Siegmund, Stephanie

Aims Testicular sex cord‐stromal tumours (TSCSTs) are relatively rare, accounting for ~5% of all testicular neoplasms. They were historically classified into Leydig cell tumour, Sertoli cell tumour, granulosa cell tumour, and unclassified sex cord‐stromal tumour. More recently, classification was expanded to incorporate additional histologic types, including some associated with inherited cancer predisposition syndromes. However, the classification of TSCSTs still relies entirely on morphology, with some tumour types being defined based on their resemblance to ovarian counterparts. In recent years, molecular studies have identified drivers and genomic alterations associated with aggressive behaviour and progression; however, these findings have not yet impacted classification and management. Methods and results Under sponsorship of the International Society of Urological Pathology (ISUP) and the Genitourinary Pathology Society (GUPS), a group of genitourinary pathologists was assembled in 2023 with the aim of assessing how to use these new data to improve the classification and management of TSCSTs. Conclusions This paper summarizes the recommendations derived from the consensus activities and the first meeting of the te sticular s ex cord‐ s tromal t umour (TESST) group (held at Johns Hopkins Hospital, Baltimore, USA, 3/23/2024).

Context.— Distinguishing between renal oncocytic tumors, such as renal oncocytoma (RO), and a subset of tumors with overlapping characteristics, including the recently identified low-grade oncocytic tumor (LOT), can present a diagnostic challenge for pathologists owing to shared histopathologic features. Objective.— To develop an automatic computational classifier for stratifying whole slide images of biopsy and resection specimens into 2 distinct groups: RO and LOT. Design.— A total of 269 whole slide images from 125 cases across 6 institutions were collected. A weakly supervised attention-based multiple-instance–learning deep learning (DL) model was trained and initially evaluated through 5-fold cross validation with case-level stratification, followed by validation using an independent holdout data set. Quantitative performance evaluation was based on accuracy and the area under the receiver operating characteristic curve (AUC). Results.— The developed model data set yielded generalizable performance, with a 5-fold average testing accuracy of 84% (AUC = 0.78), and a closely aligning accuracy of 83% (AUC = 0.92) on the independent holdout data set. Conclusions.— The proposed artificial intelligence approach contributes toward a comprehensive solution for addressing commonly encountered renal oncocytic neoplasms, encompassing well-established entities like RO along with the challenging “gray zone” LOT, thereby proving applicable in clinical practice.