Diagnostic Accuracy of Multiparametric Magnetic Resonance Imaging to Identify Clear Cell Renal Cell Carcinoma in cT1a Renal Masses

Tumor morphology evaluation using 3D-morphometric features of renal masses

OBJECTIVE

To assess the correlation between the general (gender, age, and maximum tumor size) and 3D morphotopometric features of the renal tumor node, following the MSCT data post-processing, and the tumor histological structure; to propose an equation allowing for kidney malignancy assessment based on general and morphometric features.

MATERIALS AND METHODS

In total, 304 patients with unilateral solitary renal neoplasms underwent laparoscopic (retroperitoneoscopic) or robotic partial or radical nephrectomy. Before the procedure, kidney contrast-enhanced MSCT followed by the tumor 3D-modeling was performed. 3D model of the kidney tumor, and its morphotopometric features, and histological structure were analyzed. The morphotopometric ones include the side of the lesion, location by segments, the surface where the tumor, the depth of the tumor invasion into the kidney, and the shape of tumor.

RESULTS

Out of 304 patients, 254 (83.6%) had malignant kidney tumors and 50 (16.4%) benign kidney tumors. In total, 231 patients, out of 254 (90.9%) were assessed for the degree of malignant tumor differentiation. Malignant tumors were more frequent in men than in women (p < 0.001). Mushroom-shaped tumors were the most common shapes among benign renal masses (35.2%). The most common malignant kidney tumors had spherical with a partially uneven surface (27.6%), multinodular (tuberous (27.2%)), and spherical with a conical base (24.8%) shapes. Logistic regression model enabled the development of prognostic equation for tumor malignancy prediction ("low" or "high"). The univariate analysis revealed the correlation only between high differentiation (G1) and a spherical tumor with a conical base (p = 0.029).

CONCLUSION

The resulting logistic model, based on the analysis of such predictors as gender and form of kidney lesions, demonstrated a large share (87.6%) of correct predictions of the kidney tumor malignancy.

Is there enough evidence supporting the clinical adoption of clear cell likelihood score (ccLS)? An updated systematic review and meta-analysis

OBJECTIVE

To review the evidence for clinical adoption of clear cell likelihood score (ccLS) for identifying clear cell renal cell carcinoma (ccRCC) from small renal masses (SRMs).

METHODS

We distinguished the literature on ccLS for identifying ccRCC via systematic search using PubMed, Embase, Web of Science, China National Knowledge Infrastructure, and Wanfang Data until 31 March, 2024. The risk of bias and concern on application was assessed using the modified quality assessment of diagnostic accuracy studies (QUADAS-2) tool. The level of evidence supporting the clinical adoption of ccLS for identifying ccRCC was determined based on meta-analyses.

RESULTS

Eight MRI studies and three CT studies were included. The risk of bias and application were mainly related to the index test and flow and timing, due to incomplete imaging protocol, unclear rating process, and inappropriate interval between imaging and surgery. The diagnostic odds ratios (95% confidence intervals) of MRI and CT ccLS were 14.69 (9.71-22.22; 6 studies, 1429 SRM, 869 ccRCC), and 5.64 (3.34-9.54; 3 studies, 296 SRM, 147 ccRCC), respectively, for identifying ccRCC from SRM. The evidence level for clinical adoption of MRI and CT ccLS were both rated as weak. MRI ccLS version 2.0 potentially has better diagnostic performance than version 1.0 (1 study, 700 SRM, 509 ccRCC). Both T2-weighted-imaging with or without fat suppression might be suitable for MRI ccLS version 2.0 (1 study, 111 SRM, 82 ccRCC).

CONCLUSION

ccLS shows promising diagnostic performance for identifying ccRCC from SRM, but the evidence for its adoption in clinical routine remains weak.

CRITICAL RELEVANCE STATEMENT

Although clear cell likelihood score (ccLS) demonstrates promising performance for detecting clear cell renal cell carcinoma, additional evidence is crucial to support its routine use as a tool for both initial diagnosis and active surveillance of small renal masses.

KEY POINTS

Clear cell likelihood score is designed for the evaluation of small renal masses. Both CT and MRI clear cell likelihood scores are accurate and efficient. More evidence is necessary for the clinical adoption of a clear cell likelihood score.

Diagnostic accuracy of the Clear Cell Likelihood Score and selected MRI parameters in the characterization of indeterminate renal masses - a single-institution study

PURPOSE

We aimed to assess the diagnostic accuracy of the clear cell likelihood score (ccLS) and value of other selected magnetic resonance imaging (MRI) features in the characterization of indeterminate small renal masses (SRMs).

METHODS

Fifty patients with indeterminate SRMs discovered on MRI between 2012 and 2023 were included. The ccLS for the characterization of clear cell renal cell carcinoma (ccRCC) was calculated and compared to the final diagnosis (ccRCC vs. 'all other' masses).

RESULTS

The ccLS = 5 had a satisfactory accuracy of 64.0% and a very high specificity of 96.3%; however, its sensitivity of 26.1% was relatively low. Receiver operating curve (ROC) analysis revealed that from the selected MRI features, only T1 ratio and arterial to delayed enhancement (ADER) were good discriminators between ccRCC and other types of renal masses (area under curve, AUC = 0.707, p = 0.01; AUC = 0.673, p = 0.03; respectively). The cut-off points determined in ROC analysis using the Youden index were 0.73 (p = 0.01) for T1 ratio and 0.99 for ADER (p = 0.03). The logistic regression model demonstrated that ccLS = 5 and T1 ratio (OR = 15.5 [1.1-218.72], p = 0.04; OR = 0.002 [0.00-0.81], p = 0.04) were significant predictors of ccRCC.

CONCLUSIONS

The ccLS algorithm offers an encouraging method for the standardization of imaging protocols to aid in the diagnosis and management of SRMs in daily clinical practice by enhancing detectability of ccRCC and reducing the number of unnecessary invasive procedures for benign or indolent lesions. However, its diagnostic performance needs multi-center large cohort studies to validate it before it can be incorporated as a diagnostic algorithm and will guide future iterations of clinical guidelines. The retrospective nature of our study and small patient population confined to a single clinical center may impact the generalizability of the results; thus, future studies are required to define whether employment of the T1 ratio or ADER parameter may strengthen the diagnostic accuracy of ccRCC diagnosis.

Clear cell likelihood score may improve diagnosis and management of renal masses

The detection of solid renal masses has increased over time due to incidental findings during imaging studies conducted for unrelated medical conditions. Approximately 20% of lesions measuring less than 4 cm are benign and 80% are malignant. Clear cell renal cell carcinoma (ccRCC) is the most frequent among renal carcinomas, responsible for 65-80% of cases. The increased detection of renal masses facilitates early diagnosis and treatment. However, it also leads to more invasive interventions, which result in higher morbidity and costs. Currently, only histological analysis can offer an accurate diagnosis. Surgical nephron loss significantly elevates morbidity and mortality rates. Active surveillance represents a conservative management approach for patients diagnosed with a solid renal mass that is endorsed by both American Urological Association and the European Society for Medical Oncology. However, active surveillance is used in a minority of patients and varies across institutions. The lack of clinical studies using a standardized approach to incidentally detected small renal masses precludes the widespread use of active surveillance. Hence, there is an urgent need for better patient selection, distinguishing those who require surgery from those suitable for active surveillance. The clear cell likelihood score (ccLS) represents a novel MRI tool for assessing the probability of a renal mass being a ccRCC. In this study, we present a comprehensive review of renal masses and their evaluation using the ccLS to facilitate shared decision between urologists and patients.

Cost-Effectiveness Analysis of the Clear Cell Likelihood Score Against Renal Mass Biopsy for Evaluating Small Renal Masses

OBJECTIVE

To examine the cost-effectiveness of the clear cell likelihood score compared to renal mass biopsy (RMB) alone.

METHODS

The clear cell likelihood score, a new grading system based on multiparametric magnetic resonance imaging, has been proposed as a possible alternative to percutaneous RMB for identifying clear cell renal carcinoma in small renal masses and expediting treatment of high-risk patients. A decision analysis model was developed to compare a RMB strategy where all patients undergo biopsy and a clear cell likelihood score strategy where only patients that received an indeterminant score of 3 undergo biopsy. Effectiveness was assigned 1 for correct diagnoses and 0 for incorrect or indeterminant diagnoses. Costs were obtained from institutional fees and Medicare reimbursement rates. Probabilities were derived from literature estimates from radiologists trained in the clear cell likelihood score.

RESULTS

In the base case model, the clear cell likelihood score was both more effective (0.77 vs 0.70) and less expensive than RMB ($1629 vs $1966). Sensitivity analysis found that the nondiagnostic rate of RMB and the sensitivity of the clear cell likelihood score had the greatest impact on the model. In threshold analyses, the clear cell likelihood score was the preferred strategy when its sensitivity was greater than 62.7% and when an MRI cost less than $5332.

CONCLUSION

The clear cell likelihood score is a more cost-effective option than RMB alone for evaluating small renal masses for clear cell renal carcinoma.

Evaluation of a multiparametric renal CT algorithm for diagnosis of clear-cell renal cell carcinoma among small (≤ 4 cm) solid renal masses

OBJECTIVE

To evaluate a recently proposed CT-based algorithm for diagnosis of clear-cell renal cell carcinoma (ccRCC) among small (≤ 4 cm) solid renal masses diagnosed by renal mass biopsy.

METHODS

This retrospective study included 51 small renal masses in 51 patients with renal-mass CT and biopsy between 2014 and 2021. Three radiologists independently evaluated corticomedullary phase CT for the following: heterogeneity and attenuation ratio (mass:renal cortex), which were used to inform the CT score (1-5). CT score ≥ 4 was considered positive for ccRCC. Diagnostic accuracy was calculated for each reader and overall using fixed effects logistic regression modelling.

RESULTS

There were 51% (26/51) ccRCC and 49% (25/51) other masses. For diagnosis of ccRCC, area under curve (AUC), sensitivity, specificity, and positive predictive value (PPV) were 0.69 (95% confidence interval 0.61-0.76), 78% (68-86%), 59% (46-71%), and 67% (54-79%), respectively. CT score ≤ 2 had a negative predictive value 97% (92-99%) to exclude diagnosis of ccRCC. For diagnosis of papillary renal cell carcinoma (pRCC), CT score ≤ 2, AUC, sensitivity, specificity, and PPV were 0.89 (0.81-0.98), 81% (58-94%), 98% (93-99%), and 85% (62-97%), respectively. Pooled inter-observer agreement for CT scoring was moderate (Fleiss weighted kappa = 0.52).

