Issues and challenges associated with classifying neoplasms in percutaneous needle biopsies of incidentally found small renal masses

Artificial Intelligence in Renal Cell Carcinoma Histopathology: Current Applications and Future Perspectives

Renal cell carcinoma (RCC) is characterized by its diverse histopathological features, which pose possible challenges to accurate diagnosis and prognosis. A comprehensive literature review was conducted to explore recent advancements in the field of artificial intelligence (AI) in RCC pathology. The aim of this paper is to assess whether these advancements hold promise in improving the precision, efficiency, and objectivity of histopathological analysis for RCC, while also reducing costs and interobserver variability and potentially alleviating the labor and time burden experienced by pathologists. The reviewed AI-powered approaches demonstrate effective identification and classification abilities regarding several histopathological features associated with RCC, facilitating accurate diagnosis, grading, and prognosis prediction and enabling precise and reliable assessments. Nevertheless, implementing AI in renal cell carcinoma generates challenges concerning standardization, generalizability, benchmarking performance, and integration of data into clinical workflows. Developing methodologies that enable pathologists to interpret AI decisions accurately is imperative. Moreover, establishing more robust and standardized validation workflows is crucial to instill confidence in AI-powered systems' outcomes. These efforts are vital for advancing current state-of-the-art practices and enhancing patient care in the future.

[Dignity of Small Renal Masses: Implications for Diagnostics and Therapy]

Dignity of Small Renal Masses: Implications for Diagnostics and Therapy Abstract. The ubiquitous availability of radiological imaging has increased the diagnosis of renal incidentalomas with a diameter ≤4 cm. If malignancy is suspected, these are often treated surgically without prior biopsy. However, several studies demonstrate a relevant proportion of benign tumors, equating to a degree of overtreatment. There are no Swiss data available. Renal tumors resected in our center between 2006 and 2014 (n = 404) were retrospectively examined for size on cross-sectional imaging and their respective histology, identifying 221 (54.7 %) small renal masses with a diameter ≤4 cm. Of these, 62 (28 %) were benign and three (1.4 %) were of unclear or low malignant potential. Among the remaining 156 malignancies, 116 (74.4 %) were classified as prognostically favorable, allowing for active surveillance, if the patient's clinical context allows.

Solid renal masses in adults

With the ever increasing trend of using cross-section imaging in today's era, incidental detection of small solid renal masses has dramatically multiplied. Coincidentally, the number of asymptomatic benign lesions being detected has also increased. The role of radiologists is not only to identify these lesions, but also go a one step further and accurately characterize various renal masses. Earlier detection of small renal cell carcinomas means identifying at the initial stage which has an impact on prognosis, patient management and healthcare costs. In this review article we share our experience with the typical and atypical solid renal masses encountered in adults in routine daily practice.

Development and Validation of a Deep-learning Model to Assist With Renal Cell Carcinoma Histopathologic Interpretation

OBJECTIVE

To develop and test the ability of a convolutional neural network (CNN) to accurately identify the presence of renal cell carcinoma (RCC) on histopathology specimens, as well as differentiate RCC histologic subtype and grade.

MATERIALS AND METHODS

Digital hematoxylin and eosin stained biopsy images were downloaded from The Cancer Genome Atlas. A CNN model was trained on 100 um2 samples of either normal (3000 samples) or RCC (12,168 samples) tissue samples from 42 patients. RCC specimens included clear cell, chromophobe, and papillary histiotypes, as well as tissue of Fuhrman grades 1 through 4. Model testing was performed on an additional held-out cohort of benign and RCC specimens. Model performance was assessed on the basis of diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

The CNN model achieved an overall accuracy of 99.1% in the testing cohort for distinguishing normal parenchyma from RCC (sensitivity 100%, specificity 97.1%). Accuracy for distinguishing between clear cell, papillary, and chromophobehistiotypes was 97.5%. Accuracy for predicting Fuhrman grade was 98.4%.

CONCLUSION

CNNs are able to rapidly and accurately identify the presence of RCC, distinguish RCC histologic subtypes, and identify tumor grade by analyzing histopathology specimens.

Assessing Genomic Copy Number Alterations as Best Practice for Renal Cell Neoplasia: An Evidence-Based Review from the Cancer Genomics Consortium Workgroup

