Subtypes Of Renal Tumors Research Articles

CT-based transformer model for non-invasively predicting the Fuhrman nuclear grade of clear cell renal cell carcinoma.

BackgroundClear cell Renal Cell Carcinoma (ccRCC) is the most common malignant tumor in the urinary system and the predominant subtype of malignant renal tumors with high mortality. Biopsy is the main examination to determine ccRCC grade, but it can lead to unavoidable complications and sampling bias. Therefore, non-invasive technology (e.g., CT examination) for ccRCC grading is attracting more and more attention. However, noise labels on CT images containing multiple grades but only one label make prediction difficult. However, noise labels exist in CT images, which contain multiple grades but only one label, making prediction difficult.AimWe proposed a Transformer-based deep learning algorithm with CT images to improve the diagnostic accuracy of grading prediction and to improve the diagnostic accuracy of ccRCC grading.MethodsWe integrate different training models to improve robustness and predict Fuhrman nuclear grade. Then, we conducted experiments on a collected ccRCC dataset containing 759 patients and used average classification accuracy, sensitivity, specificity, and AreaUnderCurve as indicators to evaluate the quality of research. In the comparative experiments, we further performed various current deep learning algorithms to show the advantages of the proposed method. We collected patients with pathologically proven ccRCC diagnosed from April 2010 to December 2018 as the training and internal test dataset, containing 759 patients. We propose a transformer-based network architecture that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to extract a persuasive feature automatically. And then, a nonlinear classifier is applied to classify. We integrate different training models to improve the accuracy and robustness of the model. The average classification accuracy, sensitivity, specificity, and area under curve are used as indicators to evaluate the quality of a model.ResultsThe mean accuracy, sensitivity, specificity, and Area Under Curve achieved by CNN were 82.3%, 89.4%, 83.2%, and 85.7%, respectively. In contrast, the proposed Transformer-based model obtains a mean accuracy of 87.1% with a sensitivity of 91.3%, a specificity of 85.3%, and an Area Under Curve (AUC) of 90.3%. The integrated model acquires a better performance (86.5% ACC and an AUC of 91.2%).ConclusionA transformer-based network performs better than traditional deep learning algorithms in terms of the accuracy of ccRCC prediction. Meanwhile, the transformer has a certain advantage in dealing with noise labels existing in CT images of ccRCC. This method is promising to be applied to other medical tasks (e.g., the grade of neurogliomas and meningiomas).

MND1 functions as a potential prognostic biomarker associated with cell cycle and immune infiltration in kidney renal clear cell carcinoma.

Kidney renal clear cell carcinoma (KIRC) is a common and invasive subtype of renal tumors, which has poor prognosis and high mortality. MND1 is a meiosis specific protein that participates in the progress of diverse cancers. Nonetheless, its function in KIRC was unclear. Here, TIMER, TCGA, GEO databases and IHC found MND1 expression is upregulated in KIRC, leading to poor overall survival, and MND1 can serve as an independent prognostic factor. Moreover, enrichment analysis revealed the functional relationship between MND1 and cell cycle, immune infiltration. EdU and transwell assays confirmed that MND1 knockdown surely prohibited the proliferation, migration, and invasion of KIRC cells. Additionally, immune analysis showed that MND1 displayed a strong correlation with various immune cells. Interference with MND1 significantly reduces the expression of chemokines. TCGA and GEO databases indicated that MND1 expression is significantly related to two m6A modification related gene (METTL14, IGF2BP3). Finally, the drug sensitivity analysis revealed 7 potentially sensitive drugs for KIRC patients with high MND1 expression. In conclusion, MND1 can be used as a prognostic biomarker for KIRC and provides clues regarding cell cycle, immune infiltrates and m6A. Sensitive drugs may be an effective treatment strategy for KIRC patients with high expression of MND1.

Papillary renal neoplasm with reverse polarity may be a novel renal cell tumor entity with low malignant potential

