Benign Renal Tumors Research Articles

Is Size All That Matters? New Predictors of Complications and Bleeding in Renal Angiomyolipoma.

Renal angiomyolipoma (AML) is the most common benign renal tumor. Whilst generally asymptomatic, they can cause life-threatening bleeding. Selective angioembolization (SAE) may be used to treat large symptomatic and asymptomatic AMLs. We aimed to evaluate the efficacy of SAEfor symptomatic and asymptomatic renal AMLs and determine characteristics that predict spontaneous bleeding. Data were retrospectively collected from a prospectively maintained database from July 2011 to April 2022. Patients were included if AML was >4cm and they underwent subsequent SAE. Follow-up imaging was analyzed to calculate mean reduction in AML size. Clinical notes were reviewed to analyze lesion characteristics including vascularity, fat content and presence of aneurysm as well as post-procedural complications. 26 patients with 30 AMLs were identified. Interval of follow-up imaging ranged from 1 to 60 months. 25 AMLs were embolized electively with 5 emergency embolizations performed for bleeding. Mean reduction in AML volume was 41% at 3 months (p=0.013) and 63% at 12 months (p=0.007). All 5 bleeding AMLs had a rich vascularity with 60% also having either aneurysms or a low fat content. Complications included post-embolic syndrome (n=9), segmental renal parenchyma devascularization (n=3), acute bleeding requiring re-embolization (n=2), nephrectomy for ongoing bleeding (n=1) and delayed bleeding managed conservatively (n=1). No deterioration in renal function was observed. SAE is an effective procedure for managing symptomatic and asymptomatic renal AML, with minimal significant complications. AML vascularity, fat content and aneurysms may be useful characteristics to assess future risk of bleeding in patients with renal AML.

Renal Angiomyolipoma Associated with Renal Vein and Inferior Vena Cava Thrombosis: A Case Report

Angiomyolipoma (AML) is the most common benign renal mesenchymal neoplasm. This is a report of a 36-year-old female patient with AML with the involvement of the inferior vena cava (IVC) who was admitted to our hospital. The patient complained of mild right flank pain. CT scan results showed a hypo-dense mass with 47×72 mm dimensions at the right kidney›s lower pole suggesting renal AML. In MRI with contrast, venous thrombosis was detected in the right renal vein and IVC. Right radical nephrectomy and IVC thrombectomy were successfully conducted. Renal AML was confirmed by pathological findings, and the presence of tumor thrombosis was approved in the right renal vein and IVC. Although AML is generally benign and vascular invasion is a rare finding in this condition, imaging studies (including CT scans) should always be considered to determine the extent of vascular involvement and choose an appropriate therapeutic plan, including nephrectomy and thrombectomy in case of vascular involvement. Despite its benign nature, it should be considered that AML can invade venous structures in the kidneys. Early imaging studies and therapeutic interventions are necessary for obtaining the best outcome.

Development and validation of a machine learning-based CT radiomics model for differentiation of benign and malignant solid renal tumors

Development and validation of a machine learning-based CT radiomics model for differentiation of benign and malignant solid renal tumors

Value of miR-15b-5p combined with ultrasound imaging in early diagnosis of renal cell carcinoma

Renal cancer is one of the most common malignancies, and its incidence is increasing year by year, second only to prostate and bladder cancers. Therefore, early screening is of great significance to prevent and improve the prognosis of patients with renal cancer. Therefore, this study intends to observe the early diagnostic value of miR-15b-5p combined with Colour ultrasound imaging in renal cell carcinoma. In this study, the clinical samples of 76 patients with renal cell carcinoma diagnosed by pathology in our hospital from April 2020 to June 2022 were retrospectively collected as the research objects. Another 100 healthy people who underwent general physical examination in our hospital during the same period were selected to detect the expression level of miR-15b-5 in serum by RT-PCR together with the 76 experimental samples. Colour ultrasound imaging was used to detect the blood flow distribution around and inside the kidney of the patients with renal cancer, and the parameters were measured and compared with the gold standard for statistical analysis. The expression level of miR-15b-5 in renal cell carcinoma group was significantly higher than that in control group. Most of them showed renal hamartoma (40.79%). Benign renal tumors were mainly characterized by type I and II blood flow, while malignant renal tumors were characterized by type III and IV blood flow. Compared with the pathological gold standard, the diagnostic accuracy of ultrasound imaging was founded to be about 81.25%. Further ROC analysis showed that ultrasound imaging combined with miR-15b-5 detection could effectively improve the early screening value of renal cell carcinoma. We observed that miR-15b-5 has a specific expression level in the serum of patients with renal cell carcinoma, and its combination with ultrasound imaging can significantly improve the early detection of renal cell carcinoma. This approach is envisaged to be highly useful for, early diagnosis, intervention and management of patients with renal cell carcinoma.

