Computational Characterization of Lymphocyte Topology on Whole Slide Images of Glomerular Diseases.

BACKGROUND: The distribution of inflammation in the kidney and its clinical relevance is understudied. This study aims to computationally quantify lymphocyte topology and test its prediction of disease progression. METHODS: N=333 NEPTUNE/CureGN participants (N=155 focal segmental glomerulosclerosis, N=178 minimal change disease) with available clinical/demographic data and 1 Hematoxylin & Eosin-stained whole slide image were included. Cortex and lymphocytes were automatically segmented. A novel graph-based clustering algorithm was applied to identify dense versus sparse lymphocytic habitats, from which 26 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 ElasticNet-regularized Cox proportional hazards models. Clinical and demographic characteristics and percent of interstitial fibrosis and inflammation 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. RESULTS: Unadjusted analysis: 17 features (65%) retained significance after adjustment for standard clinico-demographic variables, Number of K-core in sparse habitat maintained significance (HR=1.29, 95% CI: 1.04-1.61) even after adjustment for lymphocyte density, and Average Degree in dense habitat had borderline significance (HR=1.25, 95% CI: 1.00-1.57) after adjustment for interstitial fibrosis. Multivariable models (clinical/demographic + graph features) achieved validation concordance index of 0.78±0.15 in the CureGN external validation and 0.77±0.06 in the combined internal validation dataset. Time-dependent discrimination showed consistent performance at 3- (AUC: 0.78 vs. 0.76) and 5-year timepoints (AUC: 0.74 vs. 0.76) across validation strategies. Sparse habitat clustering patterns (Maximum of K-core × Number of K-core in sparse habitat: 88% selection frequency) and dense habitat connectivity (Average Degree in dense habitat: 47% selection frequency) were consistently identified as robust predictors alongside clinical variables. CONCLUSIONS: The topological characterization of lymphocytic inflammation identified immune habitats, capturing the complexity of patterns of inflammation.

Duke Scholars

Author Laura Barisoni Pathology