AimsThis study retrospectively investigated the morphological, immunohistochemical and molecular genetic features of papillary renal neoplasm with reverse polarity (PRNRP), a recently described renal tumor.Methods and resultsEleven cases of PRNRP were collected, and 16 cases of type I and 9 cases of type II papillary renal cell carcinoma were included as a control series. Pathological features were evaluated based on HE staining and immunohistochemistry. KRAS exon 2 and BRAF V600E mutations were detected by Real-time PCR and Sanger sequencing. Fluorescence in situ hybridization was conducted for identification of chromosomal abnormalities.Hemosiderin deposition was found in a small amount of tumor cells in 6 cases. Multifocal or patchy necrosis (5/11), small focal invasion of the pseudocapsules or renal parenchyma (6/11), and breakthrough of renal capsule with nerve invasion (1/11) were revealed, inconsistent with the previous view that the tumor lacks necrosis and intercellular hemosiderin. Immunohistochemical staining (diffusely positive for CK7 and GATA3, negative for CD117 and vimentin, and negative to weakly positive for P504S) and high frequency of KRAS mutations in exon 2 (9/10) supported the identification and inclusion of our cases. Chromosome 7 trisomy (1/7), chromosome 17 trisomy (0/7) and chromosome Y deletion (0/5 male patients) were seldom detected in this tumor.All patients were alive without metastasis or recurrence at the end of the follow-up.ConclusionOur findings may highlight the possibility of a low malignant potential of this emerging entity. We suggest that the tumor be classified as a novel renal cell tumor subtype independent of papillary renal cell carcinoma.

TFE3 and TFEB-rearranged renal cell carcinomas: an immunohistochemical panel to differentiate from common renal cell neoplasms.

TFE3/TFEB-rearranged renal cell carcinomas are characterized by translocations involving TFE3 and TFEB genes. Despite the initial description of typical morphology, their histological spectrum is wide, mimicking common subtypes of renal cell tumors. Thus, the diagnosis is challenging requiring the demonstration of the gene rearrangement, usually by FISH. However, this technique is limited in most laboratories and immunohistochemical TFE3/TFEB analysis is inconsistent. We sought to identify a useful immunohistochemical panel using the most common available markers to recognize those tumors. We performed an immunohistochemical panel comparing 27 TFE3-rearranged and 10 TFEB-rearranged renal cell carcinomas to the most common renal cell tumors (150 clear cell, 100 papillary, 50 chromophobe renal cell carcinomas, 18 clear cell papillary renal cell tumors, and 50 oncocytomas). When dealing with neoplasms characterized by cells with clear cytoplasm, CA9 is a helpful marker to exclude clear cell renal cell carcinoma. GATA3, AMACR, and CK7 are useful to rule out clear cell papillary renal cell tumor. CK7 is negative in TFE3/TFEB-rearranged renal cell carcinoma and positive in papillary renal cell carcinoma, being therefore useful in this setting. Parvalbumin and CK7/S100A1 respectively are of paramount importance when TFE3/TFEB-rearranged renal cell carcinoma resembles oncocytoma and chromophobe renal cell carcinoma. Moreover, in TFEB-rearranged renal cell carcinoma, cathepsin K and melanogenesis markers are constantly positive, whereas TFE3-rearranged renal cell carcinoma stains for cathepsin K in roughly half of the cases, HMB45 in 8% and Melan-A in 22%. In conclusion, since TFE3/TFEB-rearranged renal cell carcinoma may mimic several histotypes, an immunohistochemical panel to differentiate them from common renal cell tumors should include cathepsin K, CA9, CK7, and parvalbumin.

WHO 2022 landscape of papillary and chromophobe renal cell carcinoma.

The 5th edition of the WHO Classification of Tumours of the Urinary and Male Genital Systems contains relevant revisions and introduces a group of molecularly defined renal tumour subtypes. Herein we present the World Health Organization (WHO) 2022 perspectives on papillary and chromophobe renal cell carcinoma with emphasis on their evolving classification, differential diagnosis, and emerging entities. The WHO 2022 classification eliminated the type 1/2 papillary renal cell carcinoma (pRCC) subcategorization, given the recognition of frequent mixed tumour phenotypes and the existence of entities with a different molecular background within the type 2 pRCC category. Additionally, emerging entities such as biphasic squamoid alveolar RCC, biphasic hyalinising psammomatous RCC, papillary renal neoplasm with reverse polarity, and Warthin-like pRCC are included as part of the pRCC spectrum, while additional morphological and molecular data are being gathered. In addition to oncocytomas and chromophobe renal cell carcinoma (chRCC), a category of 'other oncocytic tumours' with oncocytoma/chRCC-like features has been introduced, including emerging entities, most with TSC/mTOR pathway alterations (eosinophilic vacuolated tumour and so-called 'low-grade' oncocytic tumour), deserving additional research. Eosinophilic solid and cystic RCC was accepted as a new and independent tumour entity. Finally, a highly reproducible and clinically relevant universal grading system for chRCC is still missing and is another niche of ongoing investigation. This review discusses these developments and highlights emerging morphological and molecular data relevant for the classification of renal cell carcinoma.

