Active surveillance as the preferred management option for small renal masses

Role of AI and Radiomic Markers in Early Diagnosis of Renal Cancer and Clinical Outcome Prediction: A Brief Review

Globally, renal cancer (RC) is the 10th most common cancer among men and women. The new era of artificial intelligence (AI) and radiomics have allowed the development of AI-based computer-aided diagnostic/prediction (AI-based CAD/CAP) systems, which have shown promise for the diagnosis of RC (i.e., subtyping, grading, and staging) and prediction of clinical outcomes at an early stage. This will absolutely help reduce diagnosis time, enhance diagnostic abilities, reduce invasiveness, and provide guidance for appropriate management procedures to avoid the burden of unresponsive treatment plans. This survey mainly has three primary aims. The first aim is to highlight the most recent technical diagnostic studies developed in the last decade, with their findings and limitations, that have taken the advantages of AI and radiomic markers derived from either computed tomography (CT) or magnetic resonance (MR) images to develop AI-based CAD systems for accurate diagnosis of renal tumors at an early stage. The second aim is to highlight the few studies that have utilized AI and radiomic markers, with their findings and limitations, to predict patients' clinical outcome/treatment response, including possible recurrence after treatment, overall survival, and progression-free survival in patients with renal tumors. The promising findings of the aforementioned studies motivated us to highlight the optimal AI-based radiomic makers that are correlated with the diagnosis of renal tumors and prediction/assessment of patients' clinical outcomes. Finally, we conclude with a discussion and possible future avenues for improving diagnostic and treatment prediction performance.

A Comprehensive Computer-Assisted Diagnosis System for Early Assessment of Renal Cancer Tumors

Renal cell carcinoma (RCC) is the most common and a highly aggressive type of malignant renal tumor. In this manuscript, we aim to identify and integrate the optimal discriminating morphological, textural, and functional features that best describe the malignancy status of a given renal tumor. The integrated discriminating features may lead to the development of a novel comprehensive renal cancer computer-assisted diagnosis (RC-CAD) system with the ability to discriminate between benign and malignant renal tumors and specify the malignancy subtypes for optimal medical management. Informed consent was obtained from a total of 140 biopsy-proven patients to participate in the study (male = 72 and female = 68, age range = 15 to 87 years). There were 70 patients who had RCC (40 clear cell RCC (ccRCC), 30 nonclear cell RCC (nccRCC)), while the other 70 had benign angiomyolipoma tumors. Contrast-enhanced computed tomography (CE-CT) images were acquired, and renal tumors were segmented for all patients to allow the extraction of discriminating imaging features. The RC-CAD system incorporates the following major steps: (i) applying a new parametric spherical harmonic technique to estimate the morphological features, (ii) modeling a novel angular invariant gray-level co-occurrence matrix to estimate the textural features, and (iii) constructing wash-in/wash-out slopes to estimate the functional features by quantifying enhancement variations across different CE-CT phases. These features were subsequently combined and processed using a two-stage multilayer perceptron artificial neural network (MLP-ANN) classifier to classify the renal tumor as benign or malignant and identify the malignancy subtype as well. Using the combined features and a leave-one-subject-out cross-validation approach, the developed RC-CAD system achieved a sensitivity of 95.3%±2.0%, a specificity of 99.9%±0.4%, and Dice similarity coefficient of 0.98±0.01 in differentiating malignant from benign tumors, as well as an overall accuracy of 89.6%±5.0% in discriminating ccRCC from nccRCC. The diagnostic abilities of the developed RC-CAD system were further validated using a randomly stratified 10-fold cross-validation approach. The obtained results using the proposed MLP-ANN classification model outperformed other machine learning classifiers (e.g., support vector machine, random forests, relational functional gradient boosting, etc.). Hence, integrating morphological, textural, and functional features enhances the diagnostic performance, making the proposal a reliable noninvasive diagnostic tool for renal tumors.

A Comparison of Cryoablation with Heat-Based Thermal Ablation for Treatment of Clinical T1a Renal Cell Carcinoma: A National Cancer Database Study

PURPOSE

To compare the overall survival (OS) of patients receiving cryoablation versus heat-based thermal ablation for clinical T1a renal cell carcinoma (RCC) in a large national cohort.

MATERIALS AND METHODS

Patients with RCC from 2004 to 2014 who were treated with ablation were identified from the National Cancer Database. OS was estimated with the use of the Kaplan-Meier method and evaluated by means of log-rank test, univariate and multivariate Cox proportional hazard regression, and propensity score-matched analysis.

