Malignant Renal Masses Research Articles

Radiomics Applications in Renal Tumor Assessment: A Comprehensive Review of the Literature.

Radiomics texture analysis offers objective image information that could otherwise not be obtained by radiologists′ subjective radiological interpretation. We investigated radiomics applications in renal tumor assessment and provide a comprehensive review. A detailed search of original articles was performed using the PubMed-MEDLINE database until 20 March 2020 to identify English literature relevant to radiomics applications in renal tumor assessment. In total, 42 articles were included in the analysis and divided into four main categories: renal mass differentiation, nuclear grade prediction, gene expression-based molecular signatures, and patient outcome prediction. The main area of research involves accurately differentiating benign and malignant renal masses, specifically between renal cell carcinoma (RCC) subtypes and from angiomyolipoma without visible fat and oncocytoma. Nuclear grade prediction may enhance proper patient selection for risk-stratified treatment. Radiomics-predicted gene mutations may serve as surrogate biomarkers for high-risk disease, while predicting patients’ responses to targeted therapies and their outcomes will help develop personalized treatment algorithms. Studies generally reported the superiority of radiomics over expert radiological interpretation. Radiomics provides an alternative to subjective image interpretation for improving renal tumor diagnostic accuracy. Further incorporation of clinical and imaging data into radiomics algorithms will augment tumor prediction accuracy and enhance individualized medicine.

Deep learning based classification of solid lipid-poor contrast enhancing renal masses using contrast enhanced CT.

Establish a workflow that utilizes convolutional neural nets (CNN) to classify solid, lipid-poor, contrast enhancing renal masses using multiphase contrast enhanced CT (CECT) images and to assess the performance of the resulting network. In this institutional review board approved study of 143 patients with predominantly solid, lipid-poor, contrast enhancing renal lesions (46 benign and 97 malignant), patients with a pre-operative multiphase CECT of the abdomen and pelvis obtained between June 2009 and June 2015 were retrospectively queried. Benign renal masses included oncocytoma and lipid-poor angiomyolipoma and the malignant group included clear cell, papillary, and chromophobe carcinomas.Region of interests of whole tumor volumes were manually segmented, and CT phase images with the largest cross-section of the segmented tumor in the axial plane were used for assessment. Post-surgical pathological evaluation was used to establish diagnosis.The segmented images of renal masses were used as input to a CNN. The data were augmented and split into training (83.9%) and validation sets (16.1%) to determine the hyperparameters of the CNN. Thereafter. the performance of the resulting CNN was quantified using eightfold cross-validation. The CNN-based classifier demonstrated an overall accuracy of 78% (95% confidence interval: 76-80%), sensitivity of 70% (95% confidence interval: 66-74%), specificity of 81% (79-83%) and an area under the curve of 0.82. A CNN-based classifier to diagnose solid enhancing malignant renal masses based on multiphase CECT images was developed. It was established that a CNN-based classifier could be trained to accurately distinguish malignant renal lesions.

Discriminating malignant and benign clinical T1 renal masses on computed tomography: A pragmatic radiomics and machine learning approach.

The aim of this study was to discriminate malignant and benign clinical T1 renal masses on routinely acquired computed tomography (CT) images using radiomics and machine learning techniques.Adult patients undergoing surgical resection and histopathological analysis of clinical T1 renal masses were included. Preoperative CT studies in venous phase from multiple referring centers were included, without restriction to specific CT scanners, slice thickness, or degrees of artifacts. Renal masses were segmented and 120 standardized radiomic features extracted. Machine learning algorithms were used to predict malignancy of renal masses using radiomics features and cross-validation. Diagnostic accuracy of machine learning models and assessment by independent blinded radiologists were compared based on the gold standard of histopathologic diagnosis.A total of 94 patients met inclusion criteria (benign renal masses: n = 18; malignant: n = 76). CT studies from 18 different scanners were assessed with median slice thickness of 2.5 mm and artifacts in 15 cases (15.9%).Area under the receiver-operating-characteristics curve (AUC) of random forest (random forest [RF], AUC = 0.83) was significantly higher compared to the radiologists (AUC = 0.68, P = .047). Sensitivity was significantly higher for RF versus radiologists (0.88 vs 0.80, P = .045), whereas specificity was numerically higher for RF (0.67 vs 0.50, P = .083).Although limited by an overall small sample size and few benign renal tumors, a radiomic features and machine learning approach suggests a high diagnostic accuracy for discrimination of malignant and benign clinical T1 renal masses on venous phase CT. The presented algorithm robustly outperforms human readers in a real-life scenario with nonstandardized imaging studies from various referring centers.

