECTIVES

The objectives of this research were to predict the WHO/ISUP grade of ccRCC pre-operatively and characterise the heterogeneity of tumour sub-regions using radiomics and ML models, including comparison with pre-operative biopsy-determined grading in a sub-group.

METHODS

Data were obtained from multiple institutions across two countries, including 391 patients with pathologically proven ccRCC. For analysis, the data were separated into four cohorts. Cohorts 1 and 2 included data from the respective institutions from the two countries, cohort 3 was the combined data from both cohort 1 and 2, and cohort 4 was a subset of cohort 1, for which both the biopsy and subsequent histology from resection (partial or total nephrectomy) were available. 3D image segmentation was carried out to derive a voxel of interest (VOI) mask. Radiomics features were then extracted from the contrast-enhanced images, and the data were normalised. The Pearson correlation coefficient and the XGBoost model were used to reduce the dimensionality of the features. Thereafter, 11 ML algorithms were implemented for the purpose of predicting the ccRCC grade and characterising the heterogeneity of sub-regions in the tumours.

RESULTS

For cohort 1, the 50% tumour core and 25% tumour periphery exhibited the best performance, with an average AUC of 77.9% and 78.6%, respectively. The 50% tumour core presented the highest performance in cohorts 2 and 3, with average AUC values of 87.6% and 76.9%, respectively. With the 25% periphery, cohort 4 showed AUC values of 95.0% and 80.0% for grade prediction when using internal and external validation, respectively, while biopsy histology had an AUC of 31.0% for the classification with the final grade of resection histology as a reference standard. The CatBoost classifier was the best for each of the four cohorts with an average AUC of 80.0%, 86.5%, 77.0% and 90.3% for cohorts 1, 2, 3 and 4 respectively.

CONCLUSIONS

Radiomics signatures combined with ML have the potential to predict the WHO/ISUP grade of ccRCC with superior performance, when compared to pre-operative biopsy. Moreover, tumour sub-regions contain useful information that should be analysed independently when determining the tumour grade. Therefore, it is possible to distinguish the grade of ccRCC pre-operatively to improve patient care and management.

Nomogram combining pre-operative clinical characteristics and spectral CT parameters for predicting the WHO/ISUP pathological grading in clear cell renal cell carcinoma

PURPOSE

To develop a novel clinical-spectral-computed tomography (CT) nomogram incorporating clinical characteristics and spectral CT parameters for the preoperative prediction of the WHO/ISUP pathological grade in clear cell renal cell carcinoma (ccRCC).

METHODS

Seventy-three ccRCC patients who underwent spectral CT were included in this retrospective analysis from December 2020 to June 2023. The subjects were pathologically divided into low- and high-grade groups (WHO/ISUP 1/2, n = 52 and WHO/ISUP 3/4, n = 21, respectively). Information on clinical characteristics, conventional CT imaging features, and spectral CT parameters was collected. Multivariate logistic regression analyses were conducted to create a nomogram combing clinical data and image data for preoperatively predicting the pathological grade of ccRCC, and the area under the curve (AUC) was utilized to assess the predictive performance of the model.

RESULTS

Multivariate logistic regression analyses revealed that age, systemic immune-inflammation index (SII), and the slope of the spectrum curve in the cortex phase (CP-K) were independent predictors for predicting high-grade ccRCC. The clinical-spectral-CT model exhibited high evaluation efficacy, with an AUC of 0.933 (95% confidence interval [CI]: 0.878-0.998; sensitivity: 0.810; specificity: 0.923). The calibration curve revealed that the predicted probability of the clinical-spectral-CT nomogram could better fit the actual probability, with high calibration. The Hosmer-Lemeshow test showed that the model had a good fitness (χ2 = 5.574, p = 0.695).

CONCLUSION

The clinical-spectral-CT nomogram has the potential to predict WHO/ISUP grading of ccRCC preoperatively.

PNI as a Potential Add-On Biomarker to Improve the IMDC Intermediate Prognostic Score

INTRODUCTION

This study aimed to assess the role of the adjusted PNI-IMDC risk scoring system in stratifying the intermediate group of metastatic RCC patients who received TKIS in the first-line setting.

METHODS

A total of 185 patients were included. The adjusted PNI and IMDC model was used to divide the intermediate group into two groups: intermediate PNI-high and intermediate PNI-low groups. The statistical data were analyzed using Kaplan-Meier and Cox regression analysis.

RESULTS

The results showed that the adjusted PNI-IMDC risk score, classic IMDC, and PNI had similar prognostic values. Adjusted PNI-IMDC risk score might be used for a more homogeneous differentiation of the classic intermediate group. On the other hand, multivariate analysis revealed that the presence of nephrectomy, adjusted favorable/intermediate (PNI-high) group, ECOG performance score, and presence of bone metastasis were independent predictors of OS.

CONCLUSIONS

Pre-treatment PNI, as a valuable and potential add-on biomarker to the adjusted PNI-IMDC classification model, can be helpful for establishing an improved prognostic model for intermediate group mRCC patients treated with first-line TKISs. Further validation studies are needed to clarify these findings.

A Weakly Supervised Deep Learning Model and Human-Machine Fusion for Accurate Grading of Renal Cell Carcinoma from Histopathology Slides

(1) Background: The Fuhrman grading (FG) system is widely used in the management of clear cell renal cell carcinoma (ccRCC). However, it is affected by observer variability and irreproducibility in clinical practice. We aimed to use a deep learning multi-class model called SSL-CLAM to assist in diagnosing the FG status of ccRCC patients using digitized whole slide images (WSIs). (2) Methods: We recruited 504 eligible ccRCC patients from The Cancer Genome Atlas (TCGA) cohort and obtained 708 hematoxylin and eosin-stained WSIs for the development and internal validation of the SSL-CLAM model. Additionally, we obtained 445 WSIs from 188 ccRCC eligible patients in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort as an independent external validation set. A human-machine fusion approach was used to validate the added value of the SSL-CLAM model for pathologists. (3) Results: The SSL-CLAM model successfully diagnosed the five FG statuses (Grade-0, 1, 2, 3, and 4) of ccRCC, and achieved AUCs of 0.917 and 0.887 on the internal and external validation sets, respectively, outperforming a junior pathologist. For the normal/tumor classification (Grade-0, Grade-1/2/3/4) task, the SSL-CLAM model yielded AUCs close to 1 on both the internal and external validation sets. The SSL-CLAM model achieved a better performance for the two-tiered FG (Grade-0, Grade-1/2, and Grade-3/4) task, with AUCs of 0.936 and 0.915 on the internal and external validation sets, respectively. The human-machine diagnostic performance was superior to that of the SSL-CLAM model, showing promising prospects. In addition, the high-attention regions of the SSL-CLAM model showed that with an increasing FG status, the cell nuclei in the tumor region become larger, with irregular contours and increased cellular pleomorphism. (4) Conclusions: Our findings support the feasibility of using deep learning and human-machine fusion methods for FG classification on WSIs from ccRCC patients, which may assist pathologists in making diagnostic decisions.