CONCLUSION

The CT scoring system for prediction of ccRCC was sensitive with a high negative predictive value and moderate agreement. The CT score is highly specific for diagnosis of pRCC.

CLINICAL RELEVANCE STATEMENT

The CT score algorithm may help guide renal mass biopsy decisions in clinical practice, with high sensitivity to identify clear-cell tumors for biopsy to establish diagnosis and grade and high specificity to avoid biopsy in papillary tumors.

KEY POINTS

• A CT score ≥ 4 had high sensitivity and negative predictive value for diagnosis of clear-cell renal cell carcinoma (RCC) among solid ≤ 4-cm renal masses. • A CT score ≤ 2 was highly specific for diagnosis of papillary RCC among solid ≤ 4-cm renal masses. • Inter-observer agreement for CT score was moderate.

Update on Renal Cell Carcinoma Diagnosis with Novel Imaging Approaches

This review highlights recent advances in renal cell carcinoma (RCC) imaging. It begins with dual-energy computed tomography (DECT), which has demonstrated a high diagnostic accuracy in the evaluation of renal masses. Several studies have suggested the potential benefits of iodine quantification, particularly for distinguishing low-attenuation, true enhancing solid masses from hyperdense cysts. By determining whether or not a renal mass is present, DECT could avoid the need for additional imaging studies, thereby reducing healthcare costs. DECT can also provide virtual unenhanced images, helping to reduce radiation exposure. The review then provides an update focusing on the advantages of multiparametric magnetic resonance (MR) imaging performance in the histological subtyping of RCC and in the differentiation of benign from malignant renal masses. A proposed standardized stepwise reading of images helps to identify clear cell RCC and papillary RCC with a high accuracy. Contrast-enhanced ultrasound may represent a promising diagnostic tool for the characterization of solid and cystic renal masses. Several combined pharmaceutical imaging strategies using both sestamibi and PSMA offer new opportunities in the diagnosis and staging of RCC, but their role in risk stratification needs to be evaluated. Although radiomics and tumor texture analysis are hampered by poor reproducibility and need standardization, they show promise in identifying new biomarkers for predicting tumor histology, clinical outcomes, overall survival, and the response to therapy. They have a wide range of potential applications but are still in the research phase. Artificial intelligence (AI) has shown encouraging results in tumor classification, grade, and prognosis. It is expected to play an important role in assessing the treatment response and advancing personalized medicine. The review then focuses on recently updated algorithms and guidelines. The Bosniak classification version 2019 incorporates MRI, precisely defines previously vague imaging terms, and allows a greater proportion of masses to be placed in lower-risk classes. Recent studies have reported an improved specificity of the higher-risk categories and better inter-reader agreement. The clear cell likelihood score, which adds standardization to the characterization of solid renal masses on MRI, has been validated in recent studies with high interobserver agreement. Finally, the review discusses the key imaging implications of the 2017 AUA guidelines for renal masses and localized renal cancer.

Diagnostic Value of Clear Cell Likelihood Score v1.0 and v2.0 for Common Subtypes of Small Renal Masses: A Multicenter Comparative Study

BACKGROUND

Clear cell likelihood score (ccLS) is reliable for diagnosing small renal masses (SRMs). However, the diagnostic value of Clear cell likelihood score version 1.0 (ccLS v1.0) and v2.0 for common subtypes of SRMs might be a potential score extension.

PURPOSE

To compare the diagnostic performance and interobserver agreement of ccLS v1.0 and v2.0 for characterizing five common subtypes of SRMs.

STUDY TYPE

Retrospective.

POPULATION

797 patients (563 males, 234 females; mean age, 53 ± 12 years) with 867 histologically proven renal masses.

FIELD STRENGTH/SEQUENCES

3.0 and 1.5 T/T2 weighted imaging, T1 weighted imaging, diffusion-weighted imaging, a dual-echo chemical shift (in- and opposed-phase) T1 weighted imaging, multiphase dynamic contrast-enhanced imaging.

ASSESSMENT

Six abdominal radiologists were trained in the ccLS algorithm and independently scored each SRM using ccLS v1.0 and v2.0, respectively. All SRMs had definite pathological results. The pooled area under curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the diagnostic performance of ccLS v1.0 and v2.0 for characterizing common subtypes of SRMs. The average κ values were calculated to evaluate the interobserver agreement of the two scoring versions.

STATISTICAL TESTS

Random-effects logistic regression; Receiver operating characteristic analysis; DeLong test; Weighted Kappa test; Z test. The statistical significance level was P < 0.05.

RESULTS

The pooled AUCs of clear cell likelihood score version 2.0 (ccLS v2.0) were statistically superior to those of ccLS v1.0 for diagnosing clear cell renal cell carcinoma (ccRCC) (0.907 vs. 0.851), papillary renal cell carcinoma (pRCC) (0.926 vs. 0.888), renal oncocytoma (RO) (0.745 vs. 0.679), and angiomyolipoma without visible fat (AMLwvf) (0.826 vs. 0.766). Interobserver agreement for SRMs between ccLS v1.0 and v2.0 is comparable and was not statistically significant (P = 0.993).

CONCLUSION

The diagnostic performance of ccLS v2.0 surpasses that of ccLS v1.0 for characterizing ccRCC, pRCC, RO, and AMLwvf. Especially, the standardized algorithm has optimal performance for ccRCC and pRCC. ccLS has potential as a supportive clinical tool.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

Characterization of Demographical Histologic Diversity in Small Renal Masses With the Clear Cell Likelihood Score

OBJECTIVE

This study aimed to develop a diagnostic model to estimate the distribution of small renal mass (SRM; ≤4 cm) histologic subtypes for patients with different demographic backgrounds and clear cell likelihood score (ccLS) designations.

MATERIALS AND METHODS

A bi-institution retrospective cohort study was conducted where 347 patients (366 SRMs) underwent magnetic resonance imaging and received a ccLS before pathologic confirmation between June 2016 and November 2021. Age, sex, race, ethnicity, socioeconomic status, body mass index (BMI), and the ccLS were tabulated. The socioeconomic status for each patient was determined using the Area Deprivation Index associated with their residential address. The magnetic resonance imaging-derived ccLS assists in the characterization of SRMs by providing a likelihood of clear cell renal cell carcinoma (ccRCC). Pathological subtypes were grouped into four categories (ccRCC, papillary renal cell carcinoma, other renal cell carcinomas, or benign). Generalized estimating equations were used to estimate probabilities of the pathological subtypes across different patient subgroups.

RESULTS

Race and ethnicity, BMI, and ccLS were significant predictors of histology (all P < 0.001). Obese (BMI, ≥30 kg/m 2 ) Hispanic patients with ccLS of ≥4 had the highest estimated rate of ccRCC (97.1%), and normal-weight (BMI, <25 kg/m 2 ) non-Hispanic Black patients with ccLS ≤2 had the lowest (0.2%). The highest estimated rates of papillary renal cell carcinoma were found in overweight (BMI, 25-30 kg/m 2 ) non-Hispanic Black patients with ccLS ≤2 (92.3%), and the lowest, in obese Hispanic patients with ccLS ≥4 (<0.1%).

CONCLUSIONS

Patient race, ethnicity, BMI, and ccLS offer synergistic information to estimate the probabilities of SRM histologic subtypes.

Rate of benign histology after resection of suspected renal cell carcinoma: multicenter comparison between Korea and the United States

BACKGROUND

In the United States, the rate of benign histology among resected renal tumors suspected to be malignant is increasing. We evaluated the rates in the Republic of Korea and assessed the racial effect using recent multi-institutional Korean-United States data.

METHODS

We conducted a multi-institutional retrospective study of 11,529 patients (8,812 from The Republic of Korea and 2,717 from the United States) and compared the rates of benign histology between the two countries. To evaluate the racial effect, we divided the patients into Korean, Asian in the US, and Non-Asian in the US.

RESULTS

The rates of benign histology and small renal masses in Korean patients were significantly lower than that in United States patients (6.3% vs. 14.3%, p < 0.001) and (≤ 4 cm, 7.6% vs. 19.5%, p < 0.001), respectively. Women, incidentaloma, partial nephrectomy, minimally invasive surgery, and recent surgery were associated with a higher rate of benign histology than others.

CONCLUSIONS

In Korea, the rate of benign histology among resected renal tumors was significantly lower than that in the United States. This disparity could be caused by environmental or cultural differences rather than racial differences. Our findings suggest that re-evaluating current context-specific standards of care is necessary to avoid overtreatment.

Concordance between renal tumour biopsy and robotic-assisted partial and radical nephrectomy histology: a 10-year experience

We aimed to assess concordance between renal tumour biopsy (RTB) and surgical pathology from robotic-assisted partial nephrectomy (RAPN) or robotic-assisted radical nephrectomy (RARN). Patients with preoperative RTB undergoing RAPN or RARN for suspected malignancy (9 September 2013-9 September 2023) were enrolled retrospectively from three sites. Patients were excluded if the tumour had prior cryotherapy or if biopsy or nephrectomy histology were unavailable or inconclusive. The primary outcome was concordance with the presence/absence of malignancy. Secondary outcomes were concordance with tumour subtype, World Health Organisation nuclear grade (patients with RTB clear cell or papillary RCC only), false-negative rate, false-positive rate, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In the enrolment period, 332 and 132 patients underwent RAPN and RARN, respectively. Of these, 160 received preoperative RTB, with nine patients excluded, leaving 151 eligible patients. Median age was 63 years, and 49 (32%) were female. On surgical specimens, 144 patients had malignant histology. RTB was highly concordant with presence/absence of malignancy (147/151, 97%). Concordance with tumour subtype occurred in 141 patients (93%), while concordance with nuclear grade was seen in 42/66 patients (64%, RTB grade missing in 53 patients). False-negative rate, false-positive rate, sensitivity, specificity, PPV, and NPV were 2%, 14%, 98%, 86%, 99%, and 67%, respectively. Limitations include absence of complication data and exclusion of patients biopsied without surgery. In patients undergoing RAPN or RARN, preoperative RTB has high concordance with surgical pathology, both in the presence of malignancy and RCC subtype.