MP18-14 CHARACTERISING DNA METHYLATION PATTERNS IN TISSUE AND CIRCULATING TUMOUR DNA TO ENABLE DIFFERENTIATION OF SMALL RENAL MASSES

You have accessJournal of UrologyKidney Cancer: Basic Research & Pathophysiology II (MP18)1 Apr 2020MP18-14 CHARACTERISING DNA METHYLATION PATTERNS IN TISSUE AND CIRCULATING TUMOUR DNA TO ENABLE DIFFERENTIATION OF SMALL RENAL MASSES Sabrina Rossi*, Sara Pita, Anne Babbage, Gahee Park, Radoslaw Lach, Christopher Smith, Kevin Brennan, Tom Mitchell, Anne Warren, Olivier Gevaert, Charlie Massie, Grant Stewart, and DIAMOND Biobank Study Group Sabrina Rossi*Sabrina Rossi* More articles by this author , Sara PitaSara Pita More articles by this author , Anne BabbageAnne Babbage More articles by this author , Gahee ParkGahee Park More articles by this author , Radoslaw LachRadoslaw Lach More articles by this author , Christopher SmithChristopher Smith More articles by this author , Kevin BrennanKevin Brennan More articles by this author , Tom MitchellTom Mitchell More articles by this author , Anne WarrenAnne Warren More articles by this author , Olivier GevaertOlivier Gevaert More articles by this author , Charlie MassieCharlie Massie More articles by this author , Grant StewartGrant Stewart More articles by this author , and DIAMOND Biobank Study GroupDIAMOND Biobank Study Group More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000843.014AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Small renal masses (SRM) represent a diagnostic challenge. Indeed, ∼20% of SRM removed at surgery are found to be benign post-operatively. Renal biopsy may be non-diagnostic due to small tumour size, challenging anatomy or tumour heterogeneity. Circulating tumour DNA (ctDNA) analysis of DNA methylation in plasma or urine may overcome sampling bias associated with genetic intratumoral heterogeneity and offer a non-invasive method to derive a diagnosis. To test whether epigenetic markers differentiate pathological subtypes of renal masses we aim to (a) analyse multi-region samples from patients with renal tumours to map the landscape of DNA methylation heterogeneity and (b) evaluate methylation markers in triplicates of tissue, plasma and urine. METHODS: We recruited a cohort of patients across the RCC disease spectrum, from small renal masses to metastatic disease, including different pathological subtypes. Ethical approval was obtained (DIAMOND biobank; REC ID 03/018). Multi-region kidney tumour samples were collected from the nephrectomy specimen, including adjacent normal tissue, as well as urine and plasma samples from the same patients. Methylation analysis was performed in tissue using the Illumina EPIC Methyl Capture library preparation kit, with post capture bisulfite conversion. RESULTS: Tumour and normal samples were collected from 75 individuals with clear cell (N=35), chromophobe (N=10), papillary (N=20) RCC and oncocytoma (N=10). Additionally, we sequenced 142 multi-region samples from a subset of 26 patients and performed epigenetic phylogenetic analyses. We identified sets of differentially methylated cytosines at base-pair resolution in tumour tissue that (a) classify pathological subtypes of RCC and oncocytomas and (b) represent early ‘stem’ markers for ctDNA analysis. We present a summary of epigenetic clonal evolution and identify markers for high-sensitivity targeted analysis of DNA methylation in liquid samples. CONCLUSIONS: We evaluate DNA methylation in a large cohort of patients with pathological subtypes of renal tumours. This may represent a promising target for non-invasive liquid biopsy to differentiate benign from malignant small renal masses. Source of Funding: SHR is funded by a Cancer Research UK PhD Fellowship. © 2020 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 203Issue Supplement 4April 2020Page: e240-e241 Advertisement Copyright & Permissions© 2020 by American Urological Association Education and Research, Inc.MetricsAuthor Information Sabrina Rossi* More articles by this author Sara Pita More articles by this author Anne Babbage More articles by this author Gahee Park More articles by this author Radoslaw Lach More articles by this author Christopher Smith More articles by this author Kevin Brennan More articles by this author Tom Mitchell More articles by this author Anne Warren More articles by this author Olivier Gevaert More articles by this author Charlie Massie More articles by this author Grant Stewart More articles by this author DIAMOND Biobank Study Group More articles by this author Expand All Advertisement PDF downloadLoading ...

Anti-G250 nanobody-functionalized nanobubbles targeting renal cell carcinoma cells for ultrasound molecular imaging