Renal cell neoplasia are heterogeneous with diverse histology, genetic alterations, and clinical behavior that are diagnosed mostly on morphologic features. The Renal Cell Neoplasia Workgroup of the Cancer Genomics Consortium systematically evaluated peer-reviewed literature on genomic studies of renal cell carcinoma (RCC), including clear cell RCC, papillary RCC, chromophobe RCC, and the translocation RCC involving TFE3, TFEB and MITF rearrangements, as well as benign oncocytoma, which together comprise about 95% of all renal cell neoplasia. The Workgroup curated recurrent copy number alterations (CNAs), copy-neutral loss-of-heterozygosity (cnLOH), rearrangements, and mutations, found in each subtype and assigned clinical relevance according to established criteria. In clear cell RCC, loss of 3p has a disease-initiating role and most likely also in progression with mutations detected in VHL and other genes mapped to this arm, and loss of 9p and/or 14q has well-substantiated prognostic utility. Gain of chromosomes 7 and 17 are hallmark CNAs of papillary RCC, but patterns of other CNAs as detected by chromosomal microarray analysis (CMA) afford sub-classification into Type 1 and 2 with prognostic value, and for further sub-stratification of Type 2. Inherent chromosome loss in chromophobe RCC as detected by CMA is useful for distinguishing the eosinophilic variant from benign oncocytoma which in contrast exhibits few CNAs or rearranged CCND1, but share mitochondrial DNA mutations. In morphologically atypical RCCs, rearrangement of TFE3 and TFEB should be considered in the differential diagnosis, portending an aggressive RCC subtype. Overall, this evidence-based review provides a validated role for assessment of CNAs in renal cell neoplasia in the clinical setting to assist in renal cell neoplasm diagnosis and sub-classification within subtypes that is integral to the management of patients, from small incidentally found renal masses to larger surgically resected specimens, and simultaneously identify the presence of key alterations portending outcome in malignant RCC subtypes.

Dataset for the reporting of renal biopsy for tumour: recommendations from the International Collaboration on Cancer Reporting (ICCR)

The International Collaboration on Cancer Reporting (ICCR) has developed a suite of detailed datasets for international implementation. These datasets are based on the reporting protocols developed by the Royal College of Pathologists (UK), The Royal College of Pathologists of Australasia and the College of American Pathologists, with modifications undertaken by international expert groups appointed according to ICCR protocols. The dataset for the reporting of renal biopsy for tumour is designed to provide a structured reporting template containing minimum data recording key elements suitable for international use. In formulating the dataset, the ICCR panel incorporated recommendations from the 2012 Vancouver Consensus Conference of the International Society of Urological Pathology (ISUP) and the 2016 edition of the WHO Bluebook on tumours of the urinary and male genital systems. Reporting elements were divided into Required (Core) and Recommended (Non-core) components of the report. Required elements are as follows: specimen laterality, histological tumour type, WHO/ISUP histological tumour grade, sarcomatoid morphology, rhabdoid morphology, necrosis, lymphovascular invasion and coexisting pathology in non-neoplastic kidney. Recommended reporting elements are as follows: operative procedure, tumour site(s), histological tumour subtype and details of ancillary studies. In particular, it is noted that fluorescence in situ hybridisation studies may assist in diagnosing translocation renal cell carcinoma (RCC) and in distinguishing oncocytoma and eosinophilic chromophobe RCC. It is anticipated that the implementation of this dataset into routine clinical practice will facilitate uniformity of pathology reporting worldwide. This, in turn, should have a positive impact on patient treatment and the quality of demographic information held by cancer registries.

WHO/ISUP classification, grading and pathological staging of renal cell carcinoma: standards and controversies

PURPOSE

Pathological parameters assessed on biopsies and resection specimens have a pivotal role in the diagnosis, prognosis and management of patients with renal cell carcinoma (RCC).

METHODS

A non-systematic literature search was performed, updated to January 2018, to identify key standards and controversies in the pathological classification, grading and staging of RCC.

RESULTS

Although most RCCs exhibit characteristic morphology that enables easy categorisation, RCCs show considerable morphological heterogeneity and it is not uncommon for there to be difficulty in assigning a tumour type, especially with rarer tumour subtypes. The differentiation between benign and malignant oncocytic tumours remains a particular challenge. The development of additional immunohistochemical and molecular tests is needed to facilitate tumour typing, because of the prognostic and therapeutic implications, and to enable more reliable identification of poorly differentiated metastatic tumours as being of renal origin. Any new tests need to be applicable to small biopsy samples, to overcome the heterogeneity of renal tumours. There is also a need to facilitate identification of tumour types that have genetic implications, to allow referral and management at specialist centres. Digital pathology has a potential role in such referral practice.

CONCLUSION

Much has been done to standardise pathological assessment of renal cell carcinomas in recent years, but there still remain areas of difficulty in classification and grading of these heterogeneous tumours.

Safety, reliability and accuracy of small renal tumour biopsies: results from a multi-institution registry

OBJECTIVE

To validate, in a multi-institution review, the safety, accuracy and reliability of renal tumour biopsy (RTB) and its role in decreasing unnecessary treatment.

MATERIALS AND METHODS

We conducted a multi-institution retrospective study of patients who underwent RTB to characterize a small renal mass (SRM) between 2011 and May 2015. Patients were identified using the prospectively maintained Canadian Kidney Cancer information system. Diagnostic and concordance rates were presented using proportions, whereas factors associated with a diagnostic RTB were identified using a logistic regression model.

RESULTS

Of the 373 biopsied SRMs, the initial biopsy was diagnostic in 87% of cases. Of the 47 non-diagnostic biopsies, 15 had a repeat biopsy of which, 80% were diagnostic. When both were combined, therefore, a diagnosis was obtained in 91% of SRMs. Of these, 18% were benign. Size was the only factor found to be associated with achieving a diagnostic biopsy. RTB histology and nuclear grade (high or low) were found to be highly concordant with surgical pathology (86 and 81%, respectively). Of the discordant tumours (n = 16), all were upgraded from low to high grade on surgical pathology. Adverse events were rare (<1% of cases).