CD34 and FSHR Expression to Differentiate Multiple Subtypes of Benign and Malignant Renal Neoplasms

BackgroundCurrently, no markers accurately differentiate benign from malignant renal masses. CD34 and FSHR are transmembrane proteins involved in neo-angiogenetic pathways and are differently expressed in several normal and cancerous tissues. However, little evidence exists on their distribution in different renal tumors. We aimed to evaluate their expressions in various renal tumors and adjacent normal tissue.MethodsWe retrieved 810 histological samples from 26 patients who underwent surgery for suspected RCa. In each case a core of 10 × 1 mm was selected perpendicular to the tumor capsule between normal kidney and tumor. Within this core 30 regions of interest (ROI), each measuring 669 μm × 500 μm, were acquired at 20× magnification (n = 2 adjacent normal tissue; n = 2 tumor capsule; n = 26 tumor). The surface area of FSHR and CD34 immunostaining was quantified in each ROI using number of stained pixels. The results were compared between RCa and normal kidney.ResultsImmunostaining was significantly different in normal, tumor capsular, and tumor tissues (both CD34 and FSHR P < 0.0001), with overall highest expression in normal and lowest in tumor tissues, where CD34 and FSHR were differently expressed amongst different tumor subtypes (both P < 0.0001). CD34 and FSHR were more expressed in benign versus malignant (both P < 0.0001) and in chromophobe carcinoma versus oncocytoma tumor tissues (CD34 P = 0.0003; FSHR P < 0.0001). The discriminating ability of FSHR alone for benign versus malignant (AUC 0.805; 95% CI 0.771 to 0.837) and chromophobe carcinoma versus oncocytoma (AUC 0.973; 95% CI 0.939 to 0.991) was high. In both cases FSHR AUC was significantly higher than CD34 (both P < 0.0001) and equivalent to the combination of CD34 and FSHR (both P > 0.9). The correlation amongst levels of staining in tumor tissues and distance from the capsule were overall weak (Spearman coefficient CD34 to 0.0644; FSHR-0.16322).ConclusionCD34 and FSHR are differentially expressed across renal tumor subtypes and between tumor and surrounding tissues. FSHR expression alone may be a useful tool to differentiate benign from malignant tumors and chromophobe carcinoma from oncocytoma.

Selected Articles from This Issue

Histone deacetylases (HDACs) play a critical role in epigenomic regulation of cancer cell signaling. HDAC inhibitors to-date have faced challenges due to poor isoform selectivity and narrow therapeutic indices. In this first disclosure, Diamond and colleagues report the discovery and preclinical development of the novel, orally bioavailable, class I-targeting HDAC inhibitor, OKI-179 (NCT03931681). OKI-179 was active against solid tumors in preclinical cancer models with a favorable pharmacokinetic profile and on-target pharmacodynamic effects. OKI-179 is a promising next generation HDAC inhibitor suitable for combining with other targeted agents based on its potency, desirable class I HDAC inhibition profile and oral bioavailability.Most men on androgen deprivation therapy (ADT) with advanced hormone-sensitive prostate cancer (HSPC) will develop castration resistant prostate cancer (CRPC), a lethal form of prostate cancer (PC). Previously, our group has demonstrated that IKKε is overexpressed in CRPC and its expression is directly correlated with aggressive PC in patients. In this issue, Gilbert and colleagues demonstrate that IKKε inhibitors, BX795 and Amlexanox, specifically target androgen-independent PC to induce a senescent phenotype, DNA damage and genomic instability. Our in vivo study shows that androgen-independent tumor PC growth is delayed with IKKε inhibitors, providing additional effective therapeutic strategies in the management of patients with CRPC.HLRCC is notorious for being resistance to all tested therapies. A standardized treatment modality for this aggressive subtype of renal tumor is still lacking. In this issue, Kerimoglu and co-workers showed that a combination of two clinically well tolerated therapeutics, rapamycin and Cyst(e)inase®, is efficacious in suppressing HLRCC growth in vivo. The combination induces ferroptosis in tumor tissues with no observable systemic toxicity. Given that rapamycin is an FDA-approved drug, and cyst(e)inase is currently in clinical trial, the combination provides an opportunity to translate into a HLRCC treatment strategy.Pediatric osteosarcoma is an aggressive bone tumor with a poor prognostic for those patients with metastatic disease or those who do not respond to therapy. Oncolytic viruses have shown a safe toxicity profile and are becoming a real treatment option for pediatric solid tumors. In this issue, Martinez-Velez and colleagues demonstrated the therapeutic effect of Delta-24-ACT, an oncolytic adenovirus armed with the 4-1BB ligand, in local and metastatic murine osteosarcoma models. Their data show the ability of Delta-24-ACT to turn the osteosarcoma tumor microenvironment from cold to hot, underscoring its potential as a therapeutic for this disease.