Differentiation between renal epithelioid angiomyolipoma and clear cell renal cell carcinoma using clear cell likelihood score

PURPOSE

Clear cell likelihood score (ccLS) may be a reliable diagnostic method for distinguishing renal epithelioid angiomyolipoma (EAML) and clear cell renal cell carcinoma (ccRCC). In this study, we aim to explore the value of ccLS in differentiating EAML from ccRCC.

METHODS

We performed a retrospective analysis in which 27 EAML patients and 60 ccRCC patients underwent preoperative magnetic resonance imaging (MRI) at our institution. Two radiologists trained in the ccLS algorithm scored independently and the consistency of their interpretation was evaluated. The difference of the ccLS score was compared between EAML and ccRCC in the whole study cohort and two subgroups [small renal masses (SRM; ≤ 4 cm) and large renal masses (LRM; > 4 cm)].

RESULTS

In total, 87 patients (59 men, 28 women; mean age, 55±11 years) with 90 renal masses (EAML: ccRCC = 1: 2) were identified. The interobserver agreement of two radiologists for the ccLS system to differentiate EAML from ccRCC was good (k = 0.71). The ccLS score in the EAML group and the ccRCC group ranged from 1 to 5 (73.3% in scores 1-2) and 2 to 5 (76.7% in scores 4-5), respectively, with statistically significant differences (P < 0.001). With the threshold value of 2, ccLS can distinguish EAML from ccRCC with the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 87.8%, 95.0%, 73.3%, 87.7%, and 88.0%, respectively. The AUC (area under the curve) was 0.913. And the distribution of the ccLS score between the two diseases was not affected by tumor size (P = 0.780).

CONCLUSION

The ccLS can distinguish EAML from ccRCC with high accuracy and efficiency.

Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI

Purpose

To develop and validate a semisupervised style transfer-assisted deep learning method for automated segmentation of the kidneys using multiphase contrast-enhanced (MCE) MRI acquisitions.

Materials and Methods

This retrospective, Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included 125 patients (mean age, 57.3 years; 67 male, 58 female) with renal masses. Cohort 1 consisted of 102 coronal T2-weighted MRI acquisitions and 27 MCE MRI acquisitions during the corticomedullary phase. Cohort 2 comprised 92 MCE MRI acquisitions (23 acquisitions during four phases each, including precontrast, corticomedullary, early nephrographic, and nephrographic phases). The kidneys were manually segmented on T2-weighted images. A cycle-consistent generative adversarial network (CycleGAN) was trained to generate anatomically coregistered synthetic corticomedullary style images using T2-weighted images as input. Synthetic images for precontrast, early nephrographic, and nephrographic phases were then generated using the synthetic corticomedullary images as input. Mask region-based convolutional neural networks were trained on the four synthetic phase series for kidney segmentation using T2-weighted masks. Segmentation performance was evaluated in a different cohort of 20 originally acquired MCE MRI examinations by using Dice and Jaccard scores.

Results

The CycleGAN network successfully generated anatomically coregistered synthetic MCE MRI-like datasets from T2-weighted acquisitions. The proposed deep learning approach for kidney segmentation achieved high mean Dice scores in all four phases of the original MCE MRI acquisitions (0.91 for precontrast, 0.92 for corticomedullary, 0.91 for early nephrographic, and 0.93 for nephrographic).

Conclusion

The proposed deep learning approach achieved high performance in kidney segmentation on different MCE MRI acquisitions.Keywords: Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Differentiation of Small Clear Renal Cell Carcinoma and Oncocytoma through Magnetic Resonance Imaging-Based Radiomics Analysis: Toward the End of Percutaneous Biopsy

PURPOSE

The aim of this study was to ascertain whether radiomics data can assist in differentiating small (<4 cm) clear cell renal cell carcinomas (ccRCCs) from small oncocytomas using T2-weighted magnetic resonance imaging (MRI).

MATERIAL AND METHODS

This retrospective study incorporated 48 tumors, 28 of which were ccRCCs and 20 were oncocytomas. All tumors were less than 4 cm in size and had undergone pre-biopsy or pre-surgery MRI. Following image pre-processing, 102 radiomics features were evaluated. A univariate analysis was performed using the Wilcoxon rank-sum test with Bonferroni correction. We compared multiple radiomics pipelines of normalization, feature selection, and machine learning (ML) algorithms, including random forest (RF), logistic regression (LR), AdaBoost, K-nearest neighbor, and support vector machine, using a supervised ML approach.

RESULTS

No statistically significant features were identified via the univariate analysis with Bonferroni correction. The most effective algorithm was identified using a pipeline incorporating standard normalization, RF-based feature selection, and LR, which achieved an area under the curve (AUC) of 83%, accuracy of 73%, sensitivity of 79%, and specificity of 65%. Subsequently, the most significant features were identified from this algorithm, and two groups of uncorrelated features were established based on Pearson correlation scores. Using these features, an algorithm was established after a pipeline of standard normalization and LR, achieving an AUC of 90%, an accuracy of 77%, sensitivity of 83%, and specificity of 69% for distinguishing ccRCCs from oncocytomas.

CONCLUSIONS

Radiomics analysis based on T2-weighted MRI can aid in distinguishing small ccRCCs from small oncocytomas. However, it is not superior to standard multiparameter renal MRI and does not yet allow us to dispense with percutaneous biopsy.

A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging

Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges.

Renal Mass Imaging with MRI Clear Cell Likelihood Score: A User's Guide

Small solid renal masses (SRMs) are frequently detected at imaging. Nearly 20% are benign, making careful evaluation with MRI an important consideration before deciding on management. Clear cell renal cell carcinoma (ccRCC) is the most common renal cell carcinoma subtype with potentially aggressive behavior. Thus, confident identification of ccRCC imaging features is a critical task for the radiologist. Imaging features distinguishing ccRCC from other benign and malignant renal masses are based on major features (T2 signal intensity, corticomedullary phase enhancement, and the presence of microscopic fat) and ancillary features (segmental enhancement inversion, arterial-to-delayed enhancement ratio, and diffusion restriction). The clear cell likelihood score (ccLS) system was recently devised to provide a standardized framework for categorizing SRMs, offering a Likert score of the likelihood of ccRCC ranging from 1 (very unlikely) to 5 (very likely). Alternative diagnoses based on imaging appearance are also suggested by the algorithm. Furthermore, the ccLS system aims to stratify which patients may or may not benefit from biopsy. The authors use case examples to guide the reader through the evaluation of major and ancillary MRI features of the ccLS algorithm for assigning a likelihood score to an SRM. The authors also discuss patient selection, imaging parameters, pitfalls, and areas for future development. The goal is for radiologists to be better equipped to guide management and improve shared decision making between the patient and treating physician. © RSNA, 2023 Quiz questions for this article are available in the supplemental material. See the invited commentary by Pedrosa in this issue.

MR Virtual Biopsy of Solid Renal Masses: An Algorithmic Approach

Between 1983 and 2002, the incidence of solid renal tumors increased from 7.1 to 10.8 cases per 100,000. This is in large part due to the increase in the volume of ultrasound and cross-sectional imaging, although a majority of solid renal tumors are still found incidentally. Ultrasound and computed tomography (CT) have been the mainstay of renal mass screening and diagnosis but recent advances in magnetic resonance (MR) technology have made this the optimal choice when diagnosing and staging renal tumors. Our purpose in writing this review is to survey the modern MR imaging approach to benign and malignant solid renal tumors, consolidate the various imaging findings into an easy-to-read reference, and provide an imaging-based, algorithmic approach to renal mass characterization for clinicians. MR is at the forefront of renal mass characterization, surpassing ultrasound and CT in its ability to describe multiple tissue parameters and predict tumor biology. Cutting-edge MR protocols and the integration of diagnostic algorithms can improve patient outcomes, allowing the imager to narrow the differential and better guide oncologic and surgical management.

Diagnostic Accuracy of MRI for Solid Renal Masses: A Systematic Review and Meta-analysis

BACKGROUND

Biparametric (bp)-MRI and multiparametric (mp)-MRI may improve the diagnostic accuracy of renal mass histology.

PURPOSE

To evaluate the available evidence on the diagnostic accuracy of bp-MRI and mp-MRI for solid renal masses in differentiating malignant from benign, aggressive from indolent, and clear cell renal cell carcinoma (ccRCC) from other histology.

STUDY TYPE

Systematic review.

POPULATION

MEDLINE, EMBASE, and CENTRAL up to January 11, 2022 were searched.

FIELD STRENGTH/SEQUENCE

1.5 or 3 Tesla.

ASSESSMENT

Eligible studies evaluated the accuracy of MRI (with at least two sequences: T2, T1, dynamic contrast and diffusion-weighted imaging) for diagnosis of solid renal masses in adult patients, using histology as reference standard. Risk of bias and applicability were assessed using QUADAS-2.

STATISTICAL TESTS

Meta-analysis using a bivariate logitnormal random effects model.

RESULTS

We included 10 studies (1239 masses from approximately 1200 patients). The risk of bias was high in three studies, unclear in five studies and low in two studies. The diagnostic accuracy of malignant (vs. benign) masses was assessed in five studies (64% [179/281] malignant). The summary estimate of sensitivity was 95% (95% confidence interval [CI]: 77%-99%), and specificity was 63% (95% CI: 46%-77%). No study assessed aggressive (vs. indolent) masses. The diagnostic accuracy of ccRCC (vs. other subtypes) was evaluated in six studies (47% [455/971] ccRCC): the summary estimate of sensitivity was 85% (95% CI: 77%-90%) and specificity was 77% (95% CI: 73%-81%).

DATA CONCLUSION

Our study reveals deficits in the available evidence on MRI for diagnosis of renal mass histology. The number of studies was limited, at unclear/high risk of bias, with heterogeneous definitions of solid masses, imaging techniques, diagnostic criteria, and outcome measures.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Role of multiparametric MRI in characterization of complicated cystic renal masses

Background

Bosniak classification improves sensitivity and specificity for malignancy among cystic renal masses characterized with MRI. The quantitative parameters derived from diffusion-weighted imaging, and contrast enhancement, can be used in distinguishing between benign and malignant cystic renal masses.