Traditional imaging examinations have difficulty in identifying benign and malignant changes in renal masses. This difficulty may be solved by ultrasound molecular imaging based on targeted nanobubbles, which could specifically enhance the ultrasound imaging of renal cell carcinomas (RCC) so as to discriminate benign and malignant renal masses. In this study, we aimed to prepare anti-G250 nanobody-functionalized targeted nanobubbles (anti-G250 NTNs) by coupling anti-G250 nanobodies to lipid nanobubbles and to verify their target specificity and binding ability to RCC cells that express G250 antigen and their capacity to enhance ultrasound imaging of RCC xenografts. Anti-G250 nanobodies were coupled to the lipid nanobubbles using the biotin-streptavidin bridge method. The average particle diameter of the prepared anti-G250 NTNs was 446 nm. Immunofluorescence confirmed that anti-G250 nanobodies were uniformly distributed on the surfaces of nanobubbles. In vitro experiments showed that the anti-G250 NTNs specifically bound to G250-positive 786-O cells and HeLa cells with affinities of 88.13% ± 4.37% and 71.8% ± 5.7%, respectively, and that they did not bind to G250-negative ACHN cells. The anti-G250 NTNs could significantly enhance the ultrasound imaging of xenograft tumors arising from 786-O cells and HeLa cells compared with blank nanobubbles, while the enhancement was not significant for xenograft tumors arising from ACHN cells. Immunofluorescence of tumor tissue slices confirmed that the anti-G250 NTNs could enter the tissue space through tumor blood vessels and bind to tumor cells specifically. In conclusion, anti-G250 nanobody-functionalized targeted nanobubbles could specifically bind to G250-positive RCC cells and enhance the ultrasound imaging of G250-positive RCC xenografts. This study has high-potential clinical application value for the diagnosis and differential diagnosis of renal tumors.

Prediction of Benign and Malignant Solid Renal Masses: Machine Learning-Based CT Texture Analysis

This study aimed to investigate whether benign and malignant renal solid masses could be distinguished through machine learning (ML)-based computed tomography (CT) texture analysis. Seventy-nine patients with 84 solid renal masses (21 benign; 63 malignant) from a single center were included in this retrospective study. Malignant masses included common renal cell carcinoma (RCC) subtypes: clear cell RCC, papillary cell RCC, and chromophobe RCC. Benign masses are represented by oncocytomas and fat-poor angiomyolipomas. Following preprocessing steps, a total of 271 texture features were extracted from unenhanced and contrast-enhanced CT images. Dimension reduction was done with a reliability analysis and then with a feature selection algorithm. A nested-approach was used for feature selection, model optimization, and validation. Eight ML algorithms were used for the classifications: decision tree, locally weighted learning, k-nearest neighbors, naive Bayes, logistic regression, support vector machine, neural network, and random forest. The number of features with good reproducibility was 198 for unenhanced CT and 244 for contrast-enhanced CT. Random forest algorithm demonstrated the best predictive performance using five selected contrast-enhanced CT texture features. The accuracy and area under the curve metrics were 90.5% and 0.915, respectively. Having eliminated the highly collinear features from the analysis, the accuracy and area under the curve values slightly increased to 91.7% and 0.916, respectively. ML-based contrast-enhanced CT texture analysis might be a potential method for distinguishing benign and malignant solid renal masses with satisfactory performance.

Quantitative Analysis of Multiphase Contrast-Enhanced CT Images: A Pilot Study of Preoperative Prediction of Fat-Poor Angiomyolipoma and Renal Cell Carcinoma.

OBJECTIVE. The objective of our study was to preoperatively predict fat-poor angiomyolipoma (fp-AML) and renal cell carcinoma (RCC) by conducting quantitative analysis of contrast-enhanced CT images. MATERIALS AND METHODS. One hundred fifteen patients with a pathologic diagnosis of fp-AML or RCC from a single institution were randomly allocated into a train set (tumor size: mean ± SD, 4.50 ± 2.62 cm) and test set (tumor size: 4.32 ± 2.73 cm) after data augmentation. High-dimensional histogram-based features, texture-based features, and Laws features were first extracted from CT images and were then combined as different combinations sets to construct a logistic prediction model based on the least absolute shrinkage and selection operator procedure for the prediction of fp-AML and RCC. Prediction performances were assessed by classification accuracy, area under the ROC curve (AUC), positive predictive value, negative predictive value, true-positive rate, and false-positive rate (FPR). In addition, we also investigated the effects of different gray-scales of quantitative features on prediction performances. RESULTS. The following combination sets of features achieved satisfying performances in the test set: histogram-based features (mean AUC = 0.8492, mean classification accuracy = 91.01%); histogram-based features and texture-based features (mean AUC = 0.9244, mean classification accuracy = 91.81%); histogram-based features and Laws features (mean AUC = 0.8546, mean classification accuracy = 88.76%); and histogram-based features, texture-based features, and Laws features (mean AUC = 0.8925, mean classification accuracy = 90.36%). The different quantitative gray-scales did not have an obvious effect on prediction performances. CONCLUSION. The integration of histogram-based features with texture-based features and Laws features provided a potential biomarker for the preoperative diagnosis of fp-AML and RCC. The accurate diagnosis of benign or malignant renal masses would help to make the clinical decision for radical surgery or close follow-up.

Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer.

