Gondim, Dibson

Background: The rapid adoption of digital pathology and artificial intelligence (AI) in oncology creates multiple opportunities for precision diagnostics but also creates an urgent need for evidence-based standards to ensure safe and effective implementation. Goal: This article, developed by the Digital Pathology Association, presents recommendations for digital pathology as well as the validation and clinical utility of AI-enabled digital pathology tools in clinical practice. This guidance addresses analytical and clinical validation, algorithm reliability, and criteria for establishing clinical utility attributed to test use. Key recommendations emphasize separate validation of scanning processes and AI algorithms, concordance studies to support interscanner generalizability, rigorous assessment of accuracy and reliability in real-world settings, and clear description of algorithmic use limitations. These recommendations further provide frameworks for when AI may replace or augment existing diagnostic approaches, such as biomarker scoring, cancer diagnosis, and prognostic risk assessment. Conclusions: By considering payer, regulatory, and clinical perspectives, the recommendations promote transparency, trust, and reproducibility in digital pathology while encouraging value-based care delivery. We support responsible innovation in computational pathology, ensuring that AI applications achieve not only technical performance goals but also deliver measurable clinical benefit to patients.

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.

Transcription factor E3-rearranged renal cell carcinoma (TFE3-RCC) has heterogenous morphologic and immunohistochemical (IHC) features. 131 pathologists with genitourinary expertise were invited in an online survey containing 23 questions assessing their experience on TFE3-RCC diagnostic work-up. Fifty (38%) participants completed the survey. 46 of 50 participants reported multiple patterns, most commonly papillary pattern (almost always 9/46, 19.5%; frequently 29/46, 63%). Large epithelioid cells with abundant cytoplasm were the most encountered cytologic feature, with either clear (almost always 10/50, 20%; frequently 34/50, 68%) or eosinophilic (almost always 4/49, 8%; frequently 28/49, 57%) cytology. Strong (3+) or diffuse (>75% of tumour cells) nuclear TFE3 IHC expression was considered diagnostic by 13/46 (28%) and 12/47 (26%) participants, respectively. Main TFE3 IHC issues were the low specificity (16/42, 38%), unreliable staining performance (15/42, 36%) and background staining (12/42, 29%). Most preferred IHC assays other than TFE3, cathepsin K and pancytokeratin were melan A (44/50, 88%), HMB45 (43/50, 86%), carbonic anhydrase IX (41/50, 82%) and CK7 (32/50, 64%). Cut-off for positive TFE3 fluorescent in situ hybridisation (FISH) was preferably 10% (9/50, 18%), although significant variation in cut-off values was present. 23/48 (48%) participants required TFE3 FISH testing to confirm TFE3-RCC regardless of the histomorphologic and IHC assessment. 28/50 (56%) participants would request additional molecular studies other than FISH assay in selected cases, whereas 3/50 participants use additional molecular cases in all cases when TFE3-RCC is in the differential. Optimal diagnostic approach on TFE3-RCC is impacted by IHC and/or FISH assay preferences as well as their conflicting interpretation methods.