Methods

This prospective observational study included 58 patients (39 male and 19 female) with complicated cystic renal mass initially diagnosed by US or CT. All patients underwent multiparametric MRI study (Pre- and Post-Gd-enhanced T1WI, T2WI and DWI) by using 3 Tesla MRI scanner. Each cystic renal lesion was assigned a category based on Bosniak classification. Demographic data were recorded. ADC ratio, dynamic enhancement parameters in both corticomedullary and nephrographic phases as well as absolute washout were calculated and compared using ROC curve analysis.

Results

The sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of the multiparametric MRI in categorization of cystic renal masses according to Bosniak classification version 2019 were 90.32%, 100%, 100%, 90% and 94.83%, respectively, which was higher compared to biparametric MRI and conventional MRI.

Conclusions

Multiparametric MRI can be utilized to confidently evaluate cystic renal masses, overcoming the traditional limitations of overlapping morphological imaging features. Quantitative parameters derived from multiparametric MRI allow better evaluation of complex cystic renal tumors to distinguish between benign and malignant complex cystic renal lesions.

Deep-learning-based ensemble method for fully automated detection of renal masses on magnetic resonance images

Purpose

Accurate detection of small renal masses (SRM) is a fundamental step for automated classification of benign and malignant or indolent and aggressive renal tumors. Magnetic resonance image (MRI) may outperform computed tomography (CT) for SRM subtype differentiation due to improved tissue characterization, but is less explored compared to CT. The objective of this study is to autonomously detect SRM on contrast-enhanced magnetic resonance images (CE-MRI).

Approach

In this paper, we described a novel, fully automated methodology for accurate detection and localization of SRM on CE-MRI. We first determine the kidney boundaries using a U-Net convolutional neural network. We then search for SRM within the localized kidney regions using a mixture-of-experts ensemble model based on the U-Net architecture. Our dataset contained CE-MRI scans of 118 patients with different solid kidney tumor subtypes including renal cell carcinomas, oncocytomas, and fat-poor renal angiomyolipoma. We evaluated the proposed model on the entire CE-MRI dataset using 5-fold cross validation.

Results

The developed algorithm reported a Dice similarity coefficient of 91.20 ± 5.41 % (mean ± standard deviation) for kidney segmentation from 118 volumes consisting of 25,025 slices. Our proposed ensemble model for SRM detection yielded a recall and precision of 86.2% and 83.3% on the entire CE-MRI dataset, respectively.

Conclusions

We described a deep-learning-based method for fully automated SRM detection using CE-MR images, which has not been studied previously. The results are clinically important as SRM localization is a pre-step for fully automated diagnosis of SRM subtypes.

Performance of clear cell likelihood scores in characterizing solid renal masses at multiparametric MRI: an external validation study

PURPOSE

The purpose of this study is to evaluate the accuracy and interobserver agreement of ccLS in diagnosing clear cell renal cell carcinoma (ccRCC).

METHODS

This retrospective single-center study evaluated consecutive patients with solid renal masses who underwent mpMRI followed by percutaneous biopsy and/or surgical excision between January 2010 and December 2020. Predominantly (> 75%) cystic masses, masses with macroscopic fat and infiltrative masses were excluded. Two abdominal radiologists independently scored each renal mass according to the proposed ccLS algorithm. The diagnostic performance of ccLS categories for ccRCC was calculated using logistic regression modeling. Diagnostic accuracy for predicting ccRCC was calculated using 2 × 2 contingency tables. Interobserver agreement for ccLS was evaluated with Cohen's k statistic.

RESULTS

A total of 79 patients (mean age, 63 years ± 12 [SD], 50 men) with 81 renal masses were evaluated. The mean size was 36 mm ± 28 (range 10-160). Of the renal masses included, 44% (36/81) were ccRCC. The area under the receiver operating characteristic curve was 0.87 (95% CI 0.79-0.95). Using ccLS ≥ 4 to diagnose ccRCC, the sensitivity, specificity, and positive predictive value were 93% (95% CI 79, 99), 63% (95% CI 48, 77), and 67% (95% CI 58, 75), respectively. The negative predictive value of ccLS ≤ 2 was 93% (95% CI 64, 99). The proportion of ccRCC by ccLS category 1 to 5 were 10%, 0%, 10%, 57%, and 84%, respectively. Interobserver agreement was moderate (k = 0.47).

CONCLUSION

In this study, clear cell likelihood score had moderate interobserver agreement and resulted in 96% negative predictive value in excluding ccRCC.

Magnetic Resonance Imaging Virtual Biopsy of Common Solid Renal Masses-A Pictorial Review

ABSTRACT

The expanded application of radiologic imaging resulted in an increased incidence of renal masses in the recent decade. Clinically, it is difficult to determine the malignant potential of the renal masses, thus resulting in complex management. Image-guided biopsies are the ongoing standard of care to identify molecular variance but are limited by tumor accessibility and heterogeneity. With the evolving importance of individualized cancer therapies, radiomics has displayed promising results in the identification of tumoral mutation status on routine imaging. This article discusses how magnetic resonance imaging features can guide a radiologist toward identifying renal mass characteristics.

Advances in Imaging-Based Biomarkers in Renal Cell Carcinoma: A Critical Analysis of the Current Literature

Cross-sectional imaging is the standard diagnostic tool to determine underlying biology in renal masses, which is crucial for subsequent treatment. Currently, standard CT imaging is limited in its ability to differentiate benign from malignant disease. Therefore, various modalities have been investigated to identify imaging-based parameters to improve the noninvasive diagnosis of renal masses and renal cell carcinoma (RCC) subtypes. MRI was reported to predict grading of RCC and to identify RCC subtypes, and has been shown in a small cohort to predict the response to targeted therapy. Dynamic imaging is promising for the staging and diagnosis of RCC. PET/CT radiotracers, such as ¹⁸F-fluorodeoxyglucose (FDG), ¹²⁴I-cG250, radiolabeled prostate-specific membrane antigen (PSMA), and ¹¹C-acetate, have been reported to improve the identification of histology, grading, detection of metastasis, and assessment of response to systemic therapy, and to predict oncological outcomes. Moreover, ⁹⁹Tc-sestamibi and SPECT scans have shown promising results in distinguishing low-grade RCC from benign lesions. Radiomics has been used to further characterize renal masses based on semantic and textural analyses. In preliminary studies, integrated machine learning algorithms using radiomics proved to be more accurate in distinguishing benign from malignant renal masses compared to radiologists' interpretations. Radiomics and radiogenomics are used to complement risk classification models to predict oncological outcomes. Imaging-based biomarkers hold strong potential in RCC, but require standardization and external validation before integration into clinical routines.

Multiparametric magnetic resonance imaging for characterizing renal tumors: A validation study of the algorithm presented by Cornelis et al

Objectives

In the last decade, the incidence of renal cell carcinoma (RCC) has been rising, with the greatest increase observed for solid tumors. Magnetic resonance imaging (MRI) protocols and algorithms have recently been available for classifying RCC subtypes and benign subtypes. The objective of this study was to prospectively validate the MRI algorithm presented by Cornelis et al. for RCC classification.

Material and Methods

Over a 7-month period, 38 patients with 44 renal tumors were prospectively included in the study and received an MRI examination in addition to the conventional investigation program. The MRI sequences were: T2-weighted, dual chemical shift MRI, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced T1-weighted in wash-in and wash-out phases. The images were evaluated according to the algorithm by two experienced, blinded radiologists, and the histopathological diagnosis served as the gold standard.

Results

Of 44 tumors in 38 patients, only 8 tumors (18.2%) received the same MRI diagnosis according to the algorithm as the histopathological diagnosis. MRI diagnosed 16 angiomyolipoma, 14 clear cell RCC (ccRCC), 12 chromophobe RCC (chRCC), and two papillary RCC (pRCC), while histopathological examination diagnosed 24 ccRCC, four pRCC, one chRCC, and one mixed tumor of both pRCC and chRCC. Malignant tumors were statistically significantly larger than the benign (3.16 ± 1.34 cm vs. 2.00 ± 1.04 cm, P = 0.006).

Conclusion

This prospective study could not reproduce Cornelis et al.'s results and does not support differentiating renal masses using multiparametric MRI without percutaneous biopsy in the future. The MRI algorithm showed few promising results to categorize renal tumors, indicating histopathology for clinical decisions and follow-up regimes of renal masses are still required.

Predicting Oncologic Outcomes in Small Renal Tumors

BACKGROUND

Most patients diagnosed with renal cancer today present with small renal masses (SRMs). Although these patients have a low risk of dying from their disease and many are followed with active surveillance protocols, a small subset of renal cell carcinomas (RCCs) behave aggressively. Knowledge regarding features of aggressive behavior would enable better adoption of active surveillance strategies among these patients.

OBJECTIVE

We sought to improve prognostic models to predict metastasis-free survival after nephrectomy through focused analyses of clinicopathologic characteristics of SRMs associated with adverse outcomes.

DESIGN, SETTING, AND PARTICIPANTS

We identified consecutive patients with surgically resected SRMs (≤4 cm) at the University of Texas Southwestern Kidney Cancer Program between 1998 and 2020. In addition, we evaluated the ability of SRMs to form tumors when implanted in mice, an indicator of tumor aggressiveness.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

We examined the clinicopathologic factors associated with metastasis including prospectively performed BAP1 immunohistochemistry at our Clinical Laboratory Improvement Amendments laboratory. Multivariable Cox proportional hazard regression was used to predict metastasis-free survival.

RESULTS AND LIMITATIONS

A total of 3900 evaluable nephrectomies (from 3674 ethnically diverse patients) were identified, of which 1984 (51%) were SRMs including 1720 RCC. Of these patients with RCC (SRMRCC), 1576 did not have synchronous or metachronous larger RCCs and among these, 37 (2%) developed metastases. SRMRCC that metastasized were significantly enriched for aggressive morphologic phenotypes and engrafted in mice at comparable rates as larger metastatic tumors. BAP1 loss remained significantly associated with metastasis-free survival after accounting for TNM (tumor-node-metastasis) stage and SSIGN (stage, size, grade, and necrosis) score in multivariable analysis.