Deregulation of N6-Methyladenosine RNA Modification and Its Erasers FTO/ALKBH5 among the Main Renal Cell Tumor Subtypes.

(1) Background: Methylation of N6-adenosine (m6A) is the most abundant messenger RNA (mRNA) modification in eukaryotes. We assessed the expression profiles of m6A regulatory proteins in renal cell carcinoma (RCC) and their clinical relevance, namely, as potential biomarkers. (2) Methods: In silico analysis of The Cancer Genome Atlas (TCGA) dataset was use for evaluating the expression of the m6A regulatory proteins among RCC subtypes and select the most promising candidates for further validation. ALKBH5 and FTO transcript and protein expression were evaluated in a series of primary RCC (n = 120) and 40 oncocytomas selected at IPO Porto. (3) Results: In silico analysis of TCGA dataset disclosed altered expression of the major m6A demethylases among RCC subtypes, particularly FTO and ALKBH5. Furthermore, decreased FTO mRNA levels associated with poor prognosis in ccRCC and pRCC. In IPO Porto’s cohort, FTO and ALKBH5 transcript levels discriminated ccRCC from oncocytomas. Furthermore, FTO and ALKBH5 immunoexpression differed among RCC subtypes, with higher expression levels found in ccRCC comparatively to the other RCC subtypes and oncocytomas. (4) Conclusion: We conclude that altered expression of m6A RNA demethylases is common in RCC and seems to be subtype specific. Specifically, FTO and ALKBH5 might constitute new candidate biomarkers for RCC patient management, aiding in differential diagnosis of renal masses and prognostication.

PD49-04 ACCURATE DIFFERENTIATION OF PATHOLOGICAL SUBTYPES OF RENAL TUMOUR BY APPLYING A MACHINE LEARNING MODEL TO EPIGENETIC MARKERS

