Automated Deep Learning-Based Classification of Wilms Tumor Histopathology

SIMPLE SUMMARY: Wilms tumor (WT) is the most frequent pediatric tumor in children and shows highly variable histology, leading to variation in classification. Artificial intelligence-based automatic recognition holds the promise that this may be done in a more consistent way than human observers can. We have therefore studied digital microscopic slides, stained with standard hematoxylin and eosin, of 72 WT patients and used a deep learning (DL) system for the recognition of 15 different normal and tumor components. We show that such DL system can do this task with high accuracy, as exemplified by a Dice score of 0.85 for the 15 components. This approach may allow future automated WT classification. ABSTRACT: (1) Background: Histopathological assessment of Wilms tumors (WT) is crucial for risk group classification to guide postoperative stratification in chemotherapy pre-treated WT cases. However, due to the heterogeneous nature of the tumor, significant interobserver variation between pathologists in WT diagnosis has been observed, potentially leading to misclassification and suboptimal treatment. We investigated whether artificial intelligence (AI) can contribute to accurate and reproducible histopathological assessment of WT through recognition of individual histopathological tumor components. (2) Methods: We assessed the performance of a deep learning-based AI system in quantifying WT components in hematoxylin and eosin-stained slides by calculating the Sørensen–Dice coefficient for fifteen predefined renal tissue components, including six tumor-related components. We trained the AI system using multiclass annotations from 72 whole-slide images of patients diagnosed with WT. (3) Results: The overall Dice coefficient for all fifteen tissue components was 0.85 and for the six tumor-related components was 0.79. Tumor segmentation worked best to reliably identify necrosis (Dice coefficient 0.98) and blastema (Dice coefficient 0.82). (4) Conclusions: Accurate histopathological classification of WT may be feasible using a digital pathology-based AI system in a national cohort of WT patients.