CONCLUSIONS

We identified clinicopathologic features that influence metastasis-free survival for patients with SRMRCC. If validated independently, these data should assist with patient prognosis and help with active surveillance strategies.

PATIENT SUMMARY

We report the identification of features of aggressiveness in small renal tumors that influence the likelihood of metastases after surgery.

Diagnostic Performance and Interreader Agreement of the MRI Clear Cell Likelihood Score for Characterization of cT1a and cT1b Solid Renal Masses: An External Validation Study

BACKGROUND. The clear cell likelihood score (ccLS) has been proposed for the noninvasive differentiation of clear cell renal cell carcinoma (ccRCC) from other renal neoplasms on multiparametric MRI (mpMRI), though further external validation remains needed. OBJECTIVE. The purpose of our study was to evaluate the diagnostic performance and interreader agreement of the ccLS version 2.0 (v2.0) for characterizing solid renal masses as ccRCC. METHODS. This retrospective study included 102 patients (67 men, 35 women; mean age, 56.9 ± 12.8 [SD] years) who underwent mpMRI between January 2013 and February 2018, showing a total of 108 (≥ 25% enhancing tissue) solid renal masses measuring 7 cm or smaller (83 cT1a [≤ 4 cm] and 25 cT1b [> 4 cm and ≤ 7 cm]), all with a histologic diagnosis. Three abdominal radiologists independently reviewed the MRI examinations using ccLS v2.0. Median reader sensitivity, specificity, and accuracy were computed for predicting ccRCC by ccLS of 4 or greater, and individual reader AUCs were derived. The percentage of masses that were ccRCC was calculated, stratified by ccLS. Interobserver agreement was assessed by the Fleiss kappa statistic. RESULTS. The sample included 45 ccRCCs (34 cT1a, 11 cT1b), 30 papillary renal cell carcinomas (RCCs), 13 chromophobe RCCs, 14 oncocytomas, and six fat-poor angiomyolipomas. Median reader sensitivity, specificity, and accuracy for predicting ccRCC by ccLS of 4 or greater were 85%, 82%, and 83% among cT1a masses and 82%, 100%, and 92% among cT1b masses. The three readers' AUCs for predicting ccRCC by ccLS for cT1a masses were 0.90, 0.84, and 0.89 and for cT1b masses were 0.99, 0.97, and 0.92. Across readers, the percentage of masses that were ccRCC among cT1a masses was 0%, 0%, 20%, 68%, and 93% for ccLS of 1, 2, 3, 4, and 5, respectively; among cT1b masses, the percentage of masses that were ccRCC was 0%, 0%, 32%, 90%, and 100% for ccLS of 1, 2, 3, 4, and 5, respectively. Interobserver agreement among cT1a and cT1b masses for ccLS of 4 or greater was 0.82 and 0.83 and for ccLS of 1-5 overall was 0.65 and 0.62, respectively. CONCLUSION. This study provides external validation of the ccLS, finding overall high measures of diagnostic performance and interreader agreement. CLINICAL IMPACT. The ccLS provides a standardized approach to the noninvasive diagnosis of ccRCC by MRI.

Development of a Multiparametric Renal CT Algorithm for Diagnosis of Clear Cell Renal Cell Carcinoma Among Small (≤ 4 cm) Solid Renal Masses

BACKGROUND. The MRI clear cell likelihood score predicts the likelihood that a renal mass is clear cell renal cell carcinoma (ccRCC). A CT-based algorithm has not yet been established. OBJECTIVE. The purpose of our study was to develop and evaluate a CT-based algorithm for diagnosing ccRCC among small (≤ 4 cm) solid renal masses. METHODS. This retrospective study included 148 patients (73 men, 75 women; mean age, 58 ± 12 [SD] years) with 148 small (≤ 4 cm) solid (> 25% enhancing tissue) renal masses that underwent renal mass CT (unenhanced, corticomedullary, and nephrographic phases) before resection between January 2016 and December 2019. Two radiologists independently evaluated CT examinations and recorded calcification, mass attenuation in all phases, mass-to-cortex corticomedullary attenuation ratio, and heterogeneity score (score on a 5-point Likert scale, assessed in corticomedullary phase). Features associated with ccRCC were identified by multivariable logistic regression analysis and then used to create a five-tiered CT score for diagnosing ccRCC. RESULTS. The masses comprised 53% (78/148) ccRCC and 47% (70/148) other histologic diagnoses. The mass-to-cortex corticomedullary attenuation ratio was higher for ccRCC than for other diagnoses (reader 1: 0.84 ± 0.68 vs 0.68 ± 0.65, p = .02; reader 2: 0.75 ± 0.29 vs 0.59 ± 0.25, p = .02). The heterogeneity score was higher for ccRCC than other diagnoses (reader 1: 4.0 ± 1.1 vs 1.5 ± 1.6, p < .001; reader 2: 4.4 ± 0.9 vs 3.3 ± 1.5, p < .001). Other features showed no difference. A five-tiered diagnostic algorithm including the mass-to-cortex corticomedullary attenuation ratio and heterogeneity score had interobserver agreement of 0.71 (weighted κ) and achieved an AUC for diagnosing ccRCC of 0.75 (95% CI, 0.68-0.82) for reader 1 and 0.72 (95% CI, 0.66-0.82) for reader 2. A CT score of 4 or greater achieved sensitivity, specificity, and PPV of 71% (95% CI, 59-80%), 79% (95% CI, 67-87%), and 79% (95% CI, 67-87%) for reader 1 and 42% (95% CI, 31-54%), 81% (95% CI, 70-90%), and 72% (95% CI, 56-84%) for reader 2. A CT score of 2 or less had NPV of 85% (95% CI, 69-95%) for reader 1 and 88% (95% CI, 69-97%) for reader 2. CONCLUSION. A five-tiered renal CT algorithm, including the mass-to-cortex corticomedullary attenuation ratio and heterogeneity score, had substantial interobserver agreement, moderate AUC and PPV, and high NPV for diagnosing ccRCC. CLINICAL IMPACT. The CT algorithm, if validated, may represent a useful clinical tool for diagnosing ccRCC.

Systematic review and meta-analysis of multiparametric MRI clear cell likelihood scores for classification of small renal masses

Purpose

To systematically assess the multiparametric MRI clear cell likelihood score (ccLS) algorithm for the classification of small renal masses (SRM).

Methods

We conducted an electronic literature search on Web of Science, MEDLINE (Ovid and PubMed), Cochrane Library, EMBASE, and Google Scholar to identify relevant articles from 2017 up to June 30, 2022. We included studies reporting the diagnostic performance of the ccLS for characterization of solid SRM. The bivariate model and hierarchical summary receiver operating characteristic (HSROC) model were used to pool sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR−), and diagnostic odds ratio (DOR). The quality evaluation was performed with the Quality Assessment of Diagnostic Accuracy Studies-2 tool.

Results

A total of 6 studies with 825 renal masses (785 patients) were included in the current meta-analysis. The pooled sensitivity and specificity for cT1a renal masses were 0.80 (95% CI 0.75–0.85) and 0.74 (95% CI 0.65–0.81) at the threshold of ccLS ≥4, the pooled LR+, LR−, and DOR were 3.04 (95% CI 2.34-3.95), 0.27 (95% CI 0.22–0.33), and 11.4 (95% CI 8.2-15.9), respectively. The area under the HSROC curve was 0.84 (95% CI 0.81–0.87). For all cT1 renal masses, the pooled sensitivity and specificity were 0.80 (95% CI 0.74–0.85) and 0.76 (95% CI 0.67–0.83).

Conclusions

The ccLS had moderate to high accuracy for identifying ccRCC from other RCC subtypes and with a moderate inter-reader agreement. However, its diagnostic performance remain needs multi-center, large cohort studies to validate in the future.

Defining the Magnetic Resonance Features of Renal Lesions and Their Response to Everolimus in a Transgenic Mouse Model of Tuberous Sclerosis Complex

Tuberous sclerosis complex (TSC) is an inherited genetic disorder characterized by mutations in TSC1 or TSC2 class of tumor suppressers which impact several organs including the kidney. The renal manifestations are usually in the form of angiomyolipoma (AML, in 80% of the cases) and cystadenomas. mTOR inhibitors such as rapamycin and everolimus have shown efficacy in reducing the renal tumor burden. Early treatment prevents the progression of AML; however, the tumors regrow upon cessation of therapy implying a lifelong need for monitoring and management of this morbid disease. There is a critical need for development of imaging strategies to monitor response to therapy and progression of disease which will also facilitate development of newer targeted therapy. In this study we evaluated the potential of multiparametric ¹H magnetic resonance imaging (mpMRI) to monitor tumor response to therapy in a preclinical model of TSC, the transgenic mouse A/J Tsc2^+/-. We found 2-dimensional T₂-weighted sequence with 0.5 mm slice thickness to be optimal for detecting renal lesions as small as 0.016 mm³. Baseline characterization of lesions with MRI to assess physiological parameters such as cellularity and perfusion is critical for distinguishing between cystic and solid lesions. Everolimus treatment for three weeks maintained tumor growth at 36% from baseline, while control tumors displayed steady growth and were 70% larger than baseline at the end of therapy. Apparent diffusion coefficient, T₁ values and normalized T₂ intensity changes were also indictive of response to treatment. Our results indicate that standardization and implementation of improved MR imaging protocols will significantly enhance the utility of mpMRI in determining the severity and composition of renal lesions for better treatment planning.