A CT-based radiomics nomogram for differentiation of benign and malignant small renal masses (≤4 cm)

Rationale and ObjectivesBased on radiomics signature and clinical data, to develop and verify a radiomics nomogram for preoperative distinguish between benign and malignant of small renal masses (SRM). Materials and MethodsOne hundred and fifty-six patients with malignant (n = 92) and benign (n = 64) SRM were divided into the following three categories: category A, typical angiomyolipoma (AML) with visible fat; category B, benign SRM without visible fat, including fat-poor angiomyolipoma (fp-AML), and other rare benign renal tumors; category C, malignant renal tumors. At the same time, one hundred and fifty-six patients included in the study were divided into the training set (n = 108) and test set (n = 48). Respectively from corticomedullary phase (CP), nephrogram phase (NP) and excretory phase (EP) CT images to extract the radiomics features, and the optimal features were screened to establish the logistic regression model and decision tree model, and computed the radiomics score (Rad-score). Demographics and CT findings were evaluated and statistically significant factors were selected to construct a clinical factors model. The radiomics nomogram was established by merging Rad-score and selected clinical factors. The Akaike information criterion (AIC) values and the area under the curve (AUC) were used to compare model discriminant performance, and decision curve analysis (DCA) was used to assess clinical usefulness. ResultsSeven, fifteen, nineteen, and seventeen distinguishing features were obtained in the CP, NP, EP, and three-phase joint, respectively, and the logistic regression and decision tree models were built based on this features. In the training set, the logistic regression model works better than the decision tree model for distinguishing categories A and B from category C, with the AUC of CP, NP, EP and three-phase joint were 0.868, 0.906, 0.937 and 0.975, respectively. The radiomics nomogram constructed based on the three-phase joint Rad-score and selected clinical factor performed well on the training set (AUC, 0.988; 95% CI, 0.974-1.000) for differentiation of categories A and B from category C. In the test set, the AUC of clinical factors model, radiomics signature and radiomics nomogram for discriminating categories A and B from category C were 0.814, 0.954 and 0.968, respectively; for the identification of category A from category C, the AUC of the three models were 0.789, 0.979, 0.985, respectively; for discriminating category B from category C, the AUC of the three models were 0.853, 0.915, 0.946, respectively. The radiomics nomogram had better discriminative than the clinical factors model in both training and test sets (P < 0.05). The radiomics nomogram (AIC = 40.222) with the lowest AIC value was considered the best model compared with that of the clinical factors model (AIC = 106.814) and the radiomics signature (AIC = 44.224). The DCA showed that the radiomics nomogram have better clinical utility than the clinical factors model and radiomics signature. ConclusionsThe logistic regression model has better discriminative performance than the decision tree model, and the radiomics nomogram based on Rad-score of three-phase joint and clinical factors has a good predictive effect in differentiating benign from malignant of SRM, which may help clinicians develop accurate and individualized treatment strategies.

Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning

ObjectivesThis study aims to develop and evaluate the deep learning-based classification model for recognizing the pathology of renal tumor from macroscopic cross-section image.MethodsA total of 467 pathology-confirmed patients who received radical nephrectomy or partial nephrectomy were retrospectively enrolled. The experiment of distinguishing malignant and benign renal tumor are conducted followed by performing the multi-subtypes classification models for recognizing four subtypes of benign tumor and four subtypes of malignant tumors, respectively. The classification models used the same backbone networks which are based on the convolutional neural network (CNN), including EfficientNet-B4, ResNet-18, and VGG-16. The performance of the classification models was evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Besides, we performed the quantitative comparison among these CNN models.ResultsFor the model to differentiate the malignant tumor from the benign tumor, three CNN models all obtained relatively satisfactory performance and the highest AUC was achieved by the ResNet-18 model (AUC = 0.9226). There is not statistically significance between EfficientNet-B4 and ResNet-18 architectures and both of them are significantly statistically better than the VGG-16 model. The micro-averaged AUC, macro-averaged sensitivity, macro-averaged specificity, and micro-averaged accuracy for the VGG-16 model to distinguish the malignant tumor subtypes achieved 0.9398, 0.5774, 0.8660, and 0.7917, respectively. The performance of the EfficientNet-B4 is not better than that of VGG-16 in terms of micro-averaged AUC except for other metrics. For the models to recognize the benign tumor subtypes, the EfficientNet-B4 ranked the best performance, but had no significantly statistical difference with other two models with respect to micro-averaged AUC.ConclusionsThe classification results were relatively satisfactory, which showed the potential for clinical application when analyzing the renal tumor macroscopic cross-section images. Automatically distinguishing the malignant tumor from benign tumor and identifying the subtypes pathology of renal tumor could make the patient-management process more efficient.