Application of digital pathology and machine learning in the liver, kidney and lung diseases

The development of rapid and accurate Whole Slide Imaging (WSI) has paved the way for the application of Artificial Intelligence (AI) to digital pathology. The availability of WSI in the recent years allowed the rapid development of various AI technologies to blossom. WSI-based digital pathology combined with neural networks can automate arduous and time-consuming tasks of slide evaluation. Machine Learning (ML)-based AI has been demonstrated to outperform pathologists by eliminating inter- and intra-observer subjectivity, obtaining quantitative data from slide images, and extracting hidden image patterns that are relevant to disease subtype and progression. In this review, we outline the functionality of different AI technologies such as neural networks and deep learning and discover how aspects of different diseases make them benefit from the implementation of AI. AI has proven to be valuable in many different organs, with this review focusing on the liver, kidney, and lungs. We also discuss how AI and image analysis not only can grade diseases objectively but also discover aspects of diseases that have prognostic value. In the end, we review the current status of the integration of AI in pathology and share our vision on the future of digital pathology.

CD70-Targeted Micelles Enhance HIF2α siRNA Delivery and Inhibit Oncogenic Functions in Patient-Derived Clear Cell Renal Carcinoma Cells

The majority of clear cell renal cell carcinomas (ccRCCs) are characterized by mutations in the Von Hippel−Lindau (VHL) tumor suppressor gene, which leads to the stabilization and accumulation of the HIF2α transcription factor that upregulates key oncogenic pathways that promote glucose metabolism, cell cycle progression, angiogenesis, and cell migration. Although FDA-approved HIF2α inhibitors for treating VHL disease-related ccRCC are available, these therapies are associated with significant toxicities such as anemia and hypoxia. To improve ccRCC-specific drug delivery, peptide amphiphile micelles (PAMs) were synthesized incorporating peptides targeted to the CD70 marker expressed by ccRCs and anti-HIF2α siRNA, and the ability of HIF2α-CD27 PAMs to modulate HIF2α and its downstream targets was evaluated in human ccRCC patient-derived cells. Cell cultures were derived from eight human ccRCC tumors and the baseline mRNA expression of HIF2A and CD70, as well as the HIF2α target genes SLC2A1, CCND1, VEGFA, CXCR4, and CXCL12 were first determined. As expected, each gene was overexpressed by at least 63% of all samples compared to normal kidney proximal tubule cells. Upon incubation with HIF2α-CD27 PAMs, a 50% increase in ccRCC-binding was observed upon incorporation of a CD70-targeting peptide into the PAMs, and gel shift assays demonstrated the rapid release of siRNA (>80% in 1 h) under intracellular glutathione concentrations, which contributed to ~70% gene knockdown of HIF2α and its downstream genes. Further studies demonstrated that knockdown of the HIF2α target genes SLC2A1, CCND1, VEGFA, CXCR4, and CXCL12 led to inhibition of their oncogenic functions of glucose transport, cell proliferation, angiogenic factor release, and cell migration by 50−80%. Herein, the development of a nanotherapeutic strategy for ccRCC-specific siRNA delivery and its potential to interfere with key oncogenic pathways is presented.

Usefulness of computed tomography textural analysis in renal cell carcinoma nuclear grading

Purpose: To evaluate the usefulness of computed tomography (CT) texture descriptors integrated with machine-learning (ML) models in the identification of clear cell renal cell carcinoma (ccRCC) and for the first time papillary renal cell carcinoma (pRCC) tumor nuclear grades [World Health Organization (WHO)/International Society of Urologic Pathologists (ISUP) 1, 2, 3, and 4]. Approach: A total of 143 ccRCC and 21 pRCC patients were analyzed in this study. Texture features were extracted from late arterial phase CT images. A complete separation of training/validation and testing subsets from the beginning to the end of the pipeline was adopted. Feature dimension was reduced by collinearity analysis and Gini impurity-based feature selection. The synthetic minority over-sampling technique was employed for imbalanced datasets. The ML classifiers were logistic regression, SVM, RF, multi-layer perceptron, and K -NN. The differentiation between low grades/ high grades, grade 1/grade 2, grade 3/grade 4, and between all grades was assessed for ccRCC and pRCC datasets. The classification performance was assessed and compared by certain metrics. Results: Textures-based classifiers were able to efficiently identify ccRCC and pRCC grades. An accuracy and area under the characteristic operating curve (AUC) up to 91%/0.9, 91%/0.9, 90%/0.9, and 88%/1 were reached when discriminating ccRCC low grades/ high grades, grade 1/grade 2, grade 3/grade 4, and all grades, respectively. An accuracy and AUC up to 96%/1, 81%/0.8, 86%/0.9, and 88%/0.9 were found when differentiating pRCC low grades/ high grades, grade 1/grade 2, grade 3/grade 4, and all grades, respectively. Conclusion: CT texture-based ML models can be used to assist radiologist in predicting the WHO/ISUP grade of ccRCC and pRCC pre-operatively.

Prognostic nutritional index as a prognostic factor for renal cell carcinoma: A systematic review and meta-analysis

Background

Prognostic nutritional index (PNI) is a simple parameter which reflects patient’s nutritional and inflammatory status and reported as a prognostic factor for renal cell carcinoma (RCC). Studies were included from database inception until February 2, 2022. The aim of this study is to evaluate prognostic value of PNI by meta-analysis of the diagnostic test accuracy in RCC.

Methods and findings

Studies were retrieved from PubMed, Cochrane, and EMBASE databases and assessed sensitivity, specificity, summary receiver operating characteristic curve (SROC) and area under curve (AUC). Totally, we identified 11 studies with a total of 7,296 patients were included to evaluate the prognostic value of PNI in RCC finally. They indicated a pooled sensitivity of 0.733 (95% CI, 0.651–0.802), specificity of 0.615 (95% CI, 0.528–0.695), diagnostic odds ratio (DOR) of 4.382 (95% CI, 3.148–6.101) and AUC of 0.72 (95% CI, 0.68–0.76). Heterogeneity was significant and univariate meta-regression revealed that metastasis and cut-off value of PNI might be the potential source of heterogeneity. Multivariate meta-regression analysis also demonstrated that metastasis might be the source of heterogeneity.

Conclusions

PNI demonstrated a good diagnostic accuracy as a prognostic factor for RCC and especially in case of metastatic RCC.

Deep Learning Using CT Images to Grade Clear Cell Renal Cell Carcinoma: Development and Validation of a Prediction Model

Simple Summary

Clear cell renal cell carcinoma (ccRCC) pathologic grade identification is essential to both monitoring patients’ conditions and constructing individualized subsequent treatment strategies. However, biopsies are typically used to obtain the pathological grade, entailing tremendous physical and mental suffering as well as heavy economic burden, not to mention the increased risk of complications. Our study explores a new way to provide grade assessment of ccRCC on the basis of the individual’s appearance on CT images. A deep learning (DL) method that includes self-supervised learning is constructed to identify patients with high grade for ccRCC. We confirmed that our grading network can accurately differentiate between different grades of CT scans of ccRCC patients using a cohort of 706 patients from West China Hospital. The promising diagnostic performance indicates that our DL framework is an effective, non-invasive and labor-saving method for decoding CT images, offering a valuable means for ccRCC grade stratification and individualized patient treatment.

