Computational Characterization of Lymphocyte Topology on Whole Slide Images of Glomerular Diseases
Year: 2025
Type: article
Abstract: The complexity of distribution of inflammatory cells in the kidney is not well captured by conventional semiquantitative visual assessment. This study aims to computationally quantify the topology of lymphocytic inflammation and tested its clinical relevance. N=333 NEPTUNE/CureGN participants (N=155 focal segmental glomerulosclerosis (FSGS) and N=178 Minimal Change Disease (MCD) with available clinical/demographic data and 1 Hematoxylin & Eosin-stained whole slide image (WSI), were included. Deep learning models were applied to segment cortex and lymphocytes. Graph modeling, where nodes were defined as lymphocytes and edges as the spatial connections between cortical lymphocytes, were applied to all WSIs. We then developed a novel graph-based habitat clustering algorithm to identify dense vs. sparse lymphocytic habitats. From each habitat, 26 high-throughput quantitative pathomic features were extracted to capture cell density, connectivity, clustering, and centrality. The association of these pathomic features with disease progression (40% eGFR decline or kidney replacement therapy) was assessed using LASSO-regularized Cox proportional hazards models. Clinical and demographic characteristics were added as potential confounders. Kaplan-Meier survival analysis with log-rank test was used to evaluate risk stratification. Two validation strategies were applied: (i) training on NEPTUNE with external validation on CureGN data, and (ii) using an 80/20 data partition of the combined datasets for training and validation, respectively. Multivariable Cox models integrating clinical/demographic variables with graph features achieved validation concordance index of 0.736±0.072 in the CureGN external validation and 0.757±0.071 in the combined validation dataset. The average degree feature (overall connectivity) in dense habitat and k-core feature (clustering pattern strength) in sparse habitat revealed consistent association with clinical outcome. The topological characterization of lymphocytic inflammation identifies immune habits, capturing the complexity of pattern of inflammation beyond human vision. These pathomic/topology signatures represent potential digital biomarkers that can enhance our ability to prognosticate/predict clinical outcome in MCD/FSGS.
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funders: University of Miami, University of Pennsylvania, Ohio State University, Emory University, Northwestern University, Texas Children's Hospital, Wake Forest University, University of Minnesota, Washington University in St. Louis, Cleveland Clinic, University of Washington, Johns Hopkins University, University of Texas Southwestern Medical Center, University of Pittsburgh, University of South Carolina, Children's Mercy Hospital, Temple University, York University, Hospital for Sick Children, National Institutes of Health, University of North Carolina at Chapel Hill, Anschutz Medical Campus, University of Colorado, National Cancer Institute, National Institute of Allergy and Infectious Diseases, National Institute of Diabetes and Digestive and Kidney Diseases, U.S. National Library of Medicine, NIH Clinical Center, National Center for Advancing Translational Sciences
Awards: Computational Pathology of Proteinuric Diseases, Targeting the B Cell Response to Treat Antibody-Mediated Rejection, Computational tumor phenotyping to interrogate treatment resistance and immune dysregulation in head and neck cancer, G3602628895, Integrative Proteomics & Metabolomics for Pediatric Glomerula Disease Biomarkers, Advancing Clinical Research in Primary Glomerular Diseases (UM1), G6503697038, Primary Outcomes in Glomerulonephritis Study (PROGRESS), GDPrime, Nephrotic Syndrome Rare Disease Clinical Research Network III, G8869320807, CUREGN 3.0 - Pediatric Nephrology Consortium - PCC, CureGN-3: UNCPCC, The Columbia PCC for CureGN: the Cure Glomerulonephropathy network, Data Management and Coordinating Center: Rare Diseases Clinical Research Network, CureGN, CureGN-Penn PCC, GDCN Clinical Center-Advancing Clinical Research in Primary Glomerular Diseases
OpenAlex ID: W4414939176