A Rare Benign Tumor in a 14-Year-Old Girl

Renal Oncocytoma: A Systematic Review of Its Metastatic Features

Oncocytomas are referred to as benign kidney neoplasms. They primarily affect adults, with patients over 70 years old being the most affected. Renal oncocytomas (ROs) are frequently detected by excision, biopsy, or scan. Hematuria, flank pain, and a palpable mass are the traditional trio of symptoms. Oncocytomas appear as well-circumscribed, tan or mahogany-coloured masses with a central scar that is stellate. Histological features include well-circumscribed lesions, bland cytology, eosinophilic cytoplasm, regular nuclei with prominent central nucleoli, and nested architecture. ROs are rarely linked to an aggressive clinical course and have an excellent prognosis. There is proof that the disease can spread to the liver and bones. Some literature has also reported oncocytoma metastases to the lung and liver. This systematic review of the literature examines and evaluates the malignant potential of oncocytoma. The purpose of the study was to determine whether ROs can be diagnosed as a benign condition or if malignancy needs to be considered and investigated. Seventeen studies were analysed which had a total of 412 ROs. Four patients (one percent) died as a result of their illness. There was evidence of disease progression in every patient who passed away from their illness. Six patients (1.5%) experienced disease progression in total. Three hundred and seventeen patients (80%) underwent radical nephrectomy, while 81 patients (20%) underwent partial nephrectomy. Liver, bone, lung, lymphadenopathy, and local recurrence were among the metastasis sites. Perinephric fat invasion, renal sinus fat invasion, renal capsular invasion, and vascular invasion are characteristics of metastatic behavior that have been found. Despite this, the small number of patients who experienced disease progression and/or death as a result of ROs implies that aggressive malignant behavior is not always correlated with the presence of metastatic features or disease. Oncocytomas should be viewed as having a low potential for malignancy rather than as benign. Individuals who exhibit aggressive characteristics, such as vascular invasion and/or perinephric fat invasion, have an atypically good prognosis. Despite advancements in imaging and immunochemical techniques, it is indisputable that ROs, which were first classified as renal tumours in 1976, continue to pose a diagnostic challenge for multidisciplinary teams. There is considerable variation in practice across the globe due to difficulties in confirming ROs, especially when it comes to metastatic disease. There is even more variation in the management of follow-up care that follows. This will remain the MDT's current state until randomised controlled trials, long-term results, and a better comprehension of the behavior of this tumour are obtained.

Convolutional neural networks for the differentiation between benign and malignant renal tumors with a multicenter international computed tomography dataset

OBJECTIVES

To use convolutional neural networks (CNNs) for the differentiation between benign and malignant renal tumors using contrast-enhanced CT images of a multi-institutional, multi-vendor, and multicenter CT dataset.

METHODS

A total of 264 histologically confirmed renal tumors were included, from US and Swedish centers. Images were augmented and divided randomly 70%:30% for algorithm training and testing. Three CNNs (InceptionV3, Inception-ResNetV2, VGG-16) were pretrained with transfer learning and fine-tuned with our dataset to distinguish between malignant and benign tumors. The ensemble consensus decision of the three networks was also recorded. Performance of each network was assessed with receiver operating characteristics (ROC) curves and their area under the curve (AUC-ROC). Saliency maps were created to demonstrate the attention of the highest performing CNN.

RESULTS

Inception-ResNetV2 achieved the highest AUC of 0.918 (95% CI 0.873-0.963), whereas VGG-16 achieved an AUC of 0.813 (95% CI 0.752-0.874). InceptionV3 and ensemble achieved the same performance with an AUC of 0.894 (95% CI 0.844-0.943). Saliency maps indicated that Inception-ResNetV2 decisions are based on the characteristics of the tumor while in most tumors considering the characteristics of the interface between the tumor and the surrounding renal parenchyma.

CONCLUSION

Deep learning based on a diverse multicenter international dataset can enable accurate differentiation between benign and malignant renal tumors.

CRITICAL RELEVANCE STATEMENT

Convolutional neural networks trained on a diverse CT dataset can accurately differentiate between benign and malignant renal tumors.

KEY POINTS

• Differentiation between benign and malignant tumors based on CT is extremely challenging. • Inception-ResNetV2 trained on a diverse dataset achieved excellent differentiation between tumor types. • Deep learning can be used to distinguish between benign and malignant renal tumors.