Abstract

This retrospective study aimed to develop and validate deep-learning-based models for grading clear cell renal cell carcinoma (ccRCC) patients. A cohort enrolling 706 patients (n = 706) with pathologically verified ccRCC was used in this study. A temporal split was applied to verify our models: the first 83.9% of the cases (years 2010–2017) for development and the last 16.1% (year 2018–2019) for validation (development cohort: n = 592; validation cohort: n = 114). Here, we demonstrated a deep learning(DL) framework initialized by a self-supervised pre-training method, developed with the addition of mixed loss strategy and sample reweighting to identify patients with high grade for ccRCC. Four types of DL networks were developed separately and further combined with different weights for better prediction. The single DL model achieved up to an area under curve (AUC) of 0.864 in the validation cohort, while the ensembled model yielded the best predictive performance with an AUC of 0.882. These findings confirms that our DL approach performs either favorably or comparably in terms of grade assessment of ccRCC with biopsies whilst enjoying the non-invasive and labor-saving property.

Long Non-Coding RNAs as Novel Biomarkers in the Clinical Management of Papillary Renal Cell Carcinoma Patients: A Promise or a Pledge?

Papillary renal cell carcinoma (pRCC) represents the second most common subtype of renal cell carcinoma, following clear cell carcinoma and accounting for 10–15% of cases. For around 20 years, pRCCs have been classified according to their mere histopathologic appearance, unsupported by genetic and molecular evidence, with an unmet need for clinically relevant classification. Moreover, patients with non-clear cell renal cell carcinomas have been seldom included in large clinical trials; therefore, the therapeutic landscape is less defined than in the clear cell subtype. However, in the last decades, the evolving comprehension of pRCC molecular features has led to a growing use of target therapy and to better oncological outcomes. Nonetheless, a reliable molecular biomarker able to detect the aggressiveness of pRCC is not yet available in clinical practice. As a result, the pRCC correct prognosis remains cumbersome, and new biomarkers able to stratify patients upon risk of recurrence are strongly needed. Non-coding RNAs (ncRNAs) are functional elements which play critical roles in gene expression, at the epigenetic, transcriptional, and post-transcriptional levels. In the last decade, ncRNAs have gained importance as possible biomarkers for several types of diseases, especially in the cancer universe. In this review, we analyzed the role of long non-coding RNAs (lncRNAs) in the prognosis of pRCC, with a particular focus on their networking. In fact, in the competing endogenous RNA hypothesis, lncRNAs can bind miRNAs, resulting in the modulation of the mRNA levels targeted by the sponged miRNA, leading to additional regulation of the target gene expression and increasing complexity in the biological processes.

Renal Oncocytoma: The Diagnostic Challenge to Unmask the Double of Renal Cancer

Renal oncocytoma represents the most common type of benign neoplasm that is an increasing concern for urologists, oncologists, and nephrologists due to its difficult differential diagnosis and frequent overtreatment. It displays a variable neoplastic parenchymal and stromal architecture, and the defining cellular element is a large polygonal, granular, eosinophilic, mitochondria-rich cell known as an oncocyte. The real challenge in the oncocytoma treatment algorithm is related to the misdiagnosis due to its resemblance, at an initial radiological assessment, to malignant renal cancers with a completely different prognosis and medical treatment. Unfortunately, percutaneous renal biopsy is not frequently performed due to the possible side effects related to the procedure. Therefore, the majority of oncocytoma are diagnosed after the surgical operation via partial or radical nephrectomy. For this reason, new reliable strategies to solve this issue are needed. In our review, we will discuss the clinical implications of renal oncocytoma in daily clinical practice with a particular focus on the medical diagnosis and treatment and on the potential of novel promising molecular biomarkers such as circulating microRNAs to distinguish between a benign and a malignant lesion.

Potential Clinical Value of Pretreatment De Ritis Ratio as a Prognostic Biomarker for Renal Cell Carcinoma

Background

We performed this study to explore the prognostic value of the pretreatment aspartate transaminase to alanine transaminase (De Ritis) ratio in patients with renal cell carcinoma (RCC).

Methods

PubMed, EMBASE, Web of Science, and Cochrane Library were searched to identify all studies. The hazard ratio (HR) with a 95% confidence interval (CI) for overall survival (OS) and cancer-specific survival (CSS) were extracted to evaluate their correlation.

Results

A total of 6,528 patients from 11 studies were included in the pooled analysis. Patients with a higher pretreatment De Ritis ratio had worse OS (HR = 1.41, p < 0.001) and CSS (HR = 1.59, p < 0.001). Subgroup analysis according to ethnicity, disease stage, cutoff value, and sample size revealed that the De Ritis ratio had a significant prognostic value for OS and CSS in all subgroups.

Conclusions

The present study suggests that an elevated pretreatment De Ritis ratio is significantly correlated with worse survival in patients with RCC. The pretreatment De Ritis ratio may serve as a potential prognostic biomarker in patients with RCC, but further studies are warranted to support these results.

MRI-Based Grading of Clear Cell Renal Cell Carcinoma Using a Machine Learning Classifier

Objective

To develop a machine learning (ML)-based classifier for discriminating between low-grade (ISUP I-II) and high-grade (ISUP III-IV) clear cell renal cell carcinomas (ccRCCs) using MRI textures.

Materials and Methods

We retrospectively evaluated a total of 99 patients (with 61 low-grade and 38 high-grade ccRCCs), who were randomly divided into a training set (n = 70) and a validation set (n = 29). Regions of interest (ROIs) of all tumors were manually drawn three times by a radiologist at the maximum lesion level of the cross-sectional CMP sequence images. The quantitative texture analysis software, MaZda, was used to extract texture features, including histograms, co-occurrence matrixes, run-length matrixes, gradient models, and autoregressive models. Reproducibility of the texture features was assessed with the intra-class correlation coefficient (ICC). Features were chosen based on their importance coefficients in a random forest model, while the multi-layer perceptron algorithm was used to build a classifier on the training set, which was later evaluated with the validation set.

Results

The ICCs of 257 texture features were equal to or higher than 0.80 (0.828–0.998. Six features, namely Kurtosis, 135dr_RLNonUni, Horzl_GLevNonU, 135dr_GLevNonU, S(4,4)Entropy, and S(0,5)SumEntrp, were chosen to develop the multi-layer perceptron classifier. A three-layer perceptron model, which has 229 nodes in the hidden layer, was trained on the training set. The accuracy of the model was 95.7% with the training set and 86.2% with the validation set. The areas under the receiver operating curves were 0.997 and 0.758 for the training and validation sets, respectively.

Conclusions

A machine learning-based grading model was developed that can aid in the clinical diagnosis of clear cell renal cell carcinoma using MRI images.

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

OBJECTIVE

To investigate the influence of different volume of interest (VOI) delineation strategies on machine learning-based predictive models for discrimination between low and high nuclear grade clear cell renal cell carcinoma (ccRCC) on dynamic contrast-enhanced CT.

METHODS

This study retrospectively collected 177 patients with pathologically proven ccRCC (124 low-grade; 53 high-grade). Tumor VOI was manually segmented, followed by artificially introducing uncertainties as: (i) contour-focused VOI, (ii) margin erosion of 2 or 4 mm, and (iii) margin dilation (2, 4, or 6 mm) inclusive of perirenal fat, peritumoral renal parenchyma, or both. Radiomics features were extracted from four-phase CT images (unenhanced phase (UP), corticomedullary phase (CMP), nephrographic phase (NP), excretory phase (EP)). Different combinations of four-phasic features for each VOI delineation strategy were used to build 176 classification models. The best VOI delineation strategy and superior CT phase were identified and the top-ranked features were analyzed.

