This single-center observational cohort study analyzed 37 patients with glomerulonephritis from Danderyd University Hospital in Stockholm, Sweden. Researchers compared high-resolution microscopy and deep learning-based podocyte morphometrics (using the AMAP tool) against conventional electron microscopy findings, with a median follow-up of 3.0 years. The primary outcome was not reported; secondary outcomes focused on correlations with clinical characteristics, conventional EM findings, and longitudinal data.
Key results showed slit diaphragm length (SDL) significantly correlated with urine albumin-to-creatinine ratio (uACR) (p=0.021), whereas conventional EM measurements did not (p=0.22). In the IgA nephropathy subgroup, lower SDL was associated with steeper eGFR decline, and higher foot process (FP) area was associated with increased long-term proteinuria. Higher FP circularity was associated with uACR improvement during the first year. Notably, the association between lower SDL and eGFR decline remained a trend in IgA nephropathy patients not treated with corticosteroids (p=0.068) but was absent in those treated with corticosteroids (p=0.59).
Safety and tolerability data were not reported. The study's main limitations include its proof-of-concept nature and the need for validation in larger, independent cohorts before clinical implementation. Funding and conflicts of interest were not reported. The findings suggest nanoscale podocyte morphometrics may offer greater sensitivity than conventional EM for quantifying podocyte changes, but this remains investigational.
View Original Abstract ↓
IntroductionPodocyte injury is central to the pathogenesis of most glomerulonephritides (GN) and causes segmental glomerulosclerotic lesions that predict progression in IgA Nephropathy (IgAN). Recent advances in high-resolution microscopy and AI-assisted image analysis have enabled detailed quantification of podocyte foot process (FP) morphology. However, whether nanoscale podocyte morphometrics can predict disease progression or treatment response in GN has not been investigated.
AimTo evaluate whether nanoscale podocyte morphometric parameters predict clinical characteristics, disease progression, and treatment response in GN, with a focus on IgAN.
MethodPodocyte morphometrics were analyzed in kidney biopsies from patients with GN using high-resolution microscopy and the deep learning-based tool Automatic Morphometric Analysis of Podocytes (AMAP). Four morphometric parameters were quantified: slit diaphragm length (SDL), FP area, FP circularity and FP perimeter. These parameters were correlated with clinical characteristics, conventional electron microscopy (EM) findings and longitudinal follow-up data.
ResultsThe study included 37 patients with GN from Danderyd University Hospital (Stockholm, Sweden), with IgAN representing the largest diagnostic subgroup (n = 19). The median follow-up for the cohort was 3.0 years. SDL correlated significantly with urine albumin-to-creatinine ratio (uACR; p = 0.021), whereas conventional EM measurements did not (p = 0.22). Within the IgAN subgroup, lower SDL was associated with a steeper decline in eGFR, higher FP area with increased long-term proteinuria, and higher FP circularity with improvement in uACR during the first year. The association between lower SDL and eGFR decline remained as a trend in IgAN patients not treated with corticosteroids (p = 0.068) but was absent in the treatment group (p = 0.59).
ConclusionIn this proof-of-concept study, nanoscale podocyte morphometrics demonstrated greater sensitivity than conventional EM in quantifying podocyte injury and predicting progression in IgAN. These findings suggest that high-resolution morphometrics may improve risk stratification in IgAN but require validation in larger, independent cohorts before clinical implementation.