The purpose of the study was to provide a comprehensive review of recent machine learning (ML) and deep learning (DL) applications in urological practice. Numerous studies have reported their use in the medical care of various urological disorders; however, no critical analysis has been made to date. A detailed search of original articles was performed using the PubMed MEDLINE database to identify recent English literature relevant to ML and DL applications in the fields of urolithiasis, renal cell carcinoma (RCC), bladder cancer (BCa), and prostate cancer (PCa). In total, 43 articles were included addressing these four subfields. The most common ML and DL application in urolithiasis is in the prediction of endourologic surgical outcomes. The main area of research involving ML and DL in RCC concerns the differentiation between benign and malignant small renal masses, Fuhrman nuclear grade prediction, and gene expression-based molecular signatures. BCa studies employ radiomics and texture feature analysis for the distinction between low- and high-grade tumors, address accurate image-based cytology, and use algorithms to predict treatment response, tumor recurrence, and patient survival. PCa studies aim at developing algorithms for Gleason score prediction, MRI computer-aided diagnosis, and surgical outcomes and biochemical recurrence prediction. Studies consistently found the superiority of these methods over traditional statistical methods. The continuous incorporation of clinical data, further ML and DL algorithm retraining, and generalizability of models will augment the prediction accuracy and enhance individualized medicine.

Clinical utility of contrast-enhanced ultrasonography in the diagnosis of benign and malignant small renal masses among Asian population.

We assessed the clinical utility of contrast‐enhanced ultrasonography (CEUS) in the diagnosis of benign and malignant small renal masses using a meta‐analysis of diagnostic test. We performed a comprehensive online search in the following database including PubMed, Embase, Web of Science, Wanfang, and Chinese National Knowledge Infrastructure from the inception to August 25, 2019. the following index were calculated for assessing the diagnostic ability, including sensitivity, specificity, diagnostic odds ratio (DOR), negative likelihood ratio (NLR), positive likelihood ratio (PLR), area under the curve (AUC) with 95% confidence intervals (CIs). Seventeen studies were included in the qualitative and quantitative analyses. The overall sensitivity was 0.93 with 95% CI of 0.88‐0.95. The specificity was 0.71 and the 95% CI was 0.60‐0.80. The pooled AUC was 0.91 (95% CI: 0.88‐0.93). The diagnostic odds ratio was 31 (95% CI: 21‐45). The NLR and PLR were 0.10 (95% CI: 0.07‐0.15) and 3.2(95% CI: 2.3‐4.4), respectively. There is a slight heterogeneity within studies. The subgroup analysis was also performed. For retrospective and perspective, the sensitivity and specificity were 0.93, 0.92 and 0.71, 0.73; For different diameter lesions, the sensitivity and specificity were 0.93, 0.94 and 0.64, 0.74; For sample size (≤median vs. >median), the sensitivity and specificity were 0.94, 0.93 and 0.67, 0.77. The Deek's funnel plot asymmetry test in indicated no publication bias. The CEUS have a high diagnostic ability in differentiating benign and malignant small renal masses among Asian population.

Contrast-Enhanced Ultrasound in Renal Imaging and Intervention.

In recent years, there has been renewed interest in the use of contrast-enhanced ultrasound (CEUS) in abdominal imaging and intervention. The goal of this article is to review the practical applications of CEUS in the kidney, including renal mass characterization, treatment monitoring during and after percutaneous ablation, and biopsy guidance. Current evidence suggests that CEUS allows accurate differentiation of solid and cystic renal masses and is an acceptable alternative to either computed tomography (CT) or magnetic resonance imaging (MRI) for characterization of indeterminate renal masses. CEUS is sensitive and specific for diagnosing residual or recurrent renal cell carcinoma (RCC) following percutaneous ablation. Furthermore, given its excellent spatial and temporal resolution, CEUS is well suited to demonstrate tumoral microvascularity associated with malignant renal masses and is an effective complement to conventional grayscale ultrasound (US) for percutaneous biopsy guidance. Currently underutilized, CEUS is an important problem-solving tool in renal imaging and intervention whose role will continue to expand in coming years.

Relationship between plasma Atherogenic index and final pathology of Bosniak III-IV renal masses: a retrospective, single-center study