RESULTS

Features extracted from UP and EP outperformed features from other single/combined phase(s). Shape features and first-order statistics features exhibited superior discrimination. The best performance (ACC 81%, SEN 67%, SPE 87%, AUC 0.87) was achieved with radiomics features extracted from UP and EP based on contour-focused VOI.

CONCLUSION

Shape and first-order features extracted from UP + EP images are better feature representations. Contour-focused VOI erosion by 2 mm or dilation by 4 mm within peritumor renal parenchyma exerts limited impact on discriminative performance. It provides a reference for segmentation tolerance in radiomics-based modeling for ccRCC nuclear grading.

KEY POINTS

• Lesion delineation uncertainties are tolerated within a VOI erosion range of 2 mm or dilation range of 4 mm within peritumor renal parenchyma for radiomics-based ccRCC nuclear grading. • Radiomics features extracted from unenhanced phase and excretory phase are superior to other single/combined phase(s) at differentiating high vs low nuclear grade ccRCC. • Shape features and first-order statistics features showed superior discriminative capability compared to texture features.

MRI Radiomics for the Prediction of Fuhrman Grade in Clear Cell Renal Cell Carcinoma: a Machine Learning Exploratory Study

The Fuhrman nuclear grade is a recognized prognostic factor for patients with clear cell renal cell carcinoma (CCRCC) and its pre-treatment evaluation significantly affects decision-making in terms of management. In this study, we aimed to assess the feasibility of a combined approach of radiomics and machine learning based on MR images for a non-invasive prediction of Fuhrman grade, specifically differentiation of high- from low-grade tumor and grade assessment. Images acquired on a 3-Tesla scanner (T2-weighted and post-contrast) from 32 patients (20 with low-grade and 12 with high-grade tumor) were annotated to generate volumes of interest enclosing CCRCC lesions. After image resampling, normalization, and filtering, 2438 features were extracted. A two-step feature reduction process was used to between 1 and 7 features depending on the algorithm employed. A J48 decision tree alone and in combination with ensemble learning methods were used. In the differentiation between high- and low-grade tumors, all the ensemble methods achieved an accuracy greater than 90%. On the other end, the best results in terms of accuracy (84.4%) in the assessment of tumor grade were achieved by the random forest. These evidences support the hypothesis that a combined radiomic and machine learning approach based on MR images could represent a feasible tool for the prediction of Fuhrman grade in patients affected by CCRCC.

Ceruloplasmin expression in renal cell carcinoma correlates with higher-grade and shortened survival

Aim: We aimed to explore ceruloplasmin (CP) expression in clear cell renal cell carcinoma (ccRCC). Materials & methods: CP was analyzed in biofluid samples of 63 ccRCC patients, divided into three grading groups, and immunohistochemically, in 308 ccRCC. Results: Significant differences of mean plasma and urine CP levels in different grading groups were found. CP immunoreactivity was significantly linked to high-grade disease. Log rank tests showed a significant shorter overall survival rate in CP-positive cases (all p < 0.05). Conclusion: CP protein levels in biofluid samples confirmed differential CP expressions, depending on nuclear grade in ccRCC as previously seen in RNA expression analysis. CP expression was linked to high-grade disease and reduced survival rate in RCC.

Computed Tomography-Based Radiomics Model for Predicting the WHO/ISUP Grade of Clear Cell Renal Cell Carcinoma Preoperatively: A Multicenter Study

Purpose

To examine the ability of computed tomography radiomic features in multivariate analysis and construct radiomic model for identification of the the WHO/ISUP pathological grade of clear cell renal cell carcinoma (ccRCC).

Methods

This was a retrospective study using data of four hospitals from January 2018 to August 2019. There were 197 patients with a definitive diagnosis of ccRCC by post-surgery pathology or biopsy. These subjects were divided into the training set (n = 122) and the independent external validation set (n = 75). Two phases of Enhanced CT images (corticomedullary phase, nephrographic phase) of ccRCC were used for whole tumor Volume of interest (VOI) plots. The IBEX radiomic software package in Matlab was used to extract the radiomic features of whole tumor VOI images. Next, the Mann-Whitney U test and minimum redundancy-maximum relevance algorithm(mRMR) was used for feature dimensionality reduction. Next, logistic regression combined with Akaike information criterion was used to select the best prediction model. The performance of the prediction model was assessed in the independent external validation cohorts. Receiver Operating Characteristic curve (ROC) was used to evaluate the discrimination of ccRCC in the training and independent external validation sets.

Results

The logistic regression prediction model constructed with seven radiomic features showed the best performance in identification for WHO/ISUP pathological grades. The Area Under Curve (AUC) of the training set was 0.89, the sensitivity comes to 0.85 and specificity was 0.84. In the independent external validation set, the AUC of the prediction model was 0.81, the sensitivity comes to 0.58, and specificity was 0.95.

Conclusion

A radiological model constructed from CT radiomic features can effectively predict the WHO/ISUP pathological grade of CCRCC tumors and has a certain clinical generalization ability, which provides an effective value for patient prognosis and treatment.

Immunohistochemical analysis of beta-catenin expression: a probable prognostic marker and potential therapeutic target in renal cell carcinoma

Background and aims

Renal cell carcinoma (RCC) seems to be the most aggressive type of genitourinary neoplasm. Down regulation of normal beta-catenin expression contributes to development of RCC, reflecting the role of beta-catenin/Wnt signaling pathway in pathogenesis. This study aims to evaluate the significance of beta-catenin expression and its correlation with the prognostic parameters.

Methods

A cross-sectional observational study was carried out in a tertiary care center on 58 RCC cases using variables like histological grade and type, tumor stage, necrosis. Formalin fixed, paraffin-embedded blocks were evaluated for beta-catenin expression by immunohistochemistry using scoring system. Data were analyzed by mean ± SD, χ² test, Pearson’s correlation test.

Results

Membranous score (MS) had a strong negative correlation with tumor stage (r=−0.407, p=0.044) and grade (r=−0.787, p=<0.001). Mean membranous score difference between low (Stage 1 and 2) vs. high stage (Stage 3 and 4) and low (Grade 1 and 2) vs. high grade (Grade 3 and 4) was statistically significant (p<0.001). Cytoplasmic score (CS) had positive correlation with tumor stage (r=0.586; p=0.002). No significant correlation was evident between cytoplasmic scores and tumor grade, however the mean cytoplasmic score difference between low grade vs. high grade was statistically significant (p < 0.001).

Conclusion

Beta-catenin may play a crucial role in the pathogenesis of RCC and has a positive correlation with the biological behavior of this tumor. The important role of beta-catenin as a prognostic parameter and probably a critical evaluator of targeted chemotherapy cannot be overemphasized.

Is preoperative neutrophil-to-lymphocyte ratio a red flag which can predict high-risk pathological characteristics in renal cell carcinoma?

Introduction

Renal cell carcinoma (RCC) is known to invoke both immunological and inflammatory responses. While the neutrophils mediate the tumor-induced inflammatory response, the lymphocytes bring about the various immunological events associated with it. The neutrophil-to-lymphocyte ratio (NLR) is a simple indicator of this dual response. We investigated the association between preoperative NLR and histopathological prognostic variables of RCC intending to find out whether it can be of value as a red flag capable of alerting the clinician as to the biological character of the tumor under consideration.