The Role of CT Imaging in Characterization of Small Renal Masses.

Small renal masses (SRM) are increasingly detected incidentally during imaging. They vary widely in histology and aggressiveness, and include benign renal tumors and renal cell carcinomas that can be either indolent or aggressive. Imaging plays a key role in the characterization of these small renal masses. While a confident diagnosis can be made in many cases, some renal masses are indeterminate at imaging and can present as diagnostic dilemmas for both the radiologists and the referring clinicians. This review focuses on CT characterization of small renal masses, perhaps helping us understand small renal masses. The following aspects were considered for the review: (a) assessing the presence of fat, (b) assessing the enhancement, (c) differentiating renal tumor subtype, and (d) identifying valuable CT signs.

Distinguishing common renal cell carcinomas from benign renal tumors based on machine learning: comparing various CT imaging phases, slices, tumor sizes, and ROI segmentation strategies.

To determine whether a CT-based machine learning (ML) can differentiate benign renal tumors from renal cell carcinomas (RCCs) and improve radiologists' diagnostic performance, and evaluate the impact of variable CT imaging phases, slices, tumor sizes, and region of interest (ROI) segmentation strategies. Patients with pathologically proven RCCs and benign renal tumors from our institution between 2008 and 2020 were included as the training dataset for ML model development and internal validation (including 418 RCCs and 78 benign tumors), and patients from two independent institutions and a public database (TCIA) were included as the external dataset for individual testing (including 262 RCCs and 47 benign tumors). Features were extracted from three-phase CT images. CatBoost was used for feature selection and ML model establishment. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of the ML model. The ML model based on 3D images performed better than that based on 2D images, with the highest AUC of 0.81 and accuracy (ACC) of 0.86. All three radiologists achieved better performance by referring to the classifier's decision, with accuracies increasing from 0.82 to 0.87, 0.82 to 0.88, and 0.76 to 0.87. The ML model achieved higher negative predictive values (NPV, 0.82-0.99), and the radiologists achieved higher positive predictive values (PPV, 0.91-0.95). A ML classifier based on whole-tumor three-phase CT images can be a useful and promising tool for differentiating RCCs from benign renal tumors. The ML model also perfectly complements radiologist interpretations. • A machine learning classifier based on CT images could be a reliable way to differentiate RCCs from benign renal tumors. • The machine learning model perfectly complemented the radiologists' interpretations. • Subtle variances in ROI delineation had little effect on the performance of the ML classifier.

Diagnostic value of the preoperative platelet/lymphocyte ratio and red cell distribution volume in patients with renal masses.

Inflammatory markers indicate immune system responses. We retrospectively explored whether the platelet/lymphocyte ratio (PLR), neutrophil/lymphocyte ratio (NLR), and red blood cell distribution width (RDW) were predictive of malignant disease. Between 2019 and 2023, 148 patients diagnosed with malignant and benign renal tumors via imaging or biopsy were included. Of these tumors, 117 were malignant and 31 were benign. Blood samples were taken for calculation of the NLR, PLR, and RDW prior to renal biopsy or operation. The NLR, PLR, and RDW did not differ significantly between patients with malignant and benign renal masses (all p > 0.05). The PLR significantly increased with the T stage of malignant masses (p = 0.011). According to the T stage, the RDW cutoff was 45.7, the sensitivity was 40 %, and the specificity 82.4 %; the respective values for PLR were 134.9, 70 %, and 70.5 % (p = 0.026 and p = 0.003, respectively). The NLR, PLR, and RDW were not predictive in this study because we only included early- stage patients lacking lymph node involvement and the follow-up was short. In patients with renal cell carcinomas, the RDW and PLR increase with the tumor burden and predict poor prognosis (Tab. 5, Fig. 1, Ref. 23). Text in PDF www.elis.sk Keywords: neutrophil/lymphocyte ratio, platelet/ lymphocyte ratio, renal mass.