BackgroundThere is an increased incidence of renal cell carcinoma (RCC) in patients with metabolic syndrome who usually have high levels of serum triglyceride (TG) and low high-density lipoprotein-cholesterol (HDL-C). Plasma atherogenic index (PAI) is the logarithmic ratio of serum TG level to HDL-C and related to cardiovascular diseases. In this study, we aimed to determine the accuracy of PAI in determining renal malignancy in localized renal masses preoperatively.MethodsTotally 169 patients who were diagnosed with Bosniak III-IV lesions by imaging modalities and treated in our hospital with partial or radical nephrectomy were retrospectively analyzed using institutional renal cancer database between 2013 and 2018. Preoperative images were evaluated by two experienced radiologists. The patients were divided into two groups according to their postoperative pathological diagnosis as malignant or benign tumors. The PAI of each patient was calculated and the statistical significance of PAI in predicting malignancy for renal masses was analyzed using uni- and multivariable analyses.ResultsOf patients, 109 (64.5%) were males and 60 (35.5%) were females with a median age of 61 (33–84) years. Median tumor size was 6.5 (2–18) cm. Pathological diagnosis was malignant in 145 (85.8%) and benign in 24 (14.2%) patients. There was no statistically significant difference in serum TG levels between malignant and benign cases (p > 0.05). The HDL-C levels were significantly lower in malignant cases (p = 0.001). Median PAI value was 0.63 (0.34–1.58) and significantly higher in malignant cases (p = 0.003). The PAI cut-off value for malignancy was ≥0.34. The sensitivity was calculated as 88.2% and specificity as 45.8%, the positive predictive value as 90.8, negative predictive value as 39.3, and odds ratio as 6.37 (95% CI: 2.466–16.458). In multivariable analysis, gender, smoking status, and hypertension had no effect on malignancy, whereas PAI and HDL-C were independent risk factors (p = 0.003 and p = 0.003, respectively). The risk of malignancy was 5.019 times higher, when PAI was > 0.34 (95% CI: 1.744–14.445) in multivariable logistic regression analysis.ConclusionsThe PAI can be used as a predictive tool in suspicion of malignant renal masses. In case of a benign pathology, PAI levels may be encouraging for surgeons for nephron-sparing surgery.

Diagnostic Performance of Ultrasound Shear Wave Elastography in Solid Small (≤4 cm) Renal Parenchymal Masses

The aim of the study was to analyze the diagnostic performance of shear wave elastography (SWE) in differentiating between malignant and benign solid renal parenchymal masses ≤4 cm, compared with conventional ultrasound. A total of 20 healthy volunteers and 117 patients had been included in this study. Conventional ultrasound and SWE were performed in all volunteers and patients. The elasticity of healthy cortex and the elastic parameters of tumors such as mean elasticity (Emean), minimum elasticity (Emin), maximum elasticity (Emax), standard deviation and elasticity ratio of the lesion to surrounding cortex (Eratio) were measured on SWE images. Diagnostic performance of SWE was compared with that of conventional ultrasound. The cortical elasticity values of healthy right and left kidneys were 4.7 ± 1.7 and 4.5 ± 1.5 kPa, respectively. Of the 117 renal tumors, 68 were renal cell carcinomas (RCCs) and 49 were benign. Emean, Emin and Eratio were significantly lower in RCCs compared with benign lesions: Emean 7.2 ± 2.5 kPa versus 10.0 ± 2.4 kPa, Emin 2.5 ± 2.4 kPa versus 5.6 ± 2.3 kPa, Eratio 1.6 ± 0.5 versus 2.2 ± 0.6 (all p values < 0.001). The cutoff values of 9.15 kPa for Emean, 3.55 kPa for Emin and 1.99 for Eratio had the highest areas under the receiver operating characteristics curve (0.801 for Emean, 0.832 for Emin and 0.806 for Eratio). Combining Emean, Emin and Eratio with conventional ultrasound improved the specificity for predicting RCCs to 87.8%, but the sensitivity was not increased.

Renal Masses: Evaluation with Contrast-Enhanced Ultrasound, with a Special Focus on the Pseudocapsule Sign

The aim of this study was to analyze the diagnostic performance of contrast-enhanced ultrasound (CEUS) in differentiating between benign and malignant renal masses, with a special emphasis on the value of the pseudocapsule sign. A total of 163 consecutive patients with 163 renal masses were involved. The conventional ultrasonography and CEUS features were assessed. Sensitivity, specificity and the area under the receiver operating characteristic curve (Az) were calculated for qualitative CEUS, and a multivariate analysis was performed to analyze the correlation between the sonographic features and malignancy. Time to peak (TTP) and peak intensity (PI) were compared between benign and malignant renal masses for quantitative CEUS analysis in 72 of 163 patients. Intraclass correlations were calculated for variability in intensity and time parameters between qualitative and quantitative evaluation. Among all qualitative CEUS features, the pseudocapsule sign showed the highest Az (0.777; 95% confidence interval: 0.701–0.853) and yielded the highest sensitivity (67.4%) and specificity (88.0%); multivariate logistic regression analysis showed that the pseudocapsule sign and color Doppler flow imaging patterns were the two strongest independent predictors for malignancy. For quantitative CEUS analysis, higher PI and shorter TTP were found in malignant renal masses than those in benign ones. The Intraclass correlation coefficient values among qualitative and the quantitative assessments were 0.00 for time and 0.03 for intensity. The pseudocapsule sign offered the most efficient performance among all the qualitative and quantitative CEUS features.

Superb microvascular imaging is a rational choice for accurate Bosniak classification of renal cystic masses.