RESULTS

A total of 3,936 patients who received cryoablation and 2,322 who received heat-based thermal ablation met the inclusion criteria. The mean age was 67 ± 12 year, and the mean size of tumors was 25 ± 8 mm. The 3-, 5-, and 10-year survival rates were, respectively, 91%, 82%, and 62% for cryoablation and 89%, 81%, and 55% for heat-based thermal ablation. After propensity score matching, cryoablation was associated with longer OS compared with heat-based thermal ablation (median 11.3 vs 10.4 years; hazard ratio 1.175, 95% CI 1.03-1.341; P = .016). For patients with tumors ≤2 cm, propensity score-matched analyses demonstrated no significant difference between the 2 treatment groups (P = .772).

CONCLUSIONS

Overall, cryoablation may be associated with longer OS compared with heat-based thermal ablation in cT1a RCC. No significant difference in survival rates was observed between the 2 treatments for patients with tumor sizes ≤2 cm. Owing to the inherent limitations of this study, further study with details on technology, local outcome, and complications is needed.

A Decision-Support Tool for Renal Mass Classification

We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists.

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

OBJECTIVE

The purpose of this study was to assess the accuracy of a panel of texture features extracted from clinical CT in differentiating benign from malignant solid enhancing lipid-poor renal masses.

MATERIALS AND METHODS

In a retrospective case-control study of 174 patients with predominantly solid nonmacroscopic fat-containing enhancing renal masses, 129 cases of malignant renal cell carcinoma were found, including clear cell, papillary, and chromophobe subtypes. Benign renal masses-oncocytoma and lipid-poor angiomyolipoma-were found in 45 patients. Whole-lesion ROIs were manually segmented and coregistered from the standard-of-care multiphase contrast-enhanced CT (CECT) scans of these patients. Pathologic diagnosis of all tumors was obtained after surgical resection. CECT images of the renal masses were used as inputs to a CECT texture analysis panel comprising 31 texture metrics derived with six texture methods. Stepwise logistic regression analysis was used to select the best predictor among all candidate predictors from each of the texture methods, and their performance was quantified by AUC.

RESULTS

Among the texture predictors aiding renal mass subtyping were entropy, entropy of fast-Fourier transform magnitude, mean, uniformity, information measure of correlation 2, and sum of averages. These metrics had AUC values ranging from good (0.80) to excellent (0.98) across the various subtype comparisons. The overall CECT-based tumor texture model had an AUC of 0.87 (p < 0.05) for differentiating benign from malignant renal masses.

CONCLUSION

The CT texture statistical model studied was accurate for differentiating benign from malignant solid enhancing lipid-poor renal masses.

Image-guided minimally invasive treatment for small renal cell carcinoma

Surgical partial nephrectomy is still considered as the "gold standard" for the definitive management of small malignant renal masses, whereas treatment with image-guided percutaneous ablation is still mainly reserved for those patients who cannot undergo nephron-sparing surgical resection due to advanced age, underlying comorbidities or compromised renal function. Nonetheless, the recent evidence that underlines the long-term oncological equipoise of percutaneous ablation methods with surgical resection in combination with the reduced complication rate and cost supports the use of an image-guided minimally invasive approach as a first-line treatment. The purpose of this review is to offer an overview of the most widely used percutaneous renal ablation treatments (radiofrequency, microwave and cryoablation) with a focus on their main technical aspects and application techniques for curative ablation of small renal cell carcinoma (stage cT1a). The authors also provide a critical narrative of the relevant medical literature with an emphasis on outcomes of comparative effectiveness research, and appraise the percutaneous methods compared to surgery in the context of evidence-based practice and future research studies.

TEACHING POINTS

• RCC is a common cancer and is increasingly detected incidentally at early stages. • There is long-term oncological equipoise of percutaneous ablation compared to surgical resection. • Large-scale trials are required to produce Level 1a evidence.

Renal cancer

The diagnosis and management of renal cell carcinoma have changed remarkably rapidly. Although the incidence of renal cell carcinoma has been increasing, survival has improved substantially. As incidental diagnosis of small indolent cancers has become more frequent, active surveillance, robot-assisted nephron-sparing surgical techniques, and minimally invasive procedures, such as thermal ablation, have gained popularity. Despite progression in cancer control and survival, locally advanced disease and distant metastases are still diagnosed in a notable proportion of patients. An integrated management strategy that includes surgical debulking and systemic treatment with well established targeted biological drugs has improved the care of patients. Nevertheless, uncertainties, controversies, and research questions remain. Further advances are expected from translational and clinical studies.

Surgeon-specific factors affecting treatment decisions among Canadian urologists in the management of pT1a renal tumours

INTRODUCTION

The ubiquitous use of diagnostic imaging has resulted in an increased incidental detection of small renal masses (SRM). Patient- and tumour-related factors affect treatment decisions greatly; however, with multiple treatment options available, surgeon-specific characteristics and biases may also influence treatment recommendations. We determine the impact of surgeon-specific factors on treatment decisions in the management of SRM in Canada.