The Effect of Histogram Analysis of DCE-MRI Parameters on Differentiating Renal Tumors.

We aimed to assess the role of histogram analysis of DCE-MRI parameters for accurately distinguishing renal clear cell carcinoma from renal hamartoma with minimal fat. Patients with renal tumors were enrolled from January 2013 to December 2015, including renal clear cell carcinoma (n = 39) and renal hamartoma (n = 10). Preoperative DCE-MR Imaging was performed, and whole-tumor regions of interest were drawn to obtain the corresponding histogram parameters, including skewness, kurtosis, frequency size, energy, quartile, etc. Histogram parameters differences between renal clear cell car-cinoma and renal hamartoma with minimal fat were compared. The diagnostic value of each significant parameter in predicting malignant tumors was determined. Histogram parameters of the DCE map contributed to differentiating the benign from malignant renal tumor groups. Histogram analysis of DCE maps could effectively present the heterogeneity of renal tumors and aid in differentiating benign and malignant tumors. ROC analysis results indicated that when frequency size = 1,732 was set as the threshold value, favorable diagnostic performance in predicting malignant tumors was achieved (AUC - 0.964; sensitivity - 84.6%; specificity - 100%), followed by skewness, Energy, Entropy, Uniformity, quartile 5, quartile 50, and kurtosis. Histogram analysis of DCE-MRI shows promise for differentiating benign and malignant renal tumors. Frequency size was the most significant parameter for predicting renal clear cell carcinoma.

Locally Aggressive Mixed Epithelial and Stromal Tumour of Kidney Leading to Nephron Loss.

Mixed epithelial and stromal tumour (MEST) is a rare benign renal tumour. It is mainly found in perimenopausal women. We present a case of a 42-year female with no known comorbid who was presented in the outpatient clinic for the right flank pain. Contrast-enhanced CT scan revealed a complex renal cyst with internal septations. Considering a large symptomatic cyst and the presence of internal septations, she was planned for cyst excision. Peroperatively, significant disease progression and loss of renal parenchyma were noted contrary to preoperative scan. Histopathology of the specimen revealed MEST. We demonstrate that MEST of the kidney may have an aggressive local behaviour leading to nephron loss. Key Words: Mixed epithelial and stromal tumour, Kidney, Benign, Renal neoplasm.

Association between decreased ipsilateral renal function and aggressive behavior in renal cell carcinoma

BackgroundTo assess prognostic value of pre-operative ipsilateral split renal function (SRF) on disease-free survival (DFS) and its association with aggressive pathological features in renal cell carcinoma (RCC) patients. MethodsWe examined patients registered in SNUG-RCC-Nx who underwent partial or radical nephrectomy at Seoul National University Hospital between January 1, 2010 and December 31, 2020. Patients with the following criteria were excluded from the study. 1) non-kidney origin cancer or benign renal tumor, 2) no pre-operative Tc 99 m-DTPA renal scan, 3) single kidney status or previous partial or radical nephrectomy, and 4) bilateral renal mass. Finally, 1,078 patients were included.ResultsAmong 1,078 patients, 899 (83.4%) showed maintained ipsilateral SRF on DTPA renal scan; 179 patients (16.6%) showed decreased SRF. The decreased SRF group showed significantly large tumor size (maintained vs. decreased SRF; 3.31 ± 2.15 vs. 6.85 ± 3.25, p < 0.001), high Fuhrman grade (grade 3–4) (41.7% vs. 55.6%, p < 0.001), and high T stage (T stage 3–4) (9.0% vs. 20.1%, p < 0.001). Pathological invasive features, including invasion of the renal capsule, perirenal fat, renal sinus fat, vein, and collecting duct system, were associated with low SRF of the ipsilateral kidney. Univariate Cox regression analysis identified higher SSIGN (The stage, size, grade, and necrosis) score and decreased ipsilateral SRF as significant risk factors, while multivariate analysis showed SSIGN (5–7) (hazard ratio [HR] 11.9, p < 0.001) and SSIGN (8–10) (HR 69.2, p < 0.001) were significantly associated with shortened DFS, while decreased ipsilateral SRF (HR 1.75, p = 0.065) showed borderline significance. Kaplan–Meier analysis showed that decreased ipsilateral SRF (< 45%) group had shorter DFS than the other group (median DFS: 90.3 months vs. not reached, p < 0.001).ConclusionsAmong unilateral RCC patients, those with low ipsilateral SRF showed poor prognosis with pathologically invasive features. Our novel approach may facilitate risk stratification in RCC patients, helping formulate a treatment strategy.