Multicenter Evaluation of Multiparametric MRI Clear Cell Likelihood Scores in Solid Indeterminate Small Renal Masses

Background Solid small renal masses (SRMs) (≤4 cm) represent benign and malignant tumors. Among SRMs, clear cell renal cell carcinoma (ccRCC) is frequently aggressive. When compared with invasive percutaneous biopsies, the objective of the proposed clear cell likelihood score (ccLS) is to classify ccRCC noninvasively by using multiparametric MRI, but it lacks external validation. Purpose To evaluate the performance of and interobserver agreement for ccLS to diagnose ccRCC among solid SRMs. Materials and Methods This retrospective multicenter cross-sectional study included patients with consecutive solid (≥25% approximate volume enhancement) SRMs undergoing multiparametric MRI between December 2012 and December 2019 at five academic medical centers with histologic confirmation of diagnosis. Masses with macroscopic fat were excluded. After a 1.5-hour training session, two abdominal radiologists per center independently rendered a ccLS for 50 masses. The diagnostic performance for ccRCC was calculated using random-effects logistic regression modeling. The distribution of ccRCC by ccLS was tabulated. Interobserver agreement for ccLS was evaluated with the Fleiss κ statistic. Results A total of 241 patients (mean age, 60 years ± 13 [SD]; 174 men) with 250 solid SRMs were evaluated. The mean size was 25 mm ± 8 (range, 10-39 mm). Of the 250 SRMs, 119 (48%) were ccRCC. The sensitivity, specificity, and positive predictive value for the diagnosis of ccRCC when ccLS was 4 or higher were 75% (95% CI: 68, 81), 78% (72, 84), and 76% (69, 81), respectively. The negative predictive value of a ccLS of 2 or lower was 88% (95% CI: 81, 93). The percentages of ccRCC according to the ccLS were 6% (range, 0%-18%), 38% (range, 0%-100%), 32% (range, 60%-83%), 72% (range, 40%-88%), and 81% (range, 73%-100%) for ccLSs of 1-5, respectively. The mean interobserver agreement was moderate (κ = 0.58; 95% CI: 0.42, 0.75). Conclusion The clear cell likelihood score applied to multiparametric MRI had moderate interobserver agreement and differentiated clear cell renal cell carcinoma from other solid renal masses, with a negative predictive value of 88%. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Mileto and Potretzke in this issue.

Transfer learning-based approach for automated kidney segmentation on multiparametric MRI sequences

Purpose: Multiparametric magnetic resonance imaging (mp-MRI) is being investigated for kidney cancer because of better soft tissue contrast ability. The necessity of manual labels makes the development of supervised kidney segmentation algorithms challenging for each mp-MRI protocol. Here, we developed a transfer learning-based approach to improve kidney segmentation on a small dataset of five other mp-MRI sequences. Approach: We proposed a fully automated two-dimensional (2D) attention U-Net model for kidney segmentation on T1 weighted-nephrographic phase contrast enhanced (CE)-MRI (T1W-NG) dataset ( N = 108 ). The pretrained weights of T1W-NG kidney segmentation model transferred to five other distinct mp-MRI sequences model (T2W, T1W-in-phase (T1W-IP), T1W-out-of-phase (T1W-OP), T1W precontrast (T1W-PRE), and T1W-corticomedullary-CE (T1W-CM), N = 50 ) and fine-tuned by unfreezing the layers. The individual model performances were evaluated with and without transfer-learning fivefold cross-validation on average Dice similarity coefficient (DSC), absolute volume difference, Hausdorff distance (HD), and center-of-mass distance (CD) between algorithm generated and manually segmented kidneys. Results: The developed 2D attention U-Net model for T1W-NG produced kidney segmentation DSC of 89.34 ± 5.31 % . Compared with randomly initialized weight models, the transfer learning-based models of five mp-MRI sequences showed average increase of 2.96% in DSC of kidney segmentation ( p = 0.001 to 0.006). Specifically, the transfer-learning approach increased average DSC on T2W from 87.19% to 89.90%, T1W-IP from 83.64% to 85.42%, T1W-OP from 79.35% to 83.66%, T1W-PRE from 82.05% to 85.94%, and T1W-CM from 85.65% to 87.64%. Conclusions: We demonstrate that a pretrained model for automated kidney segmentation of one mp-MRI sequence improved automated kidney segmentation on five other additional sequences.

Novel Imaging Methods for Renal Mass Characterization: A Collaborative Review

CONTEXT

The incidental detection of localized renal masses has been rising steadily, but a significant proportion of these tumors are benign or indolent and, in most cases, do not require treatment. At the present time, a majority of patients with an incidentally detected renal tumor undergo treatment for the presumption of cancer, leading to a significant number of unnecessary surgical interventions that can result in complications including loss of renal function. Thus, there exists a clinical need for improved tools to aid in the pretreatment characterization of renal tumors to inform patient management.

OBJECTIVE

To systematically review the evidence on noninvasive, imaging-based tools for solid renal mass characterization.

EVIDENCE ACQUISITION

The MEDLINE database was systematically searched for relevant studies on novel imaging techniques and interpretative tools for the characterization of solid renal masses, published in the past 10 yr.

EVIDENCE SYNTHESIS

Over the past decade, several novel imaging tools have offered promise for the improved characterization of indeterminate renal masses. Technologies of particular note include multiparametric magnetic resonance imaging of the kidney, molecular imaging with targeted radiopharmaceutical agents, and use of radiomics as well as artificial intelligence to enhance the interpretation of imaging studies. Among these, 99mTc-sestamibi single photon emission computed tomography/computed tomography (CT) for the identification of benign renal oncocytomas and hybrid oncocytic chromophobe tumors, and positron emission tomography/CT imaging with radiolabeled girentuximab for the identification of clear cell renal cell carcinoma, are likely to be closest to implementation in clinical practice.

CONCLUSIONS

A number of novel imaging tools stand poised to aid in the noninvasive characterization of indeterminate renal masses. In the future, these tools may aid in patient management by providing a comprehensive virtual biopsy, complete with information on tumor histology, underlying molecular abnormalities, and ultimately disease prognosis.

PATIENT SUMMARY

Not all renal tumors require treatment, as a significant proportion are either benign or have limited metastatic potential. Several innovative imaging tools have shown promise for their ability to improve the characterization of renal tumors and provide guidance in terms of patient management.

How We Do It: Managing the Indeterminate Renal Mass with the MRI Clear Cell Likelihood Score

The widespread use of cross-sectional imaging has led to a continuous increase in the number of incidentally detected indeterminate renal masses. Frequently, these clinical scenarios involve an older patient with comorbidities and a small renal mass (≤4 cm). Despite aggressive treatment in early stages of the disease, a clear positive effect in reducing kidney cancer-specific mortality is lacking, indicating that many renal cancers exhibit an indolent oncologic behavior. Furthermore, in general, one in five small renal masses is histologically benign and may not benefit from aggressive treatment. Although active surveillance is increasingly recognized as a management option for some patients, the absence of reliable clinical and imaging predictive biologic markers of aggressiveness can contribute to patient anxiety and limit its use in clinical practice. A standardized approach to the image interpretation of solid renal masses has not been broadly implemented. The clear cell likelihood score (ccLS) derived from multiparametric MRI is useful in noninvasively identifying the clear cell subtype, the most common and aggressive form of kidney cancer. Herein, a review of the ccLS is presented, including a step-by-step guide for image interpretation and additional guidance for its implementation in clinical practice.

Comparison of cortico-medullary phase contrast-enhanced MDCT and T2-weighted MR imaging in the histological subtype differentiation of renal cell carcinoma: radiology-pathology correlation

Purpose

Renal cell carcinoma (RCC) subtype differentiation is of crucial importance in the management and prognosis of these patients. In this study, we investigated the usefulness of unenhanced and cortico-medullary phase contrast-enhanced multidetector-row computed tomography (MDCT) and T2-weighted fast spin-echo (FSE) magnetic resonance imaging (MRI) modalities in the discrimination of the 3 main subtype RCC patients in correlation with their histopathological findings.

Material and methods

A total of 80 pathologically proven RCC patients who had undergone either partial or total nephrectomy were retrospectively investigated in this study. Their histological subtypes were 54 clear cell renal cell carcinoma (ccRCC), 15 papillary renal cell carcinoma (pRCC), and 11 chromophobe renal cell carcinoma (cRCC), based on pathological evaluation. There were 62 male (77.5%) and 18 female (22.5%) patients. Among the 54 ccRCC patients, 29 patients had both non-contrast and cortico-medullary phase CT, 1 had only non-contrast CT, 5 only had cortico-medullary phase CT, and 38 had MRI examination. In the pRCC group, 10 patients had both non-contrast and cortico-medullary phase CT, 1 had only non-contrast CT, 1 had only cortico-medullary phase CT, and 12 had MRI. Finally, in the remaining 11 cRCC patients, 9 had both non-contrast and cortico-medullary phase CT, and only 5 had MRI. We calculated both tumour attenuation values as HU (Hounsfield units) on unenhanced and cortico-medullary phase MDCT images and also tumour mean signal intensity values on FSE T2-weighted MRI images by using the region of interest (ROI) including normal renal cortex measurements. Besides quantitative evaluation, we also performed qualitative visual assessment of tumours on contrast-enhanced MDCT and FSE T2-weighted MRI.

Results

There was no statistically significant difference among the attenuation values of the 3 tumour subtypes on pre-contrast CT images. ccRCC demonstrated a prominent degree of contrast enhancement compared to the chromophobe and papillary ones on cortico-medullary phase MDCT. We found no statistically significant difference between chromophobe and papillary subtypes, although chromophobe tumours showed slightly higher attenuation values compared to papillary ones. ccRCCs usually demonstrated a heterogenous contrast enhancement on cortico-medullary phase CT images, while the papillary subtype usually had a homogenous appearance on visual assessment. On FSE T2-weighted MR images, the signal intensity values of ccRCC patients were found to be significantly higher than both chromophobe and papillary subtypes. Although cRCC patients had a prominently lower T2 signal intensity than clear cell subtype, there was no statistically significant signal intensity difference between chromophobe and papillary subtypes. Regarding visual assessment, papillary subtype tumours showed a mostly homogenous appearance on T2-weighted images and a statistically significant difference was present. On the other hand, there was no significant difference of visual assessment of the clear cell and chromophobe subtypes.

Conclusions

The measurement of the attenuation values on cortico-medullary phase MDCT and the mean signal intensity values on FSE T2-weighted MRI can provide useful information in the differentiation of RCC main subtypes. Also, visual assessment of tumours on both modalities can contribute to this issue by providing additional imaging properties.

Quantitative 3-tesla multiparametric MRI in differentiation between renal cell carcinoma subtypes

Background

MRI provides several distinct quantitative parameters that may better differentiate renal cell carcinoma (RCC) subtypes. The purpose of the study is to evaluate the diagnostic accuracy of apparent diffusion coefficient (ADC), chemical shift signal intensity index (SII), and contrast enhancement in differentiation between different subtypes of renal cell carcinoma.

