Histological Subtypes Of Renal Tumors Research Articles

Multi-instance learning for identifying high-risk subregions associated with synchronous distant metastasis in clear cell renal cell carcinoma.

Clear cell renal cell carcinoma (ccRCC) is one of the most common histological subtypes of renal tumors. To identify high-risk subregions associated with synchronous distant metastasis. This study enrolled a total of 277 patients with ccRCC. Voxel intensity and local entropy values were compiled within the region of interest for all patients. Unsupervised k-means clustering yielded three subregions per tumor. Radiomic features were extracted, and random forest-based feature selection was conducted. The selected features were used in a multi-instance support vector machine (mi-SVM) model for training, and predictions were made on the validation cohort. Model performance was evaluated using five-fold cross-validation. The subregion with the highest score for patients with synchronous distant metastasis was identified across all cohorts. The mi-SVM model yielded an average area under the curve (AUC) of 0.812 in the training cohort and 0.805 in the validation cohort. In the entire cohort of patients with synchronous distant metastasis, subregion 2, characterized by tumor periphery and intratumoral transitional components, accounted for the highest proportion (48.57%, 30.6/63) among all subregions. It represents a high-risk subregion for synchronous distant metastasis of clear cell renal cell carcinoma. The peripheral and intratumoral transition zones of clear cell renal cell carcinoma are high-risk subregions associated with synchronous distant metastasis.

Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting

ObjectivesTo distinguish histological subtypes of renal tumors using radiomic features and machine learning (ML) based on multiphase computed tomography (CT).Material and methodsPatients who underwent surgical treatment for renal tumors at two tertiary centers from 2012 to 2022 were included retrospectively. Preoperative arterial (corticomedullary) and venous (nephrogenic) phase CT scans from these centers, as well as from external imaging facilities, were manually segmented, and standardized radiomic features were extracted. Following preprocessing and addressing the class imbalance, a ML algorithm based on extreme gradient boosting trees (XGB) was employed to predict renal tumor subtypes using 10-fold cross-validation. The evaluation was conducted using the multiclass area under the receiver operating characteristic curve (AUC). Algorithms were trained on data from one center and independently tested on data from the other center.ResultsThe training cohort comprised n = 297 patients (64.3% clear cell renal cell cancer [RCC], 13.5% papillary renal cell carcinoma (pRCC), 7.4% chromophobe RCC, 9.4% oncocytomas, and 5.4% angiomyolipomas (AML)), and the testing cohort n = 121 patients (56.2%/16.5%/3.3%/21.5%/2.5%).The XGB algorithm demonstrated a diagnostic performance of AUC = 0.81/0.64/0.8 for venous/arterial/combined contrast phase CT in the training cohort, and AUC = 0.75/0.67/0.75 in the independent testing cohort. In pairwise comparisons, the lowest diagnostic accuracy was evident for the identification of oncocytomas (AUC = 0.57–0.69), and the highest for the identification of AMLs (AUC = 0.9–0.94)ConclusionRadiomic feature analyses can distinguish renal tumor subtypes on routinely acquired CTs, with oncocytomas being the hardest subtype to identify.Clinical relevance statementRadiomic feature analyses yield robust results for renal tumor assessment on routine CTs. Although radiologists routinely rely on arterial phase CT for renal tumor assessment and operative planning, radiomic features derived from arterial phase did not improve the accuracy of renal tumor subtype identification in our cohort.

Artificial Intelligence-Based Non-invasive Differentiation of Distinct Histologic Subtypes of Renal Tumors With Multiphasic Multidetector Computed Tomography.