Bosniak classification system provides a fine imaging evaluation for the malignant cystic renal masses. Superb microvascular imaging (SMI) is a new ultrasonic technique which apply advanced clutter suppression to reflect microflow information. The aim of this study was to evaluate the performance of ultrasound Bosniak classification aided by SMI in diagnosis of cystic renal masses. By comparing with contrast-enhanced ultrasound (CEUS) and pathology, we evaluated the sensitivity, specificity and accuracy of conventional ultrasound and SMI combination in the diagnosis of renal cystic masses. Color Doppler Flow image (CDFI) and SMI had significant difference in evaluation the blood flow and Bosniak classification for cystic renal mass of IIf, III and IV (p = 0.020). SMI was consistent with CEUS for cystic renal mass Bosniak classification of IIf, III and IV. Although, CEUS had highest sensitivity of 97.4%, SMI had the highest area under curve in differential diagnosis malignance from benign masses [area under curve = 0.869 (0.743 - 0.995), p < 0.001]. SMI can display better in observing blood flow in septa and solid structures of renal cystic lesions compared with CDFI, thus, it can perform more accurate Bosniak classification for renal cystic mass. SMI and CEUS are consistent in Bosniak classification. Bosniak classification aided by SMI maybe an accurate non-invasive ultrasonic examination in distinguishing benign and malignant renal cystic lesions. Conventional ultrasound had limited ability to distinguish malignance in Bosniak classifications IIf and III. SMI can display better in observing blood flow in septa and solid structures of renal cystic lesions compared with CDFI.

Deep learning and radiomics: the utility of Google TensorFlow™ Inception in classifying clear cell renal cell carcinoma and oncocytoma on multiphasic CT.

Currently, all solid enhancing renal masses without microscopic fat are considered malignant until proven otherwise and there is substantial overlap in the imaging findings of benign and malignant renal masses, particularly between clear cell RCC (ccRCC) and benign oncocytoma (ONC). Radiomics has attracted increased attention for its utility in pre-operative work-up on routine clinical images. Radiomics based approaches have converted medical images into mineable data and identified prognostic imaging signatures that machine learning algorithms can use to construct predictive models by learning the decision boundaries of the underlying data distribution. The TensorFlow™ framework from Google is a state-of-the-art open-source software library that can be used for training deep learning neural networks for performing machine learning tasks. The purpose of this study was to investigate the diagnostic value and feasibility of a deep learning-based renal lesion classifier using open-source Google TensorFlow™ Inception in differentiating ccRCC from ONC on routine four-phase MDCT in patients with pathologically confirmed renal masses. With institutional review board approval for this 1996 Health Insurance Portability and Accountability Act compliant retrospective study and a waiver of informed consent, we queried our institution's pathology, clinical, and radiology databases for histologically proven cases of ccRCC and ONC obtained between January 2000 and January 2016 scanned with a an intravenous contrast-enhanced four-phase renal mass protocol (unenhanced (UN), corticomedullary (CM), nephrographic (NP), and excretory (EX) phases). To extract features to be used for the machine learning model, the entire renal mass was contoured in the axial plane in each of the four phases, resulting in a 3D volume of interest (VOI) representative of the entire renal mass. We investigated thirteen different approaches to convert the acquired VOI data into a set of images that adequately represented each tumor which was used to train the final layer of the neural network model. Training was performed over 4000 iterations. In each iteration, 90% of the data were designated as training data and the remaining 10% served as validation data and a leave-one-out cross-validation scheme was implemented. Accuracy, sensitivity, specificity, positive (PPV) and negative predictive (NPV) values, and CIs were calculated for the classification of the thirteen processing modes. We analyzed 179 consecutive patients with 179 lesions (128 ccRCC and 51 ONC). The ccRCC cohort had a mean size of 3.8cm (range 0.8-14.6cm) and the ONC cohort had a mean lesion size of 3.9cm (range 1.0-13.1cm). The highest specificity and PPV (52.9% and 80.3%, respectively) were achieved in the EX phase when we analyzed the single mid-slice of the tumor in the axial, coronal and sagittal plane, and when we increased the number of mid-slices of the tumor to three, with an accuracy of 75.4%, which also increased the sensitivity to 88.3% and the PPV to 79.6%. Using the entire tumor volume also showed that classification performance was best in the EX phase with an accuracy of 74.4%, a sensitivity of 85.8% and a PPV of 80.1%. When the entire tumor volume, plus mid-slices from all phases and all planes presented as tiled images, were submitted to the final layer of the neural network we achieved a PPV of 82.5%. The best classification result was obtained in the EX phase among the thirteen classification methods tested. Our proof of concept study is the first step towards understanding the utility of machine learning in the differentiation of ccRCC from ONC on routine CT images. We hope this could lead to future investigation into the development of a multivariate machine learning model which may augment our ability to accurately predict renal lesion histology on imaging.