Results

There were 63 RCC as regard surgical histopathological analysis: 43 clear cell (ccRCC), 12 papillary (pRCC), and 8 chromophobe (cbRCC). The mean ADC ratio for ccRCC (0.75 ± 0.13) was significantly higher than that of pRCC (0.46 ± 0.12, P < 0.001) and cbRCC (0.41 ± 0.15, P < 0.001). The mean ADC value for ccRCC (1.56 ± 0.27 × 10−3 mm2/s) was significantly higher than that of pRCC (0.96 ± 0.25 × 10−3 mm2/s, P < 0.001) and cbRCC (0.89 ± 0.29 × 10−3 mm2/s, P < 0.001). The mean SII of pRCC (1.49 ± 0.04) was significantly higher than that of ccRCC (0.93 ± 0.01, P < 0.001) and cbRCC (1.01 ± 0.16, P < 0.001). The ccRCC absolute corticomedullary enhancement (196.7 ± 81.6) was significantly greater than that of cbRCC (177.8 ± 77.7, P < 0.001) and pRCC (164.3 ± 84.6, P < 0.001).

Conclusion

Our study demonstrated that multiparametric MRI is able to afford some quantitative features such as ADC ratio, SII, and absolute corticomedullary enhancement which can be used to accurately distinguish different subtypes of renal cell carcinoma.

Association between nuclear grade of renal cell carcinoma and the aorta-lesion-attenuation-difference

INTRODUCTION AND BACKGROUND

Several features noted on renal mass biopsy (RMB) can influence treatment selection including tumor histology and nuclear grade. However, there is poor concordance between renal cell carcinoma (RCC) nuclear grade on RMB compared to nephrectomy specimens. Here, we evaluate the association of nuclear grade with aorta-lesion-attenuation-difference (ALAD) values determined on preoperative CT scan.

METHODS AND MATERIALS

A retrospective review of preoperative CT scans and surgical pathology was performed on patients undergoing nephrectomy for solid renal masses. ALAD was calculated by measuring the difference in Hounsfield units (HU) between the aorta and the lesion of interest on the same image slice on preoperative CT scan. The discriminative ability of ALAD to differentiate low-grade (nuclear grade 1 and 2) and high-grade (nuclear grade 3 and 4) tumors was evaluated by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under curve (AUC) using ROC analysis. Sub-group analysis by histologic sub-type was also performed.

RESULTS

A total of 368 preoperative CT scans in patients with RCC on nephrectomy specimen were reviewed. Median patient age was 61 years (IQR 52-68). The majority of patients were male, 66% (243/368). Tumor histology was chromophobe RCC in 7.6%, papillary RCC in 15.5%, and clear cell RCC in 76.9%. The majority, 69.3% (253/365) of tumors, were stage T1a. Nuclear grade was grade 1 in 5.46% (19/348), grade 2 in 64.7% (225/348), grade 3 in 26.2% (91/348), and grade 4 in 3.2% (11/348). Nephrographic ALAD values for grade 1, 2, 3, and 4 were 73.7, 46.5, 36.4, and 43.1, respectively (p = 0.0043). Nephrographic ALAD was able to differentiate low-grade from high-grade RCC with a sensitivity of 32%, specificity of 89%, PPV of 86%, and NPV of 36%. ROC analysis demonstrated the predictive utility of nephrographic ALAD to predict high- versus low-grade RCC with an AUC of 0.60 (95% CI 0.51-0.69).

CONCLUSION

ALAD was significantly associated with nuclear grade in our nephrectomy series. Strong specificity and PPV for the nephrographic phrase demonstrate a potential role for ALAD in the pre-operative setting that may augment RMB findings in assessing nuclear grade of RCC. Although this association was statistically significant, the clinical utility is limited at this time given the results of the statistical analysis (relatively poor ROC analysis). Sub-group analysis by histologic subtype yielded very similar diagnostic performance and limitations of ALAD. Further studies are necessary to evaluate this relationship further.

Active Surveillance of Renal Masses: The Role of Radiology

Active surveillance of renal masses, which includes serial imaging with the possibility of delayed treatment, has emerged as a viable alternative to immediate therapeutic intervention in selected patients. Active surveillance is supported by evidence that many benign masses are resected unnecessarily, and treatment of small cancers has not substantially reduced cancer-specific mortality. These data are a call to radiologists to improve the diagnosis of benign renal masses and differentiate cancers that are biologically aggressive (prompting treatment) from those that are indolent (allowing treatment deferral). Current evidence suggests that active surveillance results in comparable cancer-specific survival with a low risk of developing metastasis. Radiology is central in this. Imaging is used at the outset to estimate the probability of malignancy and degree of aggressiveness in malignant masses and to follow up masses for growth and morphologic change. Percutaneous biopsy is used to provide a more definitive histologic diagnosis and to guide treatment decisions, including whether active surveillance is appropriate. Emerging applications that may improve imaging assessment of renal masses include standardized assessment of cystic and solid masses and radiomic analysis. This article reviews the current and future role of radiology in the care of patients with renal masses undergoing active surveillance.

Cross-sectional imaging assessment of renal masses with emphasis on MRI

Magnetic resonance imaging (MRI) is a useful complementary imaging tool for the diagnosis and characterization of renal masses, as it provides both morphologic and functional information. A core MRI protocol for renal imaging should include a T1-weighted sequence with in- and opposed-phase images (or, alternatively with DIXON technique), T2-weighted and diffusion-weighted images as well as a dynamic contrast-enhanced sequence with subtraction images, followed by a delayed post-contrast T1-weighted sequence. The main advantages of MRI over computed tomography include increased sensitivity for contrast enhancement, less sensitivity for detection of calcifications, absence of pseudoenhancement, and lack of radiation exposure. MRI may be applied for renal cystic lesion characterization, differentiation of renal cell carcinoma (RCC) from benign solid renal tumors, RCC histologic grading, staging, post-treatment follow-up, and active surveillance of patients with treated or untreated RCC.

Association of Clear Cell Likelihood Score on MRI and Growth Kinetics of Small Solid Renal Masses on Active Surveillance

Background: The lack of validated imaging markers to characterize biologic aggressiveness of small renal masses (SRMs; cT1a, ≤4 cm) hinders medical decision making amongst available initial management strategies. Objective: To explore the association of the clear cell likelihood score (ccLS) on MRI with growth rates and progression of SRMs. Methods: This retrospective study included consecutive SRMs assigned a ccLS on clinical MRI examinations performed between June 2016 and November 2019 at an academic tertiary-care medical center or its affiliated safety net hospital system. The ccLS scores the likelihood that the SRM represents clear cell renal cell carcinoma (ccRCC) from 1 (very unlikely) to 5 (very likely). The ccLS was extracted from clinical reports. Tumor size measurements were extracted from available prior and follow-up cross-sectional imaging examinations, through June 2020. Serial tumor size measurements were fit to linear and exponential growth curves. Estimated growth rates were grouped by the assigned ccLS. Tumor progression was defined by development of large size (>4 cm in at least two measurements) and/or rapid growth (doubling of volume within 1 year). Differences among ccLS groups were evaluated using Kruskal-Wallis tests. Correlation between ccLS and growth rate were evaluated by Spearman correlation (ρ). Results: Growth rates of 386 SRMs (100 ccLS1-2, 75 ccLS3, and 211 ccLS4-5) from 339 patients (median age 65 years; 198 men, 141 women) were analyzed. Median follow-up was 1.16 years. The ccLS was correlated with growth rates by size (ρ=0.19, p<.001; ccLS4-5: 9%/year, ccLS1-2: 5%/year, p<.001) and by volume (ρ=0.136, p=.008; ccLS4-5: 29%/year, ccLS1-2: 16%/year, p<.001). Disease progression (observed in 49 SRMs) was not significantly associated with ccLS group (p=.61). Two patients (0.6%) developed metastases during active surveillance (AS): one ccLS1 that was a type 2 papillary renal cell carcinoma and one ccLS4 that was ccRCC. Conclusions: Growth is associated with ccLS in SRMs, with higher ccLS correlating with faster growth. Clinical Impact: The non-invasive clear cell likelihood score (ccLS), derived from MRI, correlates with growth rate of SRMs and may help guide personalized management. SRMs with lower ccLS may be considered for AS, whereas SRMs with higher ccLS may warrant earlier intervention.

The diagnostic utility of diffusion weighted MRI imaging and ADC ratio to distinguish benign from malignant renal masses: sorting the kittens from the tigers

Background

MRI is playing an increasing role in risk stratification and non-invasive diagnosis of the undifferentiated small renal mass. This study was designed to assess the reliability of MRI in diagnostic evaluation of renal masses, specifically characterising lesions with diffusion weighted imaging (DWI) and apparent diffusion coefficient (ADC) values.

Methods

This is a retrospective analysis of patients undergoing MRI as part of their clinical workup for a renal mass suspicious for renal cell carcinoma (RCC) on CT or ultrasound followed by biopsy and/or surgical excision. All cases were conducted on 3 Tesla MRI, with conventional breath-held sequences, DWI and dynamic contrast enhanced phases. Tumour regions of interest were evaluated on ADC maps and compared with T2 weighted and post-contrast images.

Results

Of the 66 renal tumours included, 33 (50.0%) were Clear Cell RCC, 11 (16.7%) were Oncocytoma, nine (13.6%) were Angiomyolipoma (AML), nine (13.6%) were Papillary RCC and four (6.1%) were Chromophobe RCC. Oncocytoma had the largest ADC values, significantly larger than AMLs and all RCC subtypes (p < 0.001). The average ADC value was also significantly larger in Clear Cell RCCs compared to AMLs, and other RCC subtypes (p < 0.001).

Conclusions

MRI with DWI/ADC imaging may aid the differentiation of oncocytomas from RCCs and stratify RCC subtypes, Further studies are required to validate these findings.

Trial registration: Not applicable/retrospective study.

Magnetic Resonance Imaging Radiomics Analyses for Prediction of High-Grade Histology and Necrosis in Clear Cell Renal Cell Carcinoma: Preliminary Experience

INTRODUCTION

Percutaneous renal mass biopsy results can accurately diagnose clear cell renal cell carcinoma (ccRCC); however, their reliability to determine nuclear grade in larger, heterogeneous tumors is limited. We assessed the ability of radiomics analyses of magnetic resonance imaging (MRI) to predict high-grade (HG) histology in ccRCC.

