Litcius/Paper detail

Predicting prostate cancer grade reclassification on active surveillance using a deep learning–based grading algorithm

Chien‐Kuang Cornelia Ding, Zhuo T. Su, Erik Erak, Lia De Paula Oliveira, Daniela C. Salles, Yuezhou Jing, Pranab Samanta, Saikiran Bonthu, Uttara Joshi, Chaith Kondragunta, Nitin Singhal, Angelo M. De Marzo, Bruce J. Trock, Christian P. Pavlovich, Claire M. de la Calle, Tamara L. Lotan

2024JNCI Journal of the National Cancer Institute12 citationsDOIOpen Access PDF

Abstract

Deep learning (DL)-based algorithms to determine prostate cancer (PCa) Grade Group (GG) on biopsy slides have not been validated by comparison to clinical outcomes. We used a DL-based algorithm, AIRAProstate, to regrade initial prostate biopsies in 2 independent PCa active surveillance (AS) cohorts. In a cohort initially diagnosed with GG1 PCa using only systematic biopsies (n = 138), upgrading of the initial biopsy to ≥GG2 by AIRAProstate was associated with rapid or extreme grade reclassification on AS (odds ratio = 3.3, P = .04), whereas upgrading of the initial biopsy by contemporary uropathologist reviews was not associated with this outcome. In a contemporary validation cohort that underwent prostate magnetic resonance imaging before initial biopsy (n = 169), upgrading of the initial biopsy (all contemporary GG1 by uropathologist grading) by AIRAProstate was associated with grade reclassification on AS (hazard ratio = 1.7, P = .03). These results demonstrate the utility of a DL-based grading algorithm in PCa risk stratification for AS.

Topics & Concepts

Prostate cancerGrading (engineering)BiopsyCohortMedicineAlgorithmProstate biopsyHazard ratioLogistic regressionMagnetic resonance imagingRadiologyInternal medicineOncologyCancerComputer scienceConfidence intervalEngineeringCivil engineeringProstate Cancer Diagnosis and TreatmentProstate Cancer Treatment and ResearchUrologic and reproductive health conditions