Differentiating Oncocytic Renal Tumors from Chromophobe Renal Cell Carcinoma: Comparison of Peak Early-phase Enhancement Ratio to Clinical Risk Factors and Rater Predictions

BackgroundMost surgically resected benign renal tumors are found to be oncocytomas or indolent hybrid oncocytic tumors, which are difficult to differentiate from chromophobe renal cell carcinoma (chRCC) on renal mass biopsy. Both often exhibit CD117+ staining. ObjectiveTo evaluate the ability of the peak early-phase enhancement ratio (PEER) to distinguish oncocytomas from chRCC and compare its discrimination to traditional clinical risk factors and blinded clinical raters. Design, setting, and participantsThis was a diagnostic case-control study of patients (2006–2020) with oncocytoma or chRCC according to surgical pathology. InterventionPartial or radical nephrectomy. Outcome measurements and statistical analysisThree clinical raters blinded to histology measured the PEER and the presence of stellate scar and predicted the final histology for each tumor. Averaged and individual PEER values were compared to surgical pathology and assessed for interobserver variability. Subanalyses were conducted for patients with confirmed CD117+ status. Results and limitationsFor the 76 patients identified, PEER was higher among the 32 (42.1%) oncocytomas than among the 44 (57.9%) chRCCs (median 0.81 vs 0.43; p < 0.001), with high correlation across raters (correlation coefficients ≥0.85). A PEER cutoff of <0.60 was strongly associated with identification of chRCC (OR 95.7 (95% CI 19.9–460.8), p < 0.001). In the overall and CD117+ cohorts, sensitivity was 93.2% and 97.0%, the negative predictive value was 90.3% and 95.5%, and the area under the receiver operating characteristic curve (AUC) on multivariable modeling was 95.0% and 98.1%, respectively. PEER outperformed models with clinical risk factors alone (AUC 70.4%) and histology predictions by three raters (AUC 51.6%, 62.5%, and 63.1%). Limitations include reliance on surgical pathology and inclusion of a mix of early contrast-enhanced phases. ConclusionsPEER reliably differentiated benign renal oncocytomas and indolent hybrid tumors from malignant chRCC with excellent diagnostic performance. A diagnostic pathway with biopsy, CD117 staining, and PEER deserves further study to potentially avoid unnecessary surgery for oncocytic renal tumors. Patient summaryWe assessed a measurement called PEER on computed tomography (CT) scans and found higher values for benign and lower values for malignant kidney masses, so we were able to tell these apart. PEER was reliable for identifying tumors with positive staining for the CD117 protein biomarker as well as in the overall patient group. Our results show that PEER could be considered for use with biopsy and CD117 staining to potentially avoid unnecessary surgery for benign kidney masses.

The diagnosis of benign renal tumors on limited material.

Angiomyolipoma, papillary adenoma, oncocytoma, and clear cell papillary renal cell tumor are common benign renal tumors that may be encountered on biopsy material. The diagnostic criteria, limitations, and accuracy as well as specific sign out terminology are reviewed.

Atypical metanephric adenoma: Shares similar histopathological features and molecular changes of metanephric adenoma and epithelial-predominant Wilms' tumor.