CONCLUSION

The present multi-institution study confirms that RTB of SRMs is safe, accurate and reliable across institutions, while decreasing unnecessary treatment. Given our findings, RTBs may be a helpful tool with which to triage SRMs and guide appropriate management.

Clear cell renal cell tumors: Not all that is "clear" is cancer

Continued improvement of our understanding of the clinical, histologic, and genetic features of renal cell tumors has progressively evolved renal tumor classification, revealing an expanding array of distinct tumor types with different implications for prognosis, patient counseling, and treatment. Although clear cell renal cell carcinoma is unequivocally the most common adult renal tumor, there is growing evidence that some "clear cell" renal neoplasms, such as exemplified by multilocular cystic clear cell renal neoplasm of low malignant potential (formerly multilocular cystic renal cell carcinoma), do not have the same potential for insidious progression and metastasis, warranting reclassification as low malignant potential tumors or benign neoplasms. Still other novel tumor types such as clear cell papillary renal cell carcinoma have been more recently recognized, which similarly have shown a conspicuous absence of aggressive behavior to date, suggesting that these too may be recategorized as noncancerous or may be premalignant neoplasms. This importance for prognosis is increasingly significant in the modern era, in which renal masses are increasingly found incidentally by imaging techniques at a small tumor size, raising consideration for less aggressive management options guided by renal mass biopsy diagnosis, including imaging surveillance, tumor ablation, or partial nephrectomy.

Percutaneous Kidney Biopsy for a Small Renal Mass: A Critical Appraisal of Results

PURPOSE

We report the diagnostic accuracy of renal mass biopsy for a small renal mass (4 cm or less) and identify predictors of successful renal mass biopsy in a contemporary cohort of patients from 2 large tertiary referral centers.

MATERIALS AND METHODS

A total of 442 biopsies of renal tumors 4 cm or less at 2 tertiary centers between 2008 and 2015 were included in study. Biopsy outcomes (malignant, benign or nondiagnostic) and concordance rates between renal mass biopsy and final surgical pathology were determined. Univariate and multivariate logistic regression analyses were performed to identify factors indicative of nondiagnostic biopsy.

RESULTS

The initial biopsy was diagnostic in 393 cases (88.9%) and nondiagnostic in 49 (11.1%). Of diagnostic biopsies 76% revealed renal cell carcinoma and 24% were benign. Renal cell carcinoma histological subtyping and grading was possible in 90.2% and 31.3% of cases, respectively. A second biopsy was performed in 11 of the 49 nondiagnostic cases and a diagnosis was possible in 100%, including renal cell carcinoma in 10 and oncocytoma in 1. Small tumor size, cystic nature of tumors and biopsy during the initial years of the study were independent predictors of nondiagnostic biopsy. The rates of accuracy in identifying malignancies, histiotyping and 2-tier grading between renal mass biopsy and surgical pathology were 97.1%, 95.1% and 68.8%, respectively.

CONCLUSIONS

Renal mass biopsy for a small renal mass can be performed accurately. Nondiagnostic renal mass biopsy was common for smaller masses and cystic masses, and during the initial years of the study. A second biopsy should be considered in nondiagnostic biopsy cases.

Active Surveillance for Renal Neoplasms with Oncocytic Features is Safe

PURPOSE

Oncocytomas are benign tumors often diagnosed incidentally on imaging. Small case series have suggested that the growth kinetics of oncocytomas are similar to those of malignant renal tumors. Biopsy material may be insufficient to exclude a diagnosis of chromophobe renal cell carcinoma. We evaluated and compared the growth rates of oncocytoma and chromophobe renal cell carcinoma to improve our understanding of their natural history.

MATERIALS AND METHODS

This was a single center, retrospective study of patients diagnosed with lesions suggestive of oncocytoma or chromophobe renal cell carcinoma between 2003 and 2014. The growth rates were estimated using a mixed effect linear model. Patient and lesion characteristics were tested using a similar model for association with growth rate.

RESULTS

Of the 95 lesions (oncocytoma 81, chromophobe renal cell carcinoma 14) included in the analysis 98% were diagnosed on biopsy. The annual growth rate was 0.14 cm and 0.38 cm for oncocytoma (median followup 34 months) and chromophobe renal cell carcinoma (median followup 25 months), respectively (p=0.5). Baseline lesion size was significantly associated with growth (p <0.001). The majority of oncocytomas (74%) and chromophobe renal cell carcinomas (67%) followed up to the 3-year mark had grown. Of these, 8 underwent surgery (6 in the chromophobe renal cell carcinoma group). The initial diagnosis was confirmed in all. Overall 5 patients died, all of nonrenal related causes.

CONCLUSIONS

Although the majority of oncocytic renal neoplasms will grow with time, surveillance appears to remain safe. Patients opting for this strategy should be made aware that a diagnosis of oncocytoma following biopsy is associated with some degree of uncertainty due to the difficulty of differentiating them from other oncocytic renal neoplasms.