ComPRePS : Unlocking Scalable AI Analysis for Computational Renal Pathology
Anindya S. Paul, Luis A. Rodrigues, Suhas Katari Chaluva Kumar, David Manthey, Samuel P. Border, Clara Pardinhas, Carolina Pimenta, Vitor Sousa, Arnaldo Figueiredo, Rui Alves, Briana A. Santo, Will Dunklin, Sumanth Devarasetty, Haitham Abdelazim, Agnes B. Fogo, Avi Z. Rosenberg, Oleksandr Moskalenko, Pinaki Sarder, Pinaki Sarder · bioRxiv (Cold Spring Harbor Laboratory) · 2024
Abstract Digital pathology using whole slide imaging (WSI) and artificial intelligence (AI) has the potential to transform diagnostic workflows, but adoption remains limited by technical complexity and scalability. We developed the Computational Renal Pathology Suite (ComPRePS), a scalable cloud-based platform that automates WSI ingestion, compartmental segmentation, feature extraction, and AI-assisted interpretation through an integrated high-performance architecture. ComPRePS was evaluated in two use cases. First, using 213 procurement biopsies, we compared conventional assessments with automated AI analyses and a hybrid AI-assisted expert workflow. ComPRePS AI-assisted methods achieved higher precision and significantly improved interobserver agreement for key lesions, including global glomerulosclerosis, interstitial fibrosis and tubular atrophy, and arterial intimal thickening. Second, ComPRePS enabled high-throughput quantitative profiling of glomerular and tubular features across minimal change disease, diabetic nephropathy, and amyloid nephropathy revealing disease-specific phenotypic patterns inaccessible to manual evaluation. Overall, ComPRePS improves reproducibility, interpretability, and objectivity in renal pathology, bridging computation with clinical practice.