Methods

Preoperative NLR and clinicopathological variables, namely histological subtype, nuclear grade, staging, lymphovascular invasion, capsular invasion, tumor necrosis, renal sinus invasion, and sarcomatoid differentiation of 60 patients who underwent radical or partial nephrectomy, were analyzed to detect the association between the two.

Results

We found that mean preoperative NLR was significantly higher in clear-cell carcinomas (3.25 ± 0.29) when compared with nonclear-cell carcinomas (2.25 ± 0.63). There was a linear trend of NLR rise as the stage of the disease advanced. A significant rise in preoperative NLR was noted in tumors with various high-risk histopathological features such as tumor size, capsular invasion, tumor necrosis, and sarcomatoid differentiation.

Conclusion

Preoperative measurement of NLR is a simple test which may provide an early clue of high-risk pathological features of renal cell cancer.

Validation of the World Health Organization/International Society of Urological Pathology grading for Chinese patients with clear cell renal cell carcinoma

Background

This study aimed to compare the World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading system and the Fuhrman grading system and to verify the WHO/ISUP grade as a prognostic parameter of clear cell renal cell carcinoma (ccRCC) in a Chinese population.

Methods

The study consisted of 753 ccRCC patients treated with curative surgery between 2010 and 2018 at Xiangya Hospital Central South University (Changsha, China). All pathologic data were retrospectively reviewed by two pathologists. Cancer-specific survival (CSS) and recurrence-free survival (RFS) were examined as clinical outcomes.

Results

According to the WHO/ISUP grading system (ISUP group), nephrectomy type, pT stage and WHO/ISUP grade were independent risk factors for CSS (P<0.0001, P=0.0127 and P<0.0001, respectively) and RFS (P<0.0001, P=0.0077, and P<0.0001, respectively). In the Fuhrman group, nephrectomy type, pT stage and Fuhrman grade were independent risk factors for CSS (P<0.0001, P=0.0004, and P<0.0001, respectively) and RFS (P<0.0001, P=0.0001, and P<0.0001, respectively). The C-index for CSS and RFS using the Fuhrman grading system was 0.6323 and 0.6342, respectively, and that using the WHO/ISUP grading system was 0.6983 and 0.7005, respectively, both higher than the former (P=0.0185, and P=0.0172, respectively). In addition, upgrading from Fuhrman grade 2 to ISUP grade 3 resulted in worse CSS and RFS for ccRCC patients (P=0.0033 and P =0.0003, respectively).

Conclusions

We first verified correlations between the postoperative prognosis and WHO/ISUP grade of ccRCC in a Chinese population and confirmed that the ability to predict clinical outcomes with the WHO/ISUP grading system was superior to that with the Fuhrman grading system.

Computerized Image Analysis of Tumor Cell Nuclear Morphology Can Improve Patient Selection for Clinical Trials in Localized Clear Cell Renal Cell Carcinoma

Background:

Clinicopathological scores are used to predict the likelihood of recurrence-free survival for patients with clear cell renal cell carcinoma (ccRCC) after surgery. These are fallible, particularly in the middle range. This inevitably means that a significant proportion of ccRCC patients who will not develop recurrent disease enroll into clinical trials. As an exemplar of using digital pathology, we sought to improve the predictive power of “recurrence free” designation in localized ccRCC patients, by precise measurement of ccRCC nuclear morphological features using computational image analysis, thereby replacing manual nuclear grade assessment.

Materials and Methods:

TNM 8 UICC pathological stage pT1-pT3 ccRCC cases were recruited in Scotland and in Singapore. A Leibovich score (LS) was calculated. Definiens Tissue studio® (Definiens GmbH, Munich) image analysis platform was used to measure tumor nuclear morphological features in digitized hematoxylin and eosin (H&E) images.

Results:

Replacing human-defined nuclear grade with computer-defined mean perimeter generated a modified Leibovich algorithm, improved overall specificity 0.86 from 0.76 in the training cohort. The greatest increase in specificity was seen in LS 5 and 6, which went from 0 to 0.57 and 0.40, respectively. The modified Leibovich algorithm increased the specificity from 0.84 to 0.94 in the validation cohort.

Conclusions:

CcRCC nuclear mean perimeter, measured by computational image analysis, together with tumor stage and size, node status and necrosis improved the accuracy of predicting recurrence-free in the localized ccRCC patients. This finding was validated in an ethnically different Singaporean cohort, despite the different H and E staining protocol and scanner used. This may be a useful patient selection tool for recruitment to multicenter studies, preventing some patients from receiving unnecessary additional treatment while reducing the number of patients required to achieve adequate power within neoadjuvant and adjuvant clinical studies.

Updates in Histologic Grading of Urologic Neoplasms

CONTEXT.—

Tumor histology offers a composite view of the genetic, epigenetic, proteomic, and microenvironmental determinants of tumor biology. As a marker of tumor histology, histologic grading has persisted as a highly relevant factor in risk stratification and management of urologic neoplasms (ie, renal cell carcinoma, prostatic adenocarcinoma, and urothelial carcinoma). Ongoing research and consensus meetings have attempted to improve the accuracy, consistency, and biologic relevance of histologic grading, as well as provide guidance for many challenging scenarios.

OBJECTIVE.—

To review the most recent updates to the grading system of urologic neoplasms, including those in the 2016 4th edition of the World Health Organization (WHO) Bluebook, with emphasis on issues encountered in routine practice.

DATA SOURCES.—

Peer-reviewed publications and the 4th edition of the WHO Bluebook on the pathology and genetics of the urinary system and male genital organs.

CONCLUSIONS.—

This article summarizes the recently updated grading schemes for renal cell carcinoma, prostate adenocarcinomas, and bladder neoplasms of the genitourinary tract.

Characteristics and Outcome of Children with Renal Cell Carcinoma: A Narrative Review

Pediatric renal cell carcinoma (RCC) is a rare type of kidney cancer, most commonly occurring in teenagers and young adolescents. Few relatively large series of pediatric RCC have been reported. Knowledge of clinical characteristics, outcome and treatment strategies are often based on the more frequently occurring adult types of RCC. However, published pediatric data suggest that clinical, molecular and histological characteristics of pediatric RCC differ from adult RCC. This paper summarizes reported series consisting of ≥10 RCC pediatric patients in order to create an up-to-date overview of the clinical and histopathological characteristics, treatment and outcome of pediatric RCC patients.

A CT-based deep learning model for predicting the nuclear grade of clear cell renal cell carcinoma

PURPOSE

To investigate the effects of different methodologies on the performance of deep learning (DL) model for differentiating high- from low-grade clear cell renal cell carcinoma (ccRCC).

METHOD

Patients with pathologically proven ccRCC diagnosed between October 2009 and March 2019 were assigned to training or internal test dataset, and external test dataset was acquired from The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) database. The effects of different methodologies on the performance of DL-model, including image cropping (IC), setting the attention level, selecting model complexity (MC), and applying transfer learning (TL), were compared using repeated measures analysis of variance (ANOVA) and receiver operating characteristic (ROC) curve analysis. The performance of DL-model was evaluated through accuracy and ROC analyses with internal and external tests.