You have accessJournal of UrologyKidney Cancer: Basic Research & Pathophysiology II (PD49)1 Sep 2021PD49-04 ACCURATE DIFFERENTIATION OF PATHOLOGICAL SUBTYPES OF RENAL TUMOUR BY APPLYING A MACHINE LEARNING MODEL TO EPIGENETIC MARKERS Sabrina Rossi, Izzy Newsham, Sara Pita, Gahee Park, Radolsaw Lach, Anne Babbage, Christopher Smith, Kevin Brennan, Hong Zheng, Tom Mitchell, Anne Warren, John Leppert, Olivier Gevaert, Grant Stewart, Charles Massie, and Shamith Samarajiwa Sabrina RossiSabrina Rossi More articles by this author , Izzy NewshamIzzy Newsham More articles by this author , Sara PitaSara Pita More articles by this author , Gahee ParkGahee Park More articles by this author , Radolsaw LachRadolsaw Lach More articles by this author , Anne BabbageAnne Babbage More articles by this author , Christopher SmithChristopher Smith More articles by this author , Kevin BrennanKevin Brennan More articles by this author , Hong ZhengHong Zheng More articles by this author , Tom MitchellTom Mitchell More articles by this author , Anne WarrenAnne Warren More articles by this author , John LeppertJohn Leppert More articles by this author , Olivier GevaertOlivier Gevaert More articles by this author , Grant StewartGrant Stewart More articles by this author , Charles MassieCharles Massie More articles by this author , and Shamith SamarajiwaShamith Samarajiwa More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002071.04AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Small renal masses (SRM) represent a diagnostic challenge despite advances in imaging and renal biopsy. Approximately 20% of SRM removed at surgery are found to be benign post-operatively. DNA methylation is an early and stable event in tumorigenesis, which reveals cell ontology. We developed and validated a machine learning model, leveraging DNA methylation analysis in >1500 patient samples, to classify pathological subtypes of renal tumours and provide a platform to improve diagnosis. METHODS: Methylation was evaluated in gDNA from fresh frozen nephrectomy specimens, using the Illumina 450k microarray and EPIC Methyl Capture sequencing platforms. We combined our own dataset and TCGA data (N=approx 158000 markers). This dataset was divided into training and testing sets, using 4-fold cross validation, and used to train an XGBoost model to classify samples into one of five pathological subtypes. External validation was carried out on two independent publicly available datasets, from fresh frozen nephrectomy tissue (Brennan et al) and ex-vivo tissue biopsies (Chopra et al). RESULTS: The integrated training and testing set consisted of 1268 samples, including: 465 ccRCC, 303 pRCC, 101 chRCC, 73 oncocytomas and 329 adjacent normal kidney. The prediction accuracy in the testing set was 0.954; with high class-wise Area Under the Receiver Operating Characteristic Curves (ROC AUCs): 0.994 (ccRCC), 0.995 (pRCC), 0.982 (chRCC), 0.999 (oncocytoma), 1 (adjacent normal). The model was externally validated on 245 ex-vivo tissue biopsies from 100 renal tumours. The accuracy was 0.824 and average class-wise ROC AUCs were: 0.978 (ccRCC), 0.946 (pRCC), 0.994 (chRCC), 0.892 (oncocytoma), 0.969 (adjacent normal). Furthermore, an independent external validation was performed on 34 tissue samples, achieving average class-wise ROC AUCs: 1 (ccRCC), 0.904 (chRCC), 0.946 (oncocytoma), 0.976 (adjacent normal). In order to assess the impact of methylation heterogeneity on our classifier, the model was evaluated in 97 multi-region samples from 18 ccRCC patients. CONCLUSIONS: A machine learning model based on DNA methylation data can differentiate pathological subtypes of renal tumours with excellent accuracy, including external validation. The model may be applied to renal biopsy samples to improve the diagnostic pathway for renal tumours. This has the potential to reduce over-treatment by preventing unnecessary surgery, enhance patient QoL and minimize healthcare costs. Source of Funding: S.H. Rossi is funded by a Cancer Research UK Doctoral Research (PhD) fellowship © 2021 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e846-e846 Advertisement Copyright & Permissions© 2021 by American Urological Association Education and Research, Inc.MetricsAuthor Information Sabrina Rossi More articles by this author Izzy Newsham More articles by this author Sara Pita More articles by this author Gahee Park More articles by this author Radolsaw Lach More articles by this author Anne Babbage More articles by this author Christopher Smith More articles by this author Kevin Brennan More articles by this author Hong Zheng More articles by this author Tom Mitchell More articles by this author Anne Warren More articles by this author John Leppert More articles by this author Olivier Gevaert More articles by this author Grant Stewart More articles by this author Charles Massie More articles by this author Shamith Samarajiwa More articles by this author Expand All Advertisement Loading ...

Immunoexpression of SDHB, FH, and CK20 among eosinophilic renal tumors: A tissue microarray study

BackgroundDifferential diagnosis can be a challenge for eosinophilic subtypes of renal cell tumors due to their overlapping histomorphological and immunohistochemical features. We aimed to investigate the frequency of rare variants of renal cell carcinomas (RCCs) such as succinate dehydrogenase-deficient RCC (SDDRCC), hereditary leiomyomatosis and RCC (HLRCC)-associated RCC, and eosinophilic, solid, and cystic RCC (ESCRCC) in our population. Materials and methodsRenal tumors which could be considered in the eosinophilic tumor category were included: 91 conventional clear cell RCCs with eosinophilic cytoplasm, 72 papillary RCCs, 74 chromophobe RCCs, 88 oncocytomas, and 37 other rare subtypes. Using the tissue microarray method, succinate dehydrogenase B (SDHB), fumarate hydratase (FH), and cytokeratin 20 (CK20) antibodies were performed by immunohistochemistry. Immunohistochemistry was repeated on whole block sections for selected cases. The utility of these antibodies in the differential diagnosis was also investigated. ResultsLoss of SDHB expression was detected in three tumors, two of which showed typical morphology for SDDRCC. In additional two tumors, SDHB showed weak cytoplasmic expression without a mitochondrial pattern (possible-SDHB deficient). None of the tumors showed loss of FH expression. Heterogeneous reactions were observed with SDHB and FH antibodies. Only one ESCRCC was detected with diffuse CK20 positivity. ConclusionSDDRCCs, HLRCC-associated RCCs, and ESCRCCs are very rare tumors depending on the population. Possible weak staining and focal loss of SDHB and FH expression should be kept in mind and genetic testing must be included for equivocal results.

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.

TRIM63 is a sensitive and specific biomarker for MiT family aberration-associated renal cell carcinoma.