BackgroundMetanephric adenomas (MAs) are rare, benign renal tumors. Wilms’ tumors (WTs) are malignant embryonic tumors that originated from nephrogenic blastemal cells. However, some tumors have similar morphology to both MA and epithelial-predominant WT, which makes differential diagnosis difficult. We aimed to analyze the morphological, immunophenotypic and molecular changes in overlapping cases to explore their attribution.Methods and resultsTwenty MAs, ten WTs, and nine cases with MA/WT overlapping histological features were studied. Twenty tumors demonstrated the typical morphological spectrum of MA with high cellularity and were composed of tightly packed small, uniform, round acini with a lower Ki67 index. Almost all MAs (94.7%, 18/19) were detected with BRAF V600E mutation. The ten WTs were epithelial-predominant WTs with glands, rosettes and glomerular structures, which also showed a higher Ki-67 index (up to 60%), invasive growth patterns, and a lack of BRAF mutation. However, the other nine overlapping cases showed two components: typical MA-like areas and epithelial WT-like areas. The cells of the WT-like areas were tubular, columnar and showed marked cytological atypia, with a Ki-67 proliferative index of up to 30%. The immunophenotype of these overlapping lesions was not significantly different from that of typical MA and they positively expressed WT1 and CD57. The BRAF V600E mutation was detected in both WT-like and MA-like areas in nine overlapping tumors. The follow-up data of 31 patients were analyzed, with a median follow-up time of 66 months (range, 8-45 months). Even though most patients with WT underwent radiotherapy or chemotherapy after surgery, two died, and one had liver metastasis. No MA or overlapping cases showed any evidence of recurrence or metastasis after surgery.ConclusionsThe molecular changes in tumors with overlapping morphological features were the same as those of typical MA; thus, we think that these tumors should be classified as MA and further called atypical MA. It is important to note that atypical MA is not a neglected subtype of MA. It possesses different histological morphology and a higher Ki-67 index but has the common imaging characteristics, immunophenotype and gene expression as typical MA, and patients usually have a good prognosis.

Accurate detection of benign and malignant renal tumor subtypes with MethylBoostER: An epigenetic marker-driven learning framework.

Current gold standard diagnostic strategies are unable to accurately differentiate malignant from benign small renal masses preoperatively; consequently, 20% of patients undergo unnecessary surgery. Devising a more confident presurgical diagnosis is key to improving treatment decision-making. We therefore developed MethylBoostER, a machine learning model leveraging DNA methylation data from 1228 tissue samples, to classify pathological subtypes of renal tumors (benign oncocytoma, clear cell, papillary, and chromophobe RCC) and normal kidney. The prediction accuracy in the testing set was 0.960, with class-wise ROC AUCs >0.988 for all classes. External validation was performed on >500 samples from four independent datasets, achieving AUCs >0.89 for all classes and average accuracies of 0.824, 0.703, 0.875, and 0.894 for the four datasets. Furthermore, consistent classification of multiregion samples (N = 185) from the same patient demonstrates that methylation heterogeneity does not limit model applicability. Following further clinical studies, MethylBoostER could facilitate a more confident presurgical diagnosis to guide treatment decision-making in the future.

A Rare and Unusual Renal Tumour: A Case Report

Introduction: Multilocular cystic renal cell neoplasm of low malignant potential is a rare histologically identified form of clear cell renal cell carcinoma included in 2016 Renal tumour classification of WHO. It is a low risk neoplasm with clear cells that have less expansile proliferation than other clear cell variants of renal cell carcinoma with no recurrence and metastasis with few exceptional cases. The incidence of multilocular cystic renal cell carcinoma is estimated to be 1-2 percent.6,12 Although the WHO classification of multilocular cystic renal cell carcinoma with low malignant potential was reported in 2004. The WHO 2016 categorization of renal cell tumour has been assessed as a special entity with no documented cases of metastasizing and recurrent tumour development.4 We present a rare clinical case of multilocular cystic renal cell neoplasm with low malignant potential, which should not be mistaken with other differential diagnoses such as cystic necrosis in conventional renal cell carcinoma, tubulo cystic renal cell carcinoma, multilocular cystic nephroma, clear cell variant of renal cell carcinoma and other benign multilocular renal tumors.

Multimodal ultrasound fusion network for differentiating between benign and malignant solid renal tumors.