With rising cases of renal cell carcinoma (RCC), precise identification of tumor subtypes is essential, particularly for detecting small, heterogenous lesions often overlooked in traditional histopathological examinations. This study demonstrates the non-invasive use of deep learning for Histopathological differentiation of renal tumors through quadriphasic multidetector computed tomography (MDCT). This prospective longitudinal study includes 50 subjects (32 males, 18 females) with suspected renal tumors. A deep neural network (DNN) is developed to predict RCC subtypes using peak attenuation values measured in Hounsfield Units (HUs) obtained from quadriphasic MDCT scans. The network then generates confidence scores for each of the four primary subtypes of renal tumors, effectively distinguishing between benign oncocytoma and various malignant subtypes. Our neural network accurately distinguishes Renal tumor subtypes, including clear cell, papillary, chromophobe, and benign oncocytoma, with a confidence score of 68% with the network's diagnosis aligning with Histopathological examinations. Our network was also able to accurately classify RCC subtypes on a synthetically generated dataset with 20,000 samples. We developed an artificial intelligence-based RCC subtype classification technique. Our approach is non-invasive and has the potential to transform the methodology in Renal oncology by providing accurate and timely diagnostic information and enhancing clinical decisions.

Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography

In 2020, it is estimated that 73,750 kidney cancer cases were diagnosed, and 14,830 people died from cancer in the United States. Preoperative multi-phase abdominal computed tomography (CT) is often used for detecting lesions and classifying histologic subtypes of renal tumor to avoid unnecessary biopsy or surgery. However, there exists inter-observer variability due to subtle differences in the imaging features of tumor subtypes, which makes decisions on treatment challenging. While deep learning has been recently applied to the automated diagnosis of renal tumor, classification of a wide range of subtype classes has not been sufficiently studied yet. In this paper, we propose an end-to-end deep learning model for the differential diagnosis of five major histologic subtypes of renal tumors including both benign and malignant tumors on multi-phase CT. Our model is a unified framework to simultaneously identify lesions and classify subtypes for the diagnosis without manual intervention. We trained and tested the model using CT data from 308 patients who underwent nephrectomy for renal tumors. The model achieved an area under the curve (AUC) of 0.889, and outperformed radiologists for most subtypes. We further validated the model on an independent dataset of 184 patients from The Cancer Imaging Archive (TCIA). The AUC for this dataset was 0.855, and the model performed comparably to the radiologists. These results indicate that our model can achieve similar or better diagnostic performance than radiologists in differentiating a wide range of renal tumors on multi-phase CT.

Use of diffusion-weighted and dynamic contrast-enhanced MRI to differentiate histological subtypes of renal tumors

Use of diffusion-weighted and dynamic contrast-enhanced MRI to differentiate histological subtypes of renal tumors

Genome-Wide DNA Methylation Profiles in Renal Tumors of Various Histological Subtypes and Non-Tumorous Renal Tissues

Objective: The aim of this study is to clarify genome-wide DNA methylation profiles in renal tumors of various histological subtypes. Methods: Bacterial artificial chromosome (BAC) array-based methylated CpG island amplification was performed using tissue samples of 17 patients with papillary renal cell carcinomas (RCCs), chromophobe RCCs and oncocytomas, and the results were compared with those from 51 patients with clear cell RCCs. Results: Unsupervised hierarchical clustering analysis based on DNA methylation status clustered type 1 and type 2 papillary RCCs into different subclasses. Although chromophobe RCCs and oncocytomas were clustered into the same subclass, the DNA methylation status of 21 BAC clones was able to discriminate chromophobe RCCs from oncocytomas. The number of BAC clones showing DNA methylation alteration in non-tumorous renal tissue from patients with chromophobe RCCs and oncocytomas was smaller than that from patients with clear cell RCCs. Biphasic accumulation of DNA methylation alterations was observed in non-tumorous renal tissue from all 68 patients, and patients showing such alterations on more BAC clones had a poorer outcome than patients showing them on fewer BAC clones. Conclusions: DNA methylation profiles determining the histological subtypes of renal tumors developing in individual patients and/or patient outcome may be already established in non-tumorous renal tissue at the precancerous stage.