Microphthalmia-associated transcription factor (MiT) family aberration-associated renal cell carcinoma (MiTF-RCC) is a subtype of renal cell carcinoma harboring recurrent chromosomal rearrangements involving TFE3 or TFEB genes. MiTF-RCC is morphologically diverse, can histologically resemble common RCC subtypes like clear cell RCC and papillary RCC, and often poses a diagnostic challenge in genitourinary clinical and pathology practice. To characterize the MiTF-RCC at the molecular level and identify biomarker signatures associated with MiTF-RCC, we analyzed RNAseq data from MiTF-RCC, other RCC subtypes and benign kidney. Upon identifying TRIM63 as a cancer-specific biomarker in MiTF-RCC, we evaluated its expression independently by RNA in situ hybridization (RNA-ISH) in whole tissue sections from 177 RCC cases. We specifically included 31 cytogenetically confirmed MiTF-RCC cases and 70 RCC cases suspicious for MiTF-RCC in terms of clinical and morphological features, to evaluate and compare TRIM63 RNA-ISH results with theresults from TFE3/TFEB fluorescence in situ hybridization (FISH), which is the current clinical standard. We confirmed that TRIM63 mRNA was highly expressed in all classes of MiTF-RCC compared to other renal tumor categories, where it was mostly absent to low. While the TRIM63 RNA-ISH and TFE3/TFEB FISH results were largely concordant, importantly, TRIM63 RNA-ISH was strongly positive in TFE3 FISH false-negative cases with RBM10-TFE3 inversion. In conclusion, TRIM63 can serve as a diagnostic marker to distinguish MiTF-RCC from other renal tumor subtypes with overlapping morphology. We suggest a combination of TFE3/TFEB FISH and TRIM63 RNA-ISH assays to improve the accuracy and efficiency of MiTF-RCC diagnosis. Accurate diagnosis of MiTF-RCC and other RCC subtypes would enable effective targeted therapy and avoid poor therapeutic response due to tumor misclassification.

18Fluorodeoxyglucose-positron emission tomography/computed tomography for differentiation of renal tumors in hereditary kidney cancer syndromes.

To assess differences in FDG-PET/CT uptake among four subtypes of renal tumors: clear cell RCC (ccRCC), papillary type I and II RCC (pRCC), and oncocytoma. This retrospective study investigated 33 patients with 98 hereditary renal tumors. Lesions greater than 1cm and patients with a timeframe of less than 18months between preoperative imaging and surgery were considered. FDG-PET/CT images were independently reviewed by two nuclear medicine physicians, blinded to clinical information. Volumetric lesion SUVmean was measured and used to calculate a target-to-background ratio respective to liver (TBR). The Shrout-Fleiss intra-class correlation coefficient was used to assess reliability between readers. A linear mixed effects model, accounting for within-patient correlations, was used to compare TBR values of primary renal lesions with and without distant metastasis. The time interval between imaging and surgery for all tumors had a median of 77 (Mean: 139; Range: 1-512) days. Intra-class reliability of mean TBR resulted in a mean κ score of 0.93, indicating strong agreement between the readers. The mixed model showed a significant difference in mean TBR among the subtypes (p < 0.0001). Pairwise comparison showed significant differences between pRCC type II and ccRCC (p < 0.0001), pRCC type II and pRCC type I (p = 0.0001), and pRCC type II and oncocytoma (p = 0.0016). Furthermore, a significant difference in FDG uptake was present between primary pRCC type II renal lesions with and without distant metastasis (p = 0.023). pRCC type II lesions demonstrated significantly higher FDG activity than ccRCC, pRCC type I, or oncocytoma. These findings indicate that FDG may prove useful in studying the metabolic activity of renal neoplasms, identifying lesions of highest clinical concern, and ultimately optimizing active surveillance, and personalizing management plans.

Deep learning with a convolutional neural network model to differentiate renal parenchymal tumors: a preliminary study.

With advancements in medical imaging, more renal tumors are detected early, but it remains a challenge for radiologists to accurately distinguish subtypes of renal parenchymal tumors. We aimed to establish a novel deep convolutional neural network (CNN) model and investigate its effect on identifying subtypes of renal parenchymal tumors in T2-weighted fat saturation sequence magnetic resonance (MR) images. This retrospective study included 199 patients with pathologically confirmed renal parenchymal tumors, including 77, 46, 34, and 42 patients with clear cell renal cell carcinoma (ccRCC), chromophobe renal cell carcinoma (chRCC), angiomyolipoma (AML), and papillary renal cell carcinoma (pRCC), respectively. All enrolled patients underwent kidney MR scans with the field strength of 1.5Tesla (T) or 3.0T before surgery. We selected T2-weighted fat saturation sequence images of all patients and built a deep learning model to determine the type of renal tumors. Receiver operating characteristic(ROC) curve was depicted to estimate the performance of the CNN model; the accuracy, precision, sensitivity, specificity, F1-score, and area under the curve (AUC) were calculated. One-way analysis of variance and χ2 tests of independent samples were used to analyze the variables. The experimental results demonstrated that the model had a 60.4% overall accuracy, a 61.7% average accuracy, and a macro-average AUC of 0.82. The AUCs for ccRCC, chRCC, AML, and pRCC were 0.94, 0.78, 0.80, and 0.76, respectively. Deep CNN model based on T2-weighted fat saturation sequence MR images was useful to classify the subtypes of renal parenchymal tumors with a relatively high diagnostic accuracy.