Objective: We aim to establish a deep learning model called multimodal ultrasound fusion network (MUF-Net) based on gray-scale and contrast-enhanced ultrasound (CEUS) images for classifying benign and malignant solid renal tumors automatically and to compare the model’s performance with the assessments by radiologists with different levels of experience. Methods: A retrospective study included the CEUS videos of 181 patients with solid renal tumors (81 benign and 100 malignant tumors) from June 2012 to June 2021. A total of 9794 B-mode and CEUS-mode images were cropped from the CEUS videos. The MUF-Net was proposed to combine gray-scale and CEUS images to differentiate benign and malignant solid renal tumors. In this network, two independent branches were designed to extract features from each of the two modalities, and the features were fused using adaptive weights. Finally, the network output a classification score based on the fused features. The model’s performance was evaluated using five-fold cross-validation and compared with the assessments of the two groups of radiologists with different levels of experience. Results: For the discrimination between benign and malignant solid renal tumors, the junior radiologist group, senior radiologist group, and MUF-Net achieved accuracy of 70.6%, 75.7%, and 80.0%, sensitivity of 89.3%, 95.9%, and 80.4%, specificity of 58.7%, 62.9%, and 79.1%, and area under the receiver operating characteristic curve of 0.740 (95% confidence internal (CI): 0.70–0.75), 0.794 (95% CI: 0.72–0.83), and 0.877 (95% CI: 0.83–0.93), respectively. Conclusion: The MUF-Net model can accurately classify benign and malignant solid renal tumors and achieve better performance than senior radiologists. Key points: The CEUS video data contain the entire tumor microcirculation perfusion characteristics. The proposed MUF-Net based on B-mode and CEUS-mode images can accurately distinguish between benign and malignant solid renal tumors with an area under the receiver operating characteristic curve of 0.877, which surpasses senior radiologists’ assessments by a large margin.

Contrast-enhanced ultrasound (CEUS) of benign and malignant renal tumors: Distinguishing CEUS features differ with tumor size.

Contrast-enhanced ultrasound (CEUS) is now a guideline-recommended strategy for diagnosing renal lesions. Tumor size is related to the risk of the treatment and prognosis in renal tumors. Thus, we aim to analyze the CEUS features of solid renal tumors in relation to tumor size. The CEUS appearance of 156 pathologically diagnosed solid renal tumors were retrospectively analyzed. Three groups were stratified according to the tumor size (≤2cm [group I], 2.1-4cm [group II] and 4.1-7cm [group III]). For each group, the features of wash-in type, enhancement degree, enhancement homogeneity, and the presence of a pseudocapsule sign were compared between benign and malignant tumors. All 156 included lesions were detected by CEUS. The proportion of benign tumors in three size groups was 37.1%, 19.4%, and 20.4%, respectively. The proportion of malignant tumors was highest (80.6%) in group II, followed by group III (79.6%) and group I (62.9%). In group I, malignant and benign tumors differed significantly in the presence of a pseudocapsule sign (p=0.015) and homogeneity (p=0.007). In group II, the degree of enhancement differed (p=0.02) between tumor types. In group III, the two tumor types differed in both the wash-in pattern (p=0.015) and enhancement degree (p=0.024). The weighted and Cohen's kappa values for the concordance between inter-observer agreement ranged from 0.31 (95% CI: 0.36-0.57) to 0.90 (95% CI: 0.77-1.00). CEUS features of malignant and benign renal tumors change along with the tumor size. The use of CEUS features in the diagnosis of benign and malignant tumors requires consideration of tumor size.

Comparison of perinephric fat measurements between malignant and benign renal tumours.

ObjectiveTo investigate different parameters derived from the quantity and quality of perinephric fat, and to compare their effectiveness in predicting the malignant pathology of renal tumours.MethodsData from patients diagnosed with renal tumour between April 2014 and December 2020 were retrospectively reviewed, and patients were categorized into malignant or benign tumour groups. Fat parameters, including perinephric fat volume (PFV), perinephric fat area (PFA), perinephric fat thickness (PFT), and Mayo adhesive probability (MAP) score were measured using abdominal computed tomography scans. Between-group differences were assessed by analysis of variance and χ2-test. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the performance of perinephric fat parameters in diagnosing malignancy.ResultsA total of 109 patients were included. MAP score, PFV, PFA, and PFT were significantly increased in the malignant versus benign tumour group, and after correction for body mass index (BMI), the indexed PFV/BMI, PFA/BMI, and PFT/BMI values remained significantly higher in the malignant tumour group. All parameters showed fair predictivity of malignancy, with comparable area under the curve values in the ROC curve.ConclusionAn increased amount of perinephric fat is predictive of malignant pathology for renal tumours. The predictive accuracy for each perinephric fat parameter remained fair after correcting for BMI.