Journal Article Preprint Epublish
PubMed: 42465438 DOI: 10.64898/2026.07.07.736891
Scalable 3D cell-interaction analysis via supercell graphs for prostate cancer risk stratification.
bioRxiv
Authors: Yujie Zhao, Sarah S L Chow, Renao Yan, David Brenes, Robert Serafin, Cristina Almagro-Pérez, Andrew H Song, Priti Lal, Emily Chan, Michelle Downes, Elena Baraznenok, Jennifer Salguero Lopez, Anant Madabhush, Faisal Mahmood, Lawrence D True, Jonathan T C Liu
Abstract
Cellular interactions underlie fundamental biological processes but are not fully represented in conventional 2D histology images. While 3D pathology allows for more-accurate construction of cell-level graphs, machine-learning models are computationally unwieldy and prone to overfitting, especially when dealing with small cohorts. Here, we introduce SCALE3D , a S uper C ell graph A nalysis framework for L arg E 3D pathology datasets. In SCALE3D, spatially adjacent and morphologically similar cells are grouped into functional "supercells." Supercell subtypes are defined via morphology-based clustering and 3D graphs connecting these supercells are used to model their interactions. Validation was performed with 76 radical prostatectomy specimens from patients with known 5-year biochemical recurrence (BCR) outcomes. SCALE3D-derived features achieve higher performance for BCR prediction than established 3D nuclear and glandular morphological features. Combining these complementary features further improves prediction performance. Compared to individual cell-level 3D graphs, SCALE3D maintains comparable prognostic performance with improved noise tolerance while reducing computational times by up to 1,000-fold.
MeSH
Cells, Neoplasms, Pathology, Prostate, Cell Communication, Prostatic Neoplasms