Raman optical identification of renal cell carcinoma via machine learning

High pathologic tumor-node-metastasis (pTNM) stage grade or Fuhrman grade indicates poor oncological outcome in renal cell carcinoma (RCC). Early diagnosis and screening of these RCCs and adjust surgical planning accordingly are greatly beneficial to patients. Raman spectroscopy is a highly specific fingerprint spectrum on molecular level, pretty appropriate for label-free and noninvasive cancer diagnosis. In this work we established a Raman spectrum-based supporting vector machine (SVM) model to accurately ex vivo distinguish human renal tumor from normal tissues and fat with an accuracy of 92.89%. The model can also be used to determine tumor boundary, showing consistent results to pathological staining analysis. This method can be additionally used to accomplish the classification purposes of renal tumor subtypes and grades with an accuracy of 86.79% and 89.53%, respectively. Therefore, we prove that Raman spectroscopy has great potential in the rapid and accurate clinical diagnosis of renal cancers.

CT-based radiomics for differentiating renal tumours: a systematic review.

Differentiating renal tumours into grades and tumour subtype from medical imaging is important for patient management; however, there is an element of subjectivity when performed qualitatively. Quantitative analysis such as radiomics may provide a more objective approach. The purpose of this article is to systematically review the literature on computed tomography (CT) radiomics for grading and differentiating renal tumour subtypes. An educational perspective will also be provided. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist was followed. PubMed, Scopus and Web of Science were searched for relevant articles. The quality of each study was assessed using the Radiomic Quality Score (RQS). 13 studies were found. The main outcomes were prediction of pathological grade and differentiating between renal tumour types, measured as area under the curve (AUC) for either the receiver operator curve or precision recall curve. Features extracted to predict pathological grade or tumour subtype included shape, intensity, texture and wavelet (a type of higher order feature). Four studies differentiated between low-grade and high-grade clear cell renal cell cancer (RCC) with good performance (AUC = 0.82-0.978). One other study differentiated low- and high-grade chromophobe with AUC = 0.84. Finally, eight studies used radiomics to differentiate between tumour types such as clear cell RCC, fat-poor angiomyolipoma, papillary RCC, chromophobe RCC and renal oncocytoma with high levels of performance (AUC 0.82-0.96). Renal tumours can be pathologically classified using CT-based radiomics with good performance. The main radiomic feature used for tumour differentiation was texture. Fuhrman was the most common pathologic grading system used in the reviewed studies. Renal tumour grading studies should be extended beyond clear cell RCC and chromophobe RCC. Further research with larger prospective studies, performed in the clinical setting, across multiple institutions would help with clinical translation to the radiologist's workstation.

IPSILATERAL SYNCHRONOUS MUCINOUS TUBULAR AND SPINDLE CELL CARCINOMA AND CLEAR CELL PAPILLARY RENAL CELL CARCINOMA: A CASE REPORT AND REVIEW OF THE LITERATURE

