Development and evaluation of deep learning–based segmentation of histologic structures in the kidney cortex with multiple histologic stains

TLDR

The application of deep learning to automatically segment histologic primitives from whole‑slide images can enable new protocols for kidney biopsy assessment. The study developed and validated deep‑learning networks to segment kidney histologic structures in biopsies and nephrectomies. The authors trained 20 deep‑learning models on 125 Minimal Change Disease biopsies and 459 whole‑slide images stained with H&E, PAS, Silver, and Trichrome, using 30,048 manual annotations from five nephropathologists and optimizing magnification for each structure and stain. PAS‑stained images achieved the highest agreement with pathologists (F‑scores 0.81–0.94), with optimal magnifications of 5× for glomerular structures, 10× for tubules and arteries, and 40× for peritubular capillaries; Silver staining performed worst, and the study is the largest to date, with all data and a tutorial publicly released.

Abstract

The application of deep learning for automated segmentation (delineation of boundaries) of histologic primitives (structures) from whole slide images can facilitate the establishment of novel protocols for kidney biopsy assessment. Here, we developed and validated deep learning networks for the segmentation of histologic structures on kidney biopsies and nephrectomies. For development, we examined 125 biopsies for Minimal Change Disease collected across 29 NEPTUNE enrolling centers along with 459 whole slide images stained with Hematoxylin & Eosin (125), Periodic Acid Schiff (125), Silver (102), and Trichrome (107) divided into training, validation and testing sets (ratio 6:1:3). Histologic structures were manually segmented (30048 total annotations) by five nephropathologists. Twenty deep learning models were trained with optimal digital magnification across the structures and stains. Periodic Acid Schiff-stained whole slide images yielded the best concordance between pathologists and deep learning segmentation across all structures (F-scores: 0.93 for glomerular tufts, 0.94 for glomerular tuft plus Bowman's capsule, 0.91 for proximal tubules, 0.93 for distal tubular segments, 0.81 for peritubular capillaries, and 0.85 for arteries and afferent arterioles). Optimal digital magnifications were 5X for glomerular tuft/tuft plus Bowman's capsule, 10X for proximal/distal tubule, arteries and afferent arterioles, and 40X for peritubular capillaries. Silver stained whole slide images yielded the worst deep learning performance. Thus, this largest study to date adapted deep learning for the segmentation of kidney histologic structures across multiple stains and pathology laboratories. All data used for training and testing and a detailed online tutorial will be publicly available.