RESULTS

In this retrospective study, patients (n = 390) from one hospital were randomly assigned to training (n = 370) or internal test dataset (n = 20), and the other 20 patients from TCGA-KIRC database were assigned to external test dataset. IC, the attention level, MC, and TL had major effects on the performance of the DL-model. The DL-model based on the cropping of an image less than three times the tumor diameter, without attention, a simple model and the application of TL achieved the best performance in internal (ACC = 73.7 ± 11.6%, AUC = 0.82 ± 0.11) and external (ACC = 77.9 ± 6.2%, AUC = 0.81 ± 0.04) tests.

CONCLUSIONS

CT-based DL model can be conveniently applied for grading ccRCC with simple IC in routine clinical practice.

Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning

PURPOSE

To identify optimal classification methods for computed tomography (CT) radiomics-based preoperative prediction of clear cell renal cell carcinoma (ccRCC) grade.

MATERIALS AND METHODS

Seventy-one ccRCC patients (31 low grade and 40 high grade) were included in this study. Tumors were manually segmented on CT images followed by the application of three image preprocessing techniques (Laplacian of Gaussian, wavelet filter, and discretization of the intensity values) on delineated tumor volumes. Overall, 2530 radiomics features (tumor shape and size, intensity statistics, and texture) were extracted from each segmented tumor volume. Univariate analysis was performed to assess the association between each feature and the histological condition. Multivariate analysis involved the use of machine learning (ML) algorithms and the following three feature selection algorithms: the least absolute shrinkage and selection operator, Student's t test, and minimum Redundancy Maximum Relevance. These selected features were then used to construct three classification models (SVM, random forest, and logistic regression) to discriminate high from low-grade ccRCC at nephrectomy. Lastly, multivariate model performance was evaluated on the bootstrapped validation cohort using the area under the receiver operating characteristic curve (AUC) metric.

RESULTS

The univariate analysis demonstrated that among the different image sets, 128 bin-discretized images have statistically significant different texture parameters with a mean AUC of 0.74 ± 3 (q value < 0.05). The three ML-based classifiers showed proficient discrimination between high and low-grade ccRCC. The AUC was 0.78 for logistic regression, 0.62 for random forest, and 0.83 for the SVM model, respectively.

CONCLUSION

CT radiomic features can be considered as a useful and promising noninvasive methodology for preoperative evaluation of ccRCC Fuhrman grades.

The Role of Obesity in Renal Cell Carcinoma Patients: Clinical-Pathological Implications

Obesity is a well-known risk factor for renal cell carcinoma (RCC) development. However, the RCC–obesity link has not been fully addressed when considering a comprehensive scenario starting from pathogenetic aspects through pathological issues up to the outcome of medical treatment. We therefore conducted an electronic PubMed search using keywords “obesity”, “body mass index”, “overweight”, “renal cell carcinoma/kidney cancer”, “medical treatment”, “targeted therapy”, and “immunotherapy/immune checkpoint inhibitors”. The selected data supported a crosstalk between adipose tissue (adipocytes and other white adipose tissue cells) and cancer cells inducing several signaling pathways that finally stimulated angiogenesis, survival, and cellular proliferation. Accurate sampling of renal sinus fat correlated with a prognostic value. Retrospective clinical evidence in metastatic RCC patients with higher body mass index (BMI) and treated with targeted therapies and/or immune checkpoint inhibitors showed advantageous survival outcomes. Therefore, obesity may influence the course of RCC patients, although the interplay between obesity/BMI and RCC warrants a large prospective confirmation. We are therefore still far from determining a clear role of obesity as a prognostic/predictive factor in metastatic RCC patients undergoing targeted therapy and immunotherapy.

Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade

PURPOSE

To evaluate the performance of machine learning (ML)-based computed tomography (CT) radiomics analysis for discriminating between low grade (WHO/ISUP I-II) and high grade (WHO/ISUP III-IV) clear cell renal cell carcinomas (ccRCCs).

METHODS

A total of 164 low grade and 107 high grade ccRCCs were retrospectively analyzed in this study. Radiomic features were extracted from corticomedullary phase (CMP) and nephrographic phase (NP) CT images. Intraclass correlation coefficient (ICC) was calculated to quantify the feature's reproducibility. The training and validation cohort consisted of 163 and 108 cases. Least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were k-NearestNeighbor (KNN), Logistic Regression (LR), multilayer perceptron (MLP), Random Forest (RF), and support vector machine (SVM). The performance of classifiers was mainly evaluated and compared by certain metrics.

RESULTS

Seven CMP features (ICC range, 0.990-0.999) and seven NP features (ICC range, 0.931-0.999) were selected. The accuracy of CMP, NP and the combination of CMP and NP ranged from 82.2%-85.9 %, 82.8%-94.5 % and 86.5%-90.8 % in the training cohort, and 90.7%-95.4%, 77.8%-79.6 % and 91.7%-93.5 % in the validation cohort. The AUC of CMP, NP and the combination of CMP and NP ranged from 0.901 to 0.938, 0.912 to 0.976, 0.948 to 0.968 in the training cohort, and 0.957 to 0.974, 0.856 to 0.875, 0.960 to 0.978 in the validation cohort.

CONCLUSIONS

ML-based CT radiomics analysis can be used to predict the WHO/ISUP grade of ccRCCs preoperatively.

Automated clear cell renal carcinoma grade classification with prognostic significance

We developed an automated 2-tiered Fuhrman's grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman's grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21-3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

Unenhanced CT Texture Analysis of Clear Cell Renal Cell Carcinomas: A Machine Learning-Based Study for Predicting Histopathologic Nuclear Grade

OBJECTIVE. The purpose of this study is to investigate the predictive performance of machine learning (ML)-based unenhanced CT texture analysis in distinguishing low (grades I and II) and high (grades III and IV) nuclear grade clear cell renal cell carcinomas (RCCs). MATERIALS AND METHODS. For this retrospective study, 81 patients with clear cell RCC (56 high and 25 low nuclear grade) were included from a public database. Using 2D manual segmentation, 744 texture features were extracted from unenhanced CT images. Dimension reduction was done in three consecutive steps: reproducibility analysis by two radiologists, collinearity analysis, and feature selection. Models were created using artificial neural network (ANN) and binary logistic regression, with and without synthetic minority oversampling technique (SMOTE), and were validated using 10-fold cross-validation. The reference standard was histopathologic nuclear grade (low vs high). RESULTS. Dimension reduction steps yielded five texture features for the ANN and six for the logistic regression algorithm. None of clinical variables was selected. ANN alone and ANN with SMOTE correctly classified 81.5% and 70.5%, respectively, of clear cell RCCs, with AUC values of 0.714 and 0.702, respectively. The logistic regression algorithm alone and with SMOTE correctly classified 75.3% and 62.5%, respectively, of the tumors, with AUC values of 0.656 and 0.666, respectively. The ANN performed better than the logistic regression (p < 0.05). No statistically significant difference was present between the model performances created with and without SMOTE (p > 0.05). CONCLUSION. ML-based unenhanced CT texture analysis using ANN can be a promising noninvasive method in predicting the nuclear grade of clear cell RCCs.