Renal cell carcinoma (RCC), the most common solid lesion of the kidney, accounts for approximately 2%-3% of all malignancies among adults. Clear cell carcinoma and papillary cell carcinoma are the most common types of renal tumors. Some case reports have described synchronous benign and malignant tumors in the same kidney. In particular, angiomyolipoma and RCC in patients with tuberous sclerosis (TSC) and non-TSC have been reported many times in the literature. However, unilateral concordance of malignant renal tumors is very rare; thus, only few cases have been reported in the literature.Here we report the case of a 58-year-old male who had ipsilateral synchronous mucinous tubular and spindle cell carcinoma (MTSCC) and clear cell papillary renal cell carcinoma (CCPRCC). Both cancers are rare and relatively recently defined subtypes of RCC. Additionally, both were successfully treated using partial nephrectomy. MTSCC has been a distinct entity in the World Health Organization classification of kidney tumors since 2004. The classic type of MTSCC is characterized by small elongated tubules lined with clear cuboidal or spindle cells with mucinous stroma. Neoplastic cells always exhibit low-grade histological features. However, unclassified variants of MTSCC, such as mucin-poor, papillary, high-grade, and sarcomatoid variants, have also been reported. MTSCC is considered to have a relatively good prognosis, but some patients with poor prognoses have recently been reported. CCPRCC is a recently recognized entity and represents the fourth most common variant of RCC. It has unique morphological and immunohistochemical features and shows indolent clinical behavior. Microscopically, CCPRCC may mimic other RCCs with clear cell features, such as clear cell RCC, translocation RCC, and papillary RCC, with clear cell changes. In 2006, CCPRCC was described as a subtype of renal tumors in patients with end-stage renal disease. However, currently, CCPRCC has also been shown to occur in kidneys with normal function.To the best of our knowledge, this is the first report of ipsilateral synchronous MTSCC and CCPRCC, which we present with a review of the pertinent literature.

Radiomic Features and Machine Learning for the Discrimination of Renal Tumor Histological Subtypes: A Pragmatic Study Using Clinical-Routine Computed Tomography.

Simple SummaryThis study evaluates how advanced image analyses (radiomic features) and machine learning algorithms can help to distinguish subtypes of kidney tumors in computed tomography (CT) images, which is important for further patient treatment. For 201 patients, the image analyses showed a moderate performance, but robustly performed across various imaging centers and even in cases with suboptimal image quality. In particular, distinguishing one specific subtype of kidney tumor (oncocytomas) from other subtypes proves to be challenging. The algorithms presented in this study can help in the clinical decision-making process for kidney tumor patients, for example, to decide whether to perform kidney surgery or not.This study evaluates the diagnostic performance of radiomic features and machine learning algorithms for renal tumor subtype assessment in venous computed tomography (CT) studies from clinical routine. Patients undergoing surgical resection and histopathological assessment of renal tumors at a tertiary referral center between 2012 and 2019 were included. Preoperative venous-phase CTs from multiple referring imaging centers were segmented, and standardized radiomic features extracted. After preprocessing, class imbalance handling, and feature selection, machine learning algorithms were used to predict renal tumor subtypes using 10-fold cross validation, assessed as multiclass area under the curve (AUC). In total, n = 201 patients were included (73.7% male; mean age 66 ± 11 years), with n = 131 clear cell renal cell carcinomas (ccRCC), n = 29 papillary RCC, n = 11 chromophobe RCC, n = 16 oncocytomas, and n = 14 angiomyolipomas (AML). An extreme gradient boosting algorithm demonstrated the highest accuracy (multiclass area under the curve (AUC) = 0.72). The worst discrimination was evident for oncocytomas vs. AML and oncocytomas vs. chromophobe RCC (AUC = 0.55 and AUC = 0.45, respectively). In sensitivity analyses excluding oncocytomas, a random forest algorithm showed the highest accuracy, with multiclass AUC = 0.78. Radiomic feature analyses from venous-phase CT acquired in clinical practice with subsequent machine learning can discriminate renal tumor subtypes with moderate accuracy. The classification of oncocytomas seems to be the most complex with the lowest accuracy.

Fumarate Hydratase–Deficient Renal Cell Carcinoma: A Review

Abstract Fumarate hydratase (FH)–deficient renal cell carcinoma (RCC) has emerged in recent years as a subtype of renal tumors that show diverse morphologic patterns with predominance of papillary architecture. Most of these tumors show high-grade cytologic features and at least focally prominent eosinophilic macronucleoli with perinuclear halos. Infrequently, these tumors show low-grade oncocytic cytologic features. Fumarate hydratase–deficient RCCs are characterized by inactivating FH gene mutations resulting in FH loss and 2-succinocysteine [2SC] accumulation, demonstrable by immunohistochemistry. A vast majority of these tumors occur in the setting of hereditary leiomyomatosis and RCC syndrome. Fumarate hydratase–deficient RCCs show slight male preponderance and present at relatively younger age. These tumors are often locally advanced at the time of presentation. Prospective recognition of these tumors upon histologic examination is of paramount importance not only for the appropriate management of the patient but also for a potential to detect undiagnosed hereditary leiomyomatosis and RCC syndrome in at-risk family members.

471 - Coarse texture in contrast-enhanced CT as a predictor of renal tumor subtype and grade

471 - Coarse texture in contrast-enhanced CT as a predictor of renal tumor subtype and grade