IJU this issue

This, the latest issue of the International Journal of Urology, covers a wide range of topics including three Review Articles, 17 Original Articles and eight Urological Notes. In their Review Article, Johnin et al. (Otsu, Japan) reconsider the indications for voiding cystourethrography and the procedure itself in view of the distress and anxiety it causes pediatric patients, despite the fact it is considered essential for investigation of lower urogenital tract diseases in children. The other two reviews provide up-to-date information on upper tract urothelial carcinomas and the endourological management of urolithiasis. In their Original Article, Song et al. (St. Louis, USA) report the utility of urine aquaporin 1 and perilipin 2 as new non-invasive biomarkers for distinguishing benign from malignant small renal masses. The authors have confirmed that the two biomarkers have high sensitivity and specificity for detecting clear cell and papillary renal cell carcinoma. Their results imply that the use of these markers might reduce both the number of operations for benign renal masses and the number of renal biopsies required for diagnosis of malignant renal lesions. The Original Article by Harada et al. (Kobe, Japan) provides detailed data on the treatment patterns and outcomes in patients with unresectable or metastatic renal cell carcinoma (RCC) in a real-world setting in Japan. As few previous studies have summarized such data, this study is noteworthy in clarifying the actual clinical situation in Japan. However, as immune checkpoint inhibitors are becoming a standard form of treatment for advanced RCC in the place of tyrosine kinase inhibitors, data from similar investigations carried out several years later would be interesting. In their Urological Note, Shiraishi et al. (Kobe, Japan) describe a unique case of right RCC involving the inferior vena cava in which the surgical specimen was found to have become completely necrotic after sequential treatment with pazopanib followed by nivolumab, even though the tumor mass was still present in both the right kidney and inferior vena cava extending to just above the diaphragm. This case report provides two important pieces of information. One is that sequential treatment with a tyrosine kinase inhibitor followed by nivolumab might be an optimal form of presurgical neoadjuvant therapy. The other is that a pathological response appeared to have been obtained even though the effect was not clinically complete. Clinicians sometimes encounter patients with metastatic RCC who show a good outcome after immuno-oncology drugs, even though the tumor response might not be complete. The reason for this could be related to this mechanism. Inoue et al. (Kyoto, Japan) report some important results of primary targeted focal cryotherapy for patients with magnetic resonance imaging-visible, magnetic resonance–ultrasound image fusion targeted biopsy-proven clinically localized prostate cancer. The authors found that the combination of both multiparametric magnetic resonance imaging (not only both diffusion-weighted and T2-weighted imaging, but also contrast magnetic resonance imaging) and prostate-specific antigen variables (prostate-specific antigen <4 ng/mL and rate of prostate-specific antigen decrease >50%) might provide possible follow-up criteria for suggesting the technical success of focal therapy and/or indications for follow-up biopsy. Currently, very few data are available for defining what form of biochemical control is appropriate for confirming treatment success when an appreciable proportion of the prostate gland is left untreated by focal therapy. There is also a lack of clarity regarding the optimal selection of imaging sequences for the detection of remaining (insufficiently ablated) or recurrent prostate cancer. Therefore, the authors’ criteria will be useful to other focal therapists. None declared.

Comparison of Monoexponential, Biexponential, Stretched-Exponential, and Kurtosis Models of Diffusion-Weighted Imaging in Differentiation of Renal Solid Masses.

ObjectiveTo compare various models of diffusion-weighted imaging including monoexponential apparent diffusion coefficient (ADC), biexponential (fast diffusion coefficient [Df], slow diffusion coefficient [Ds], and fraction of fast diffusion), stretched-exponential (distributed diffusion coefficient and anomalous exponent term [α]), and kurtosis (mean diffusivity and mean kurtosis [MK]) models in the differentiation of renal solid masses.Materials and MethodsA total of 81 patients (56 men and 25 women; mean age, 57 years; age range, 30–69 years) with 18 benign and 63 malignant lesions were imaged using 3T diffusion-weighted MRI. Diffusion model selection was investigated in each lesion using the Akaike information criteria. Mann-Whitney U test and receiver operating characteristic (ROC) analysis were used for statistical evaluations.ResultsGoodness-of-fit analysis showed that the stretched-exponential model had the highest voxel percentages in benign and malignant lesions (90.7% and 51.4%, respectively). ADC, Ds, and MK showed significant differences between benign and malignant lesions (p < 0.05) and between low- and high-grade clear cell renal cell carcinoma (ccRCC) (p < 0.05). α was significantly lower in the benign group than in the malignant group (p < 0.05). All diffusion measures showed significant differences between ccRCC and non-ccRCC (p < 0.05) except Df and α (p = 0.143 and 0.112, respectively). α showed the highest diagnostic accuracy in differentiating benign and malignant lesions with an area under the ROC curve of 0.923, but none of the parameters from these advanced models revealed significantly better performance over ADC in discriminating subtypes or grades of renal cell carcinoma (RCC) (p > 0.05).ConclusionCompared with conventional diffusion parameters, α may provide additional information for differentiating benign and malignant renal masses, while ADC remains the most valuable parameter for differentiation of RCC subtypes and for ccRCC grading.