Data set for the reporting of carcinoma of renal tubular origin: recommendations from the International Collaboration on Cancer Reporting (ICCR)

AIMS

The International Collaboration on Cancer Reporting (ICCR) has provided detailed data sets based upon the published reporting protocols of the Royal College of Pathologists, the Royal College of Pathologists of Australasia and the College of American Pathologists.

METHODS AND RESULTS

The data set for carcinomas of renal tubular origin treated by nephrectomy was developed to provide a minimum structured reporting template suitable for international use, and incorporated recommendations from the 2012 Vancouver Consensus Conference of the International Society of Urological Pathology (ISUP) and the fourth edition of the World Health Organisation Bluebook on tumours of the urinary and male genital systems published in 2016. Reporting elements were divided into those, which are required and recommended components of the report. Required elements are: specimen laterality, operative procedure, attached structures, tumour focality, tumour dimension, tumour type, WHO/ISUP grade, sarcomatoid/rhabdoid morphology, tumour necrosis, extent of invasion, lymph node status, surgical margin status, AJCC TNM staging and co-existing pathology. Recommended reporting elements are: pre-operative treatment, details of tissue removed for experimental purposes prior to submission, site of tumour(s) block identification key, extent of sarcomatoid and/or rhabdoid component, extent of necrosis, presence of tumour in renal vein wall, lymphovascular invasion and lymph node status (size of largest focus and extranodal extension).

CONCLUSIONS

It is anticipated that the implementation of this data set in routine clinical practice will inform patient treatment as well as provide standardised information relating to outcome prediction. The harmonisation of data reporting should also facilitate international research collaborations.

Percentage grade 4 tumour predicts outcome for clear cell renal cell carcinoma

Heterogeneity of tumour grading is common in clear cell renal cell carcinoma (ccRCC). WHO/ISUP grading specifies that RCC should be graded based on the highest grade present in at least one high power field. This does not take into account the proportion of high grade tumour present in a cancer, which may itself influence outcome. Cases of ccRCC accessioned by Aquesta Uropathology, Brisbane, Australia, between 2008 and 2015, were reviewed and grading assigned according to WHO/ISUP criteria. For tumours classified as grade 3 (G3) and 4 (G4), the percentage of tumour showing G3 and G4 morphology was assessed for each case. Survival analysis, with time to the development of metastases as the clinical outcome, was performed for six grading subclasses (G3 <10%, G3 10-50%, G3 >50%, G4 <10%, G4 10-50%, G4 >50%). Of the 681 cases of ccRCC in the series, there were 153 cases classified as G3 (91 cases) and G4 (62 cases) for which follow-up was available. During the follow-up period of <1-89 months, 19 (20.9%) patients with G3 and 30 (48.3%) patients with G4 cancers developed metastatic disease. The three subgroups of <10%, 10-50% and >50% G3 tumour were not significant in predicting outcome (p=0.47). Separating G3 into two groups of ≤50% vs >50% was also not significantly associated with outcome (p=0.22). For the three subgroups of G4 ccRCC (<10%, 10-50% and >50% G4) a higher percentage of G4 correlated with time to the development of metastases (p=0.01). Even though G4 tumours as a whole had a significantly worse outcome than G3 tumours (p=0.0004), the difference between G4 <10% and G3 tumours was not significant (p=0.27). On multivariate analysis, that included pT staging category and tumour size, there was a significant difference in survival between G4<10% and G4>50% tumours (p=0.018). The results of the study suggest that for ccRCC, WHO/ISUP G4 category should incorporate the percentage of G4 tumour present.

Prediction of ISUP grading of clear cell renal cell carcinoma using support vector machine model based on CT images

BACKGROUND

To explore whether radiomics combined with computed tomography (CT) images can be used to establish a model for differentiating high grade (International Society of Urological Pathology [ISUP] grade III-IV) from low-grade (ISUP I-II) clear cell renal cell carcinoma (ccRCC).

METHODS

For this retrospective study, 3-phase contrast-enhanced CT images were collected from 227 patients with pathologically confirmed ISUP-grade ccRCC (155 cases in the low-grade group and 72 cases in the high-grade group). First, we delineated the largest dimension of the tumor in the corticomedullary and nephrographic CT images to obtain the region of interest. Second, variance selection, single variable selection, and the least absolute shrinkage and selection operator were used to select features in the corticomedullary phase, nephrographic phase, and 2-phase union samples, respectively. Finally, a model was constructed using the optimal features, and the receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the predictive performance of the features in the training and validation queues. A Z test was employed to compare the differences in AUC values.

RESULTS

The support vector machine (SVM) model constructed using the screening features for the 2-stage joint samples can effectively distinguish between high- and low-grade ccRCC, and obtained the highest prediction accuracy. Its AUC values in the training queue and the validation queue were 0.88 and 0.91, respectively. The results of the Z test showed that the differences between the 3 groups were not statistically significant.

CONCLUSION

The SVM model constructed by CT-based radiomic features can effectively identify the ISUP grades of ccRCC.

Influence of venous tumour extension on local and remote recurrence of stage pT3a pN0 cM0 kidney tumours

INTRODUCTION AND OBJECTIVE

One of the inherent features of kidney tumours is the capacity to spread inside the venous system as tumour thrombi. The aim of this study was to assess in patients with stage pT3apN0cM0 kidney cancer whether venous tumour involvement influenced tumour recurrence.

MATERIALS AND METHODS

A retrospective analysis of patients with stage pT3apN0cM0 kidney cancer treated with radical nephrectomy between 1990-2015. Univariate and multivariate Cox regression analysis to identify predictive variables and independent predictive variables relating to recurrence.

RESULTS

The results of 153 patients were studied. The median follow-up was 82 (IQR 36-117) months. Recurrence-free survival at 5 years was 58.9% with a median of 97 (95% CI 49.9-144.1) months. Seventy-seven (50.3%) patients recurred. Seventy cases 70 (90.9%) had distant metastases, 17 (14.2%) of these patients had local recurrence in the bed of nephrectomy. Tumour necrosis (p=.0001), and microvascular invasion (p=.001) were identified as independent predictors of tumour recurrence in the multivariable analysis.

CONCLUSIONS

In our series, after multivariable analysis, venous tumour extension was not related to recurrence. Tumour necrosis and microvascular infiltration did behave as independent predictive factors of tumour recurrence.

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

PURPOSE

Pathological parameters assessed on biopsies and resection specimens have a pivotal role in the diagnosis, prognosis and management of patients with renal cell carcinoma (RCC).

METHODS

A non-systematic literature search was performed, updated to January 2018, to identify key standards and controversies in the pathological classification, grading and staging of RCC.

RESULTS

Although most RCCs exhibit characteristic morphology that enables easy categorisation, RCCs show considerable morphological heterogeneity and it is not uncommon for there to be difficulty in assigning a tumour type, especially with rarer tumour subtypes. The differentiation between benign and malignant oncocytic tumours remains a particular challenge. The development of additional immunohistochemical and molecular tests is needed to facilitate tumour typing, because of the prognostic and therapeutic implications, and to enable more reliable identification of poorly differentiated metastatic tumours as being of renal origin. Any new tests need to be applicable to small biopsy samples, to overcome the heterogeneity of renal tumours. There is also a need to facilitate identification of tumour types that have genetic implications, to allow referral and management at specialist centres. Digital pathology has a potential role in such referral practice.

