Rapid slide-level assessment of glomerular yield using virtual staining of unstained renal biopsy sections

Renal biopsy remains the gold standard for the diagnosis of kidney diseases, and specimen adequacy is essential for reliable histopathological evaluation. However, confirmation of glomerular yield in routine pathology workflows often relies on histological sections after staining, which may delay feedback when deeper sectioning is required. In this study, we investigated whether virtual staining applied to unstained renal biopsy sections could enable early assessment of glomerular adequacy. Unstained sections prepared under different mounting conditions were virtually transformed into H&E and special stains. The visibility of glomerular structures and the reliability of glomerular assessment were evaluated across multiple scanners. Optimized preparation of unstained sections enabled stable virtual staining with preserved morphological features. Virtual special stains enhanced the visualization of glomerular basement membranes and mesangial regions, allowing reliable identification of glomeruli on unstained tissue sections. This approach demonstrated robustness across different scanning systems, outperforming direct assessment on raw unstained images. Virtual staining of unstained renal biopsy sections provides a rapid and reagent-free strategy for early slide-level assessment of glomerular yield. By enabling feedback at the sectioning stage before routine staining, this method may improve efficiency and quality control in routine renal pathology workflows.

Institutions

Publication Details

Journal
Diagnostic Pathology
Published
2026-05-19
DOI
https://doi.org/10.1186/s13000-026-01794-8
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Rapid slide-level assessment of glomerular yield using virtual staining of unstained renal biopsy sections

Diagnostic Pathology
AI in cancer detection
article

Rapid slide-level assessment of glomerular yield using virtual staining of unstained renal biopsy sections

article en

Abstract

Renal biopsy remains the gold standard for the diagnosis of kidney diseases, and specimen adequacy is essential for reliable histopathological evaluation. However, confirmation of glomerular yield in routine pathology workflows often relies on histological sections after staining, which may delay feedback when deeper sectioning is required. In this study, we investigated whether virtual staining applied to unstained renal biopsy sections could enable early assessment of glomerular adequacy. Unstained sections prepared under different mounting conditions were virtually transformed into H&E and special stains. The visibility of glomerular structures and the reliability of glomerular assessment were evaluated across multiple scanners. Optimized preparation of unstained sections enabled stable virtual staining with preserved morphological features. Virtual special stains enhanced the visualization of glomerular basement membranes and mesangial regions, allowing reliable identification of glomeruli on unstained tissue sections. This approach demonstrated robustness across different scanning systems, outperforming direct assessment on raw unstained images. Virtual staining of unstained renal biopsy sections provides a rapid and reagent-free strategy for early slide-level assessment of glomerular yield. By enabling feedback at the sectioning stage before routine staining, this method may improve efficiency and quality control in routine renal pathology workflows.

Diagnostic Pathology
Soochow University (CN), Institute of Computing Technology (CN), Second Affiliated Hospital of Soochow University (CN), First Affiliated Hospital of Soochow University (CN)
National Natural Science Foundation of China
Openalex Percentile: Top 3%
AI in cancer detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.