METHODS

An online survey study was conducted among Canadian urologists currently registered with the Canadian Urological Association. The questionnaire collected demographic information and recommended treatments for 6 SRM index cases involving theoretical patients of various ages (51-80 years) and comorbidities.

RESULTS

A total of 110 urologists responded (17% response rate) to the survey. Of these, 18% were over 65 years old and 45% were from academic centres. With increasing patient age and comorbidity, active surveillance and thermal ablative therapies were more the recommended treatment. Laparoscopic/robotic surgery was more commonly recommended by academic urologists and those under 65. Recommending surgery (radical nephrectomy or partial nephrectomy) for both elderly (about 80 years old) index patients correlated with surgeon age (surgeons over 65, p < 0.001), surgeons with no oncologic fellowship training (p = 0.021), surgeons with a non-academic practice (p = 0.003), surgeons with a personal history of cancer (p = 0.038) and surgeons with a family history of cancer death in the last 10 years (p = 0.022).

CONCLUSIONS

There are various factors that influence the management options offered to patients with SRMs. Our results suggest that surgeon age, personal history of cancer, practice-type and other surgeon-specific variables may affect treatments offered among urologists across Canada.

Usefulness of the ice-cream cone pattern in computed tomography for prediction of angiomyolipoma in patients with a small renal mass

Purpose

A morphologic contour method for assessing an exophytic renal mass as benign versus malignant on the basis of the shape of the interface with the renal parenchyma was recently developed. We investigated the usefulness of this morphologic contour method for predicting angiomyolipoma (AML) in patients who underwent partial nephrectomy for small renal masses (SRMs).

Materials and Methods

From January 2004 to March 2013, among 197 patients who underwent partial nephrectomy for suspicious renal cell carcinoma (RCC), the medical records of 153 patients with tumors (AML or RCC) ≤3 cm in diameter were retrospectively reviewed. Patient characteristics including age, gender, type of surgery, size and location of tumor, pathologic results, and specific findings of the imaging study ("ice-cream cone" shape) were compared between the AML and RCC groups.

Results

AML was diagnosed in 18 patients and RCC was diagnosed in 135 patients. Gender (p=0.001), tumor size (p=0.032), and presence of the ice-cream cone shape (p=0.001) showed statistically significant differences between the AML group and the RCC group. In the multivariate logistic regression analysis, female gender (odds ratio [OR], 5.20; 95% confidence interval [CI], 1.45 to 18.57; p=0.011), tumor size (OR, 0.34; 95% CI, 0.12 to 0.92; p=0.034), and presence of the ice-cream cone shape (OR, 18.12; 95% CI, 4.97 to 66.06; p=0.001) were predictors of AML.

Conclusions

This study confirmed a high incidence of AML in females. Also, the ice-cream cone shape and small tumor size were significant predictors of AML in SRMs. These finding could be beneficial for counseling patients with SRMs.

Active surveillance, radiofrequency ablation, or cryoablation for the nonsurgical management of a small renal mass: a cost-utility analysis

BACKGROUND

Patients with a cortical small (≤4 cm) renal mass often are not candidates for or choose not to undergo surgery. The optimal management strategy for such patients is unclear.

METHODS

A decision-analytic Markov model was developed from the perspective of a third party payer to compare the quality-adjusted life expectancy and lifetime costs for 67-year-old patients with a small renal mass undergoing premanagement decision biopsy, immediate percutaneous radiofrequency ablation or percutaneous cryoablation (without premanagement biopsy), or active surveillance with serial imaging and subsequent ablation if needed.

RESULTS

The dominant strategy (most effective and least costly) was active surveillance with subsequent cryoablation if needed. On a quality-adjusted and discounted basis, immediate cryoablation resulted in a similar life expectancy (3 days fewer) but cost $3,010 more. This result was sensitive to the relative rate of progression to metastatic disease. Strategies that employed radiofrequency ablation had decreased quality-adjusted life expectancies (82-87 days fewer than the dominant strategy) and higher costs ($3,231-$6,398 more).

CONCLUSIONS

Active surveillance with delayed percutaneous cryoablation, if needed, may be a safe and cost-effective alternative to immediate cryoablation. The uncertainty in the relative long-term rate of progression to metastatic disease in patients managed with active surveillance versus immediate cryoablation needs to be weighed against the higher cost of immediate cryoablation. A randomized trial is needed directly to evaluate the nonsurgical management of patients with a small renal mass, and could be limited to the most promising strategies identified in this analysis.