CONCLUSION

Much has been done to standardise pathological assessment of renal cell carcinomas in recent years, but there still remain areas of difficulty in classification and grading of these heterogeneous tumours.

Accurate Risk Assessment of Patients with Pathologic T3aN0M0 Renal Cell Carcinoma

To develop a more precise risk-stratification system by investigating the prognostic impact of tumor growth within fatty tissues surrounding the kidney and/or renal vein. We conducted a retrospective review of the medical records of 211 patients with a pathologic diagnosis of T3aN0M0RCC among 4,483 renal cell carcinoma (RCC) patients from February 1988 to December 2015 according to the number of T3a pathologies—extrarenal fat invasion (EFI) and/or renal venous invasion (RVI). During a mean follow-up duration of 38.8 months, the patients with both pathologies (EFI + RVI) had lower recurrence free survival (RFS) rate than those with only a single pathology (p = 0.001). Using multivariable Cox regression analysis, the presence of both factors was shown to be an independent predictor of RFS (HR = 1.964, p = 0.032); cancer specific survival rate was not different among patients with EFI and/or RVI. Patients with pathologic T3aN0M0 RCC presenting with both EFI and RVI were at an increased risk of recurrence following nephrectomy. Therefore, pathologic T3a RCC could be sub-divided into those with favorable and unfavorable disease according to presence of EFI and/or RVI pathologies.

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

OBJECTIVE

To evaluate the performance of quantitative computed tomography (CT) texture analysis using different machine learning (ML) classifiers for discriminating low and high nuclear grade clear cell renal cell carcinomas (cc-RCCs).

MATERIALS AND METHODS

This retrospective study included 53 patients with pathologically proven 54 cc-RCCs (31 low-grade [grade 1 or 2]; 23 high-grade [grade 3 or 4]). In one patient, two synchronous cc-RCCs were included in the analysis. Mean age was 57.5 years. Thirty-four (64.1%) patients were male and 19 were female (35.9%). Mean tumour size based on the maximum diameter was 57.4 mm (range, 16-145 mm). Forty patients underwent radical nephrectomy and 13 underwent partial nephrectomy. Following pre-processing steps, two-dimensional CT texture features were extracted using portal-phase contrast-enhanced CT. Reproducibility of texture features was assessed with the intra-class correlation coefficient (ICC). Nested cross-validation with a wrapper-based algorithm was used in feature selection and model optimisation. The ML classifiers were support vector machine (SVM), multilayer perceptron (MLP, a sort of neural network), naïve Bayes, k-nearest neighbours, and random forest. The performance of the classifiers was compared by certain metrics.

RESULTS

Among 279 texture features, 241 features with an ICC equal to or higher than 0.80 (excellent reproducibility) were included in the further feature selection process. The best model was created using SVM. The selected subset of features for SVM included five co-occurrence matrix (ICC range, 0.885-0.998), three run-length matrix (ICC range, 0.889-0.992), one gradient (ICC = 0.998), and four Haar wavelet features (ICC range, 0.941-0.997). The overall accuracy, sensitivity (for detecting high-grade cc-RCCs), specificity (for detecting high-grade cc-RCCs), and overall area under the curve of the best model were 85.1%, 91.3%, 80.6%, and 0.860, respectively.

CONCLUSIONS

The ML-based CT texture analysis can be a useful and promising non-invasive method for prediction of low and high Fuhrman nuclear grade cc-RCCs.

KEY POINTS

• Based on the percutaneous biopsy literature, ML-based CT texture analysis has a comparable predictive performance with percutaneous biopsy. • Highest predictive performance was obtained with use of the SVM. • SVM correctly classified 85.1% of cc-RCCs in terms of nuclear grade, with an AUC of 0.860.

The Immunoexpression of YAP1 and LATS1 Proteins in Clear Cell Renal Cell Carcinoma: Impact on Patients' Survival

The aim of the study was to determine by immunohistochemistry cellular localization and immunoreactivity levels of YAP1 and LATS1 proteins in paired sections of tumor and unchanged renal tissues of 54 clear cell renal cell carcinoma (ccRCC) patients. Associations between clinical-pathological and overall survival (OS; median follow-up was 40.6 months) data of patients and YAP1 and LATS1 immunoreactivity were analyzed by uni- and multivariate Cox regression model and log-rank test. YAP1 immunoreactivity was found in the nuclei of tumor cells in 64.8% of ccRCC patients, whereas only 24.1% of tumors revealed cytoplasmic YAP1 expression. LATS1 immunoexpression was observed only in the cytoplasm of tumor cells in 59.3% of patients. LATS1 immunoreactivity in cancer cells negatively correlated with the size of primary tumor. The overall YAP1 immunoreactivity did not correlate with clinical-pathological data of patients. However, the subgroup of ccRCC patients who presented with cytoplasmic YAP1 immunoexpression had significantly shorter OS (median = 26.8 months) than patients without cytoplasmic YAP1 expression (median undefined). Multivariate Cox analysis revealed that increased cytoplasmic YAP1 (HR = 4.53) and decreased LATS1 immunoreactivity levels (HR = 0.90) were associated with worse prognosis, being independent prognostic factors. These results suggest that YAP1 and LATS1 can be considered as new prognostic factors in ccRCC.

Verification of the International Society of Urological Pathology recommendations in Japanese patients with clear cell renal cell carcinoma

The aim of the present study was to evaluate the validity of potential prognostic parameters of clear cell renal cell carcinoma (ccRCC) recommended by the 2012 International Society of Urological Pathology (ISUP) Consensus Conference in the Japanese population. We reviewed 406 Japanese patients with localized or locally advanced ccRCC who underwent curative surgery during 2004-2014 at Tokai University Hospital (Isehara, Japan) and were followed up for >2 years after surgery. A single pathologist reviewed all the histological slides. Morphological subtype and pathological T stage were reassigned according to the 2016 World Health Organization and TNM classifications. Sarcomatoid differentiation (SD), rhabdoid differentiation (RD), tumor necrosis (TN) and microvascular invasion (MVI) were assessed according to the 2012 ISUP recommendations. Nuclear grade was reclassified according to both the Fuhrman and the ISUP grading systems. Recurrence‑free survival (RFS) and cancer-specific survival (CSS) were assessed through univariate and multivariate analyses. According to the Fuhrman grading system (group Fuhrman), TN and MVI were independent risk factors for postoperative recurrence in the multivariate analysis using the Cox proportional hazards model. According to the ISUP grading system (group ISUP), TN and MVI were independent risk factors for postoperative recurrence. In group Fuhrman, age, Fuhrman grade and TN were independent risk factors for CSS. In group ISUP, age, ISUP grade, and TN were independent risk factors for CSS. Furthermore, the group that was upgraded from Fuhrman grade 2 to ISUP grade 3 exhibited poorer CSS compared with the group that was reclassified from Fuhrman grade 2 to ISUP grade 2 (non-upgraded). Regardless of the nuclear grade, TN remained an independent predictor of RFS and CSS. To the best of our knowledge, this is the first report to prove the correlation between the 2012 ISUP recommendations and clinical outcomes in a Japanese ccRCC cohort. TN and upgrading to ISUP grade 3 were found to be potentially useful independent indicators of postoperative prognosis.