Prognostic relevance of the histological subtype of renal cell carcinoma

According to several studies, when the histological subtype of renal cell carcinoma is established it is possible to attribute a different life expectancy to each patient. We analyzed the prognostic significance of the histological subtype in renal cell carcinoma. The authors retrospectively analyzed the follow-up of 230 patients after radical or conservative renal surgery. The histological characteristics of the different subtypes of tumor were obtained and the disease-free and cancer-specific survival curves for the clear cell, cromophobic, papillary, collecting duct (Bellini) subtypes and those with sarcomatoid differentiation were individualized. The disease-free and cancer-specific survival rates for clear cell tumors were 76.6% and 68.0% respectively, 71.2% and 82.1% respectively for the cromophobic type, 71.1% and 79.8% respectively for the papillary type, 26.9% and 39.3% respectively for the sarcomatoid type, and 0.0% and 0.0% respectively for the collecting ducts (p < 0.001). The histological subtypes of renal tumors can stratify patients into different prognostic groups only when the sarcomatoid differentiation is present.

The Distribution of Histological Subtypes of Renal Tumors by Decade of Life Using the 2004 WHO Classification

The 2004 World Health Organization histological classification of renal tumors reflects our understanding of the underlying molecular determinants of renal tumors. We reviewed all partial and radical nephrectomy specimens at Barnes-Jewish Hospital to determine if the distribution of renal tumor histological subtypes varies by decade of life using the new scheme. A total of 1,043 consecutive cases of renal masses operated on for presumed malignancy from 1989 to 2003 were identified. All specimens were rereviewed by a single pathologist (MFS) and classified by the 2004 WHO scheme. In addition to decade of life and histological subtype, gender, tumor size and pathological tumor stage were analyzed. Analysis demonstrated an association between histological subtype and decade of life (p <0.001). The proportions of clear cell renal cell carcinoma (p = 0.008) and angiomyolipoma (p <0.001) decreased while the proportions of oncocytoma (p <0.001) and papillary renal cell carcinoma (p = 0.005) increased with increasing decade of life. The proportions of chromophobe (p = 0.181) and unclassified (p = 0.660) renal cell carcinoma did not change with increasing decade of life. In addition, younger patients were more likely to have larger tumors (p = 0.019) and metastatic disease at diagnosis (p = 0.017), while gender (p = 0.809) and tumor stage (p = 0.334) were not associated with increasing decade of life. This study provides baseline histological subtypes by decade for the most common renal tumors using the 2004 WHO histological classification. Clinicians may consider using these trends along with imaging, history and physical examination to counsel patients before recommending treatment.

Significance of Peritumoral Vascularity on CT in Evaluation of Renal Cortical Tumor

To investigate whether the presence and degree of peritumoral vascularity may provide any diagnostic information regarding the histological subtypes of renal tumors. Between January 2004 and March 2006, 214 patients (age, 19-94 years; 120 men, 94 women) with renal masses underwent total or partial nephrectomy and preoperative renal protocol computed tomography. Two radiologists retrospectively reviewed the computed tomographic exams in an independent and blinded fashion. The radiologists evaluated the presence of peritumoral vascularity and measured the largest vessel caliber. Fisher exact tests, multivariate logistic regression, and Wilcoxon rank-sum tests were performed for statistical analysis. Of 219 renal tumors (median size, 3.5 cm; range, 0.9-20.0 cm) included in this study, 112 (51%) were clear cell renal cell carcinoma, 34 (16%) were papillary, 32 (15%) were chromophobe, 17 (8%) were oncocytomas, 6 (3%) were lipid-poor angiomyolipomas, and 18 (8%) were other or unclassified renal tumors. The presence of peritumoral vascularity was significantly associated with tumor size within each subtype. For both readers, peritumoral vascularity was more frequently identified in clear cell carcinomas than in papillary renal carcinomas of similar size (P = 0.019 and 0.008, respectively). For one of the readers, chromophobe carcinomas were also significantly less frequently associated with peritumoral vascularity than clear cell carcinomas of similar size (P = 0.014). Clear cell carcinomas demonstrate peritumoral vascularity significantly more frequently than other malignant renal tumors of similar size. The presence of peritumoral vascularity may provide additional diagnostic information and improve therapeutic planning in some cases.