PATIENTS AND METHODS

Seventy patients with a renal mass underwent 3 T MRI before surgery between August 2012 and August 2017. Tumor length, first-order statistics, and Haralick texture features were calculated on T2-weighted and dynamic contrast-enhanced (DCE) MRI after manual tumor segmentation. After a variable clustering algorithm was applied, tumor length, washout, and all cluster features were evaluated univariably by receiver operating characteristic curves. Three logistic regression models were constructed to assess the predictability of HG ccRCC and then cross-validated.

RESULTS

At univariate analysis, area under the curve values of length, and DCE texture cluster 1 and cluster 3 for diagnosis of HG ccRCC were 0.7 (95% confidence interval [CI], 0.58-0.82, false discovery rate P = .008), 0.72 (95% CI, 0.59-0.84, false discovery rate P = .004), and 0.75 (95% CI, 0.63-0.87, false discovery rate P = .0009), respectively. At multivariable analysis, area under the curve for model 1 (tumor length only), model 2 (length + DCE clusters 3 and 4), and model 3 (DCE cluster 1 and 3) for diagnosis of HG ccRCC were 0.67 (95% CI, 0.54-0.79), 0.82 (95% CI, 0.71-0.92), and 0.81 (95% CI, 0.70-0.91), respectively.

CONCLUSION

Radiomics analysis of MRI images was superior to tumor size for the prediction of HG histology in ccRCC in our cohort.

Characterizing T2 iso- and hypo-intense renal masses on MRI: Can templated algorithms improve accuracy?

PURPOSE

To assess if a templated algorithm can improve the diagnostic performance of MRI for characterization of T2 isointense and hypointense renal masses.

METHODS

In this retrospective study, 60 renal masses with histopathologic diagnoses that were also confirmed as T2 iso- or hypointense on MRI were identified (mean ± standard deviation, range: 3.9 ± 2.5, 1.0-13.7 cm). Two semi-quantitative diagnostic algorithms were created based on MRI features of renal masses reported in the literature. Three body-MRI trained radiologists provided clinical diagnoses based on their experience and separately provided semiquantitative data for each components of the two algorithms. The algorithms were applied separately by a radiology trainee without additional interpretive input. Logistic regression was used to compare the accuracy of the three methods in distinguishing malignant versus benign lesions and in diagnosing the exact histopathology. Inter-reader agreement for each method was calculated using Fleiss' kappa statistics.

RESULTS

The accuracy of the two algorithms and clinical experience were similar (70%, 69%, and 64%, respectively, p = 0.22-0.32), with fair to moderate inter-reader agreement (Fleiss's kappa: r = 0.375, r = 0.308, r = 0.375, respectively, all p < 0.0001). The accuracy of the two algorithms and clinical experience in diagnosing specific histopathology were also no different from each other (34%, 29%, and 32%, respectively, p = 0.49-0.74), with fair to moderate inter-reader agreement (Fleiss's kappa: r = 0.20, r = 0.28, r = 0.375, respectively, all p < 0.0001).

CONCLUSION

Semi-quantitative templated algorithms based on MRI features of renal masses did not improve the ability to diagnose T2 iso- and hypointense renal masses when compared to unassisted interpretation by body MR trained subspecialists.

Effect of phase of enhancement on texture analysis in renal masses evaluated with non-contrast-enhanced, corticomedullary, and nephrographic phase-enhanced CT images

OBJECTIVE

To compare texture analysis (TA) features of solid renal masses on renal protocol (non-contrast enhanced [NECT], corticomedullary [CM], nephrographic [NG]) CT.

MATERIALS AND METHODS

A total of 177 consecutive solid renal masses (116 renal cell carcinoma [RCC]; 51 clear cell [cc], 40 papillary, 25 chromophobe, and 61 benign masses; 49 oncocytomas, 12 fat-poor angiomyolipomas) with three-phase CT between 2012 and 2017 were studied. Two blinded radiologists independently assessed tumor heterogeneity (5-point Likert scale) and segmented tumors. TA features (N = 25) were compared between groups and between phases. Accuracy (area under the curve [AUC]) for RCC versus benign and cc-RCC versus other masses was compared.

RESULTS

Subjectively, tumor heterogeneity differed between phases (p < 0.01) and between tumors within the same phase (p = 0.03 [NECT] and p < 0.01 [CM, NG]). Inter-observer agreement was moderate to substantial (intraclass correlation coefficient = 0.55-0.73). TA differed in 92.0% (23/25) features between phases (p < 0.05) except for GLNU and f6. More TA features differed significantly on CM (80.0% [20/25]) compared with NG (40.0% [10/25]) and NECT (16.0% [4/25]) (p < 0.01). For RCC versus benign, AUCs of texture features did not differ comparing CM and NG (p > 0.05), but were higher for 20% (5/25) and 28% (7/25) of features comparing CM and NG with NECT (p < 0.05). For cc-RCC versus other, 36% (9/25) and 40% (10/25) features on CM had higher AUCs compared with NECT and NG images (p < 0.05).

CONCLUSION

Texture analysis of renal masses differs, when evaluated subjectively and quantitatively, by phase of CT enhancement. The corticomedullary phase had the highest discriminatory value when comparing masses and for differentiating cc-RCC from other masses.

KEY POINTS

• Subjectively evaluated renal tumor heterogeneity on CT differs by phase of enhancement. • Quantitative CT texture analysis features in renal tumors differ by phases of enhancement with the corticomedullary phase showing the highest number and most significant differences compared with non-contrast-enhanced and nephrographic phase images. • For diagnosis of clear cell RCC, corticomedullary phase texture analysis features had improved accuracy of classification in approximately 40% of features studied compared with non-contrast-enhanced and nephrographic phase images.

Importance of phase enhancement for machine learning classification of solid renal masses using texture analysis features at multi-phasic CT

OBJECTIVE

To compare machine learning (ML) of texture analysis (TA) features for classification of solid renal masses on non-contrast-enhanced CT (NCCT), corticomedullary (CM) and nephrographic (NG) phase contrast-enhanced (CE) CT.

MATERIALS AND METHODS

With IRB approval, we retrospectively identified 177 consecutive solid renal masses (116 renal cell carcinoma [RCC]; 51 clear cell [cc], 40 papillary, 25 chromophobe and 61 benign tumors; 49 oncocytomas and 12 fat-poor angiomyolipomas) with renal protocol CT between 2012 and 2017. Tumors were independently segmented by two blinded radiologists. Twenty-five 2-dimensional TA features were extracted from each phase. Diagnostic accuracy for 1) RCC versus benign tumor and 2) cc-RCC versus other tumor was assessed using XGBoost.

RESULTS

ML of texture analysis features on different phases achieved mean area under the ROC curve (AUC [SD]), sensitivity/specificity for 1) RCC vs benign = 0.70(0.19), 96%/32% on CM-CECT and 0.71(0.14), 83%/58% on NG-CECT and; 2) cc-RCC vs other = 0.77(0.12), 49%/90% on CM-CECT and 0.71(0.16), 22%/94% on NG-CECT. There was no difference in AUC comparing CECT to NCCT (p = 0.058-0.54) and no improvement when combining data across all three phases compared single-phase assessment (p = 0.39-0.68) for either outcome. AUCs decreased when ML models were trained with one phase and tested on a different phase for both outcomes (RCC;p = 0.045-0.106, cc-RCC; < 0.001).

CONCLUSION

Accuracy of machine learning classification of renal masses using texture analysis features did not depend on phase; however, models trained using one phase performed worse when tested on another phase particularly when associating NCCT and CECT. These findings have implications for large registries which use varying CT protocols to study renal masses.

Prospective performance of clear cell likelihood scores (ccLS) in renal masses evaluated with multiparametric magnetic resonance imaging

OBJECTIVES

Solid renal masses have unknown malignant potential with commonly utilized imaging. Biopsy can offer a diagnosis of cancer but has a high non-diagnostic rate and complications. Reported use of multiparametric magnetic resonance imaging (mpMRI) to diagnose aggressive histology (i.e., clear cell renal cell carcinoma (ccRCC)) via a clear cell likelihood score (ccLS) was based on retrospective review of cT1a tumors. We aim to retrospectively assess the diagnostic performance of ccLS prospectively assigned to renal masses of all stages evaluated with mpMRI prior to histopathologic evaluation.

METHODS

In this retrospective cohort study from June 2016 to November 2019, 434 patients with 454 renal masses from 2 institutions with heterogenous patient populations underwent mpMRI with prospective ccLS assignment and had pathologic diagnosis. ccLS performance was assessed by contingency table analysis. The association between ccLS and ccRCC was assessed with logistic regression.

RESULTS

Mean age and tumor size were 60 ± 13 years and 5.4 ± 3.8 cm. Characteristics were similar between institutions except for patient age and race (both p < 0.001) and lesion laterality and histology (both p = 0.04). The PPV of ccLS increased with each increment in ccLS (ccLS1 5% [3/55], ccLS2 6% [3/47], ccLS3 35% [20/57], ccLS4 78% [85/109], ccLS5 93% [173/186]). Pooled analysis for ccRCC diagnosis revealed sensitivity 91% (258/284), PPV 87% (258/295) for ccLS ≥ 4, and specificity 56% (96/170), NPV 94% (96/102) for ccLS ≤ 2. Diagnostic performance was similar between institutions.

CONCLUSIONS

We confirm the optimal diagnostic performance of mpMRI to identify ccRCC in all clinical stages. High PPV and NPV of ccLS can help inform clinical management decision-making.

KEY POINTS

• The positive predictive value of the clear cell likelihood score (ccLS) for detecting clear cell renal cell carcinoma was 5% (ccLS1), 6% (ccLS2), 35% (ccLS3), 78% (ccLS4), and 93% (ccLS5). Sensitivity of ccLS ≥ 4 and specificity of ccLS ≤ 2 were 91% and 56%, respectively. • When controlling for confounding variables, ccLS is an independent risk factor for identifying clear cell renal cell carcinoma. • Utilization of the ccLS can help guide clinical care, including the decision for renal mass biopsy, reducing the morbidity and risk to patients.