Image-based Detection of Mismatch Repair Deficiency in Prostate Cancer Using Transfer Learning

Abstract

Purpose/Background: Tumors with microsatellite instability high/mismatch repair-deficient (MSI-H/dMMR) exhibit distinct biological features and are associated with Lynch syndrome. Current approaches for detecting MSI-H/dMMR status rely on immunohistochemistry or molecular assays. Recent advances in digital pathology have enabled the extraction of clinically relevant molecular tumor features from routine hematoxylin and eosin (H&E)–stained diagnostic slides. Image-based deep learning approaches have the potential to screen for MSI-H/dMMR at scale in tumor types such as localized prostate cancer, in which MSI-H/dMMR is so rare that traditional testing is not routinely performed. Experimental Design: We developed and validated PathStage-MSI, a multi-stage transfer learning framework to predict MSI-H/dMMR status from H&E-stained slides. The model was trained and validated on 984 standard-of-care whole slide images (n = 906 patients) from three international clinical prostate cancer cohorts with matched H&E images and genomic data. To assess model generalizability and stability, we additionally evaluated PathStage-MSI in an independent metastatic prostate cancer cohort comprising 85 WSIs from 29 patients. Results: PathStage-MSI achieved the area under the receiver operating characteristic curve (AUROC) of 0.89 [0.79 - 0.96] and 0.91 [0.81 - 0.98] in two internal hold-out validation cohorts, 0.75 [0.57 - 0.88] and 0.81 [0.66 - 0.94] in two independent external validation cohorts. Conclusions: PathStage-MSI is a deep learning–based image analysis framework for detecting MSI-H/dMMR prostate cancer directly from routine histopathology. By enabling efficient pre-screening for this rare molecular subtype, it has the potential to improve patient identification for precision therapies and appropriate germline genetic testing.