Decreased expression of the human stem cell marker, Rex-1 (zfp-42) , in renal cell carcinoma

The Rex-1 (Zfp-42) gene encodes a zinc finger family transcription factor which is highly expressed in mouse and human embryonic stem cells. It is one of several gene markers used to identify human stem cells. While several organs are known to harbor adult human stem cells, the presence and distribution of stem cells in both the normal and neoplastic adult kidney remains largely unknown. In this study we evaluated Rex-1 mRNA and protein expression in normal and malignant kidney tissue specimens from human patients. Rex-1 mRNA expression was determined using both reverse transcription and real-time PCR. REX1 protein expression was assessed by western analysis and immunohistochemistry, using an affinity-purified, polyclonal antibody to the REX1 protein. We found that 14 of 15 (93%) non-tumor renal parenchymal specimens demonstrated Rex-1 mRNA, compared with 5 of 14 (36%) renal tumors (P < 0.005). REX1 protein expression was detected in 21 of 23 (91%) non-tumor and in 7 of 19 (37%) tumor specimens (P < 0.001). Furthermore, in six of these seven renal tumor specimens where REX1 protein expression was detected, the levels were at least 3-fold lower than those in adjacent, normal kidney tissue. There were no differences in Rex-1 mRNA or protein expression among the various histologic subtypes of renal tumors (clear cell carcinoma, papillary carcinoma, chromophobe carcinoma and oncocytoma). Immunohistochemical staining confirmed the absence of REX1 in three renal tumor specimens (two clear cell and one papillary carcinoma), while the REX1 protein was detected in a small percentage of proximal tubular cells in normal renal tissue. Immunohistochemical staining of another stem cell marker, OCT4, demonstrated a similar pattern of protein expression in a small percentage of normal renal proximal tubular cells. In summary, we were able to detect Rex-1 mRNA and protein expression in over 90% of normal renal parenchymal specimens and we observed a significant reduction in REX1 expression in renal tumor specimens of all histologic subtypes.

Pax-2 expression in adult renal tumors

To assess the expression of the homeogene Pax-2 in adult renal cell carcinomas, we did a retrospective immunohistochemical analysis of 56 frozen tumor samples representing all major histologic subtypes of renal tumors. There were 33 conventional renal cell carcinomas (58.9%), 12 papillary renal cell carcinomas (21.4%), 4 chromophobe cell renal carcinomas, 4 urothelial cell renal carcinomas, and 3 oncocytomas. Forty-five tumors (62.5%) were localized, and 21 tumors had extrarenal involvement. Eight patients (14%) had metastatic disease at the end of the follow-up. We searched for relationships between Pax-2 expression and nuclear grading, TNM staging, Ki-67 proliferation index, expression of transforming growth factor-β1 (TGF-β1), an in vitro down-regulator of Pax-2 expression, and finally cytogenetic abnormalities. All histologic subtypes expressed Pax-2 protein, except urothelial renal carcinomas. The highest expression was in papillary renal cell carcinomas. In this subtype, all tumors and 83.3% ± 12.3% of tumor cells were immunoreactive for Pax-2. All but 2 conventional renal cell carcinomas expressed Pax-2, but with 26.3% ± 29.6% of immunoreactive cells (P <.001). Pax-2 expression was not correlated with nuclear grading (P =.6), tumor size (P =.3), and TGF-β1 expression (P =.1). Nevertheless, Pax-2 expression correlated with the Ki-67 proliferation index only for the conventional histologic subtype (P =.03). In this histologic subtype, Pax-2 expression was higher in patients with metastatic disease than in those without (P =.02). Pax-2 expression was not associated with specific cytogenetic abnormalities like trisomy 7 (P =.1), 3p deletion (P =.5), and hyperdiploidy (P =.2). TGF-β1 expression, positive in 33 tumors (59%), was not correlated with either Pax-2 expression (P =.1) or current prognostic factors such as nuclear grading (P =.2). Interestingly, we also observed an expression of TGF-βRI and TGF-βRII in the tumors with high nuclear grading (P =.005). We conclude that Pax-2 protein is expressed in all major histologic subtypes of renal cell carcinomas. The pattern of expression differs between these subtypes. Pax-2 expression in conventional renal cell carcinomas is correlated with the proliferation index and is significantly higher in patients with metastatic disease. HUM PATHOL 32:282-287. Copyright © 2001 by W.B. Saunders Company