Septate uterus and recurrent pregnancy loss: An immunological perspective

The aim of the study was to analyze the diagnostic performance of shear wave elastography (SWE) in differentiating between malignant and benign solid renal parenchymal masses ≤4 cm, compared with conventional ultrasound. A total of 20 healthy volunteers and 117 patients had been included in this study. Conventional ultrasound and SWE were performed in all volunteers and patients. The elasticity of healthy cortex and the elastic parameters of tumors such as mean elasticity (Emean), minimum elasticity (Emin), maximum elasticity (Emax), standard deviation and elasticity ratio of the lesion to surrounding cortex (Eratio) were measured on SWE images. Diagnostic performance of SWE was compared with that of conventional ultrasound. The cortical elasticity values of healthy right and left kidneys were 4.7 ± 1.7 and 4.5 ± 1.5 kPa, respectively. Of the 117 renal tumors, 68 were renal cell carcinomas (RCCs) and 49 were benign. Emean, Emin and Eratio were significantly lower in RCCs compared with benign lesions: Emean 7.2 ± 2.5 kPa versus 10.0 ± 2.4 kPa, Emin 2.5 ± 2.4 kPa versus 5.6 ± 2.3 kPa, Eratio 1.6 ± 0.5 versus 2.2 ± 0.6 (all p values < 0.001). The cutoff values of 9.15 kPa for Emean, 3.55 kPa for Emin and 1.99 for Eratio had the highest areas under the receiver operating characteristics curve (0.801 for Emean, 0.832 for Emin and 0.806 for Eratio). Combining Emean, Emin and Eratio with conventional ultrasound improved the specificity for predicting RCCs to 87.8%, but the sensitivity was not increased.

Classification tree for the prediction of malignant disease and the prediction of non-diagnostic biopsies in patients with small renal masses.

Preoperative prediction of benign vs. malignant small renal masses (SRMs) remains a challenge. This study: 1) validates our previously published classification tree (CT) with an external cohort; 2) creates a new CT with the combined cohort; and 3) evaluates the RENAL and PADUA scoring systems for prediction of malignancy. This study includes a total of 818 patients with renal masses; 395 underwent surgical resection and 423 underwent biopsy. A CT to predict benign disease was developed using patient and tumour characteristics from the 709 eligible participants. Our CT is based on four parameters: tumour volume, symptoms, gender, and symptomatology. CART modelling was also used to determine if RENAL and PADUA scoring could predict malignancy. When externally validated with the surgical cohort, the predictive accuracy of the old CT dropped. However, by combining the cohorts and creating a new CT, the predictive accuracy increased from 74% to 87% (95% confidence interval 0.84-0.89). RENAL and PADUA score alone were not predictive of malignancy. One limitation was the lack of available histological data from the biopsy series. The validated old CT and new combined-cohort CT have a predictive value greater than currently published nomograms and single-biopsy cohorts. Overall, RENAL and PADUA scores were not able to predict malignancy.

Differentiation of Predominantly Solid Enhancing Lipid-Poor Renal Cell Masses by Use of Contrast-Enhanced CT: Evaluating the Role of Texture in Tumor Subtyping.

The purpose of this study was to assess the accuracy of a panel of texture features extracted from clinical CT in differentiating benign from malignant solid enhancing lipid-poor renal masses. In a retrospective case-control study of 174 patients with predominantly solid nonmacroscopic fat-containing enhancing renal masses, 129 cases of malignant renal cell carcinoma were found, including clear cell, papillary, and chromophobe subtypes. Benign renal masses-oncocytoma and lipid-poor angiomyolipoma-were found in 45 patients. Whole-lesion ROIs were manually segmented and coregistered from the standard-of-care multiphase contrast-enhanced CT (CECT) scans of these patients. Pathologic diagnosis of all tumors was obtained after surgical resection. CECT images of the renal masses were used as inputs to a CECT texture analysis panel comprising 31 texture metrics derived with six texture methods. Stepwise logistic regression analysis was used to select the best predictor among all candidate predictors from each of the texture methods, and their performance was quantified by AUC. Among the texture predictors aiding renal mass subtyping were entropy, entropy of fast-Fourier transform magnitude, mean, uniformity, information measure of correlation 2, and sum of averages. These metrics had AUC values ranging from good (0.80) to excellent (0.98) across the various subtype comparisons. The overall CECT-based tumor texture model had an AUC of 0.87 (p < 0.05) for differentiating benign from malignant renal masses. The CT texture statistical model studied was accurate for differentiating benign from malignant solid enhancing lipid-poor renal masses.