Development of an automated estimation of foot process width using deep learning in kidney biopsies from patients with Fabry, minimal change, and diabetic kidney diseases

Podocyte injury plays a key role in pathogenesis of many kidney diseases with increased podocyte foot process width (FPW), an important measure of podocyte injury. Unfortunately, there is no consensus on the best way to estimate FPW and unbiased stereology, the current gold standard, is time consuming and not widely available. To address this, we developed an automated FPW estimation technique using deep learning. A U-Net architecture variant model was trained to semantically segment the podocyte-glomerular basement membrane interface and filtration slits. Additionally, we employed a post-processing computer vision approach to accurately estimate FPW. A custom segmentation utility was also created to manually classify these structures on digital electron microscopy (EM) images and to prepare a training dataset. The model was applied to EM images of kidney biopsies from 56 patients with Fabry disease, 15 with type 2 diabetes, 10 with minimal change disease, and 17 normal individuals. The results were compared with unbiased stereology measurements performed by expert technicians unaware of the clinical information. FPW measured by deep learning and by the expert technicians were highly correlated and not statistically different in any of the studied groups. A Bland-Altman plot confirmed interchangeability of the methods. FPW measurement time per biopsy was substantially reduced by deep learning. Thus, we have developed a novel validated deep learning model for FPW measurement on EM images. The model is accessible through a cloud-based application making calculation of this important biomarker more widely accessible for research and clinical applications.

Mitochondrial Dynamics of Podocyte in Various International Society of Nephrology/Renal Pathology Society Class Lupus Nephritis Patients

Morphological changes of podocyte mitochondria are observed in patients with mitochondrial cytopathy and nephrotic syndrome. However, whether mitochondrial dynamics involved in podocyte in lupus nephritis (LN) is still not clear. This study aims to investigate the associations between mitochondrial morphology and podocyte lesions and laboratory and pathological features in LN. The foot process width (FPW) and mitochondrial morphology were observed through electron microscope. Then the associations between mitochondrial morphology and podocyte lesions and laboratory features were explored in various International Society of Nephrology/Renal Pathology Society class LN patients. Foot process effacement and excessive mitochondria fission in podocyte were observed and proteinuria was positively correlated with FPW. Mitochondria area, circumference, and aspect ratio were negatively correlated with BUN, and 24h-UTP positively correlated with Alb. At the same time, Alb was negatively correlated with form factor. FPW, form factor, surface density, and numerical density on area were positively correlated with 24h-UTP. Excessive mitochondrial fission is associated with podocyte damage and proteinuria, whereas the mechanism still needs to be explored.

Podocyte involvement in lupus nephritis based on the 2003 ISN/RPS system: a large cohort study from a single centre

OBJECTIVE

The podocyte lesion in LN is still an intriguing controversy. We assess the associations between podocyte lesions and clinico-pathological features in a large cohort of LN patients.

METHODS

The clinico-pathological data of 202 patients with renal biopsy-proven LN were retrospectively studied. The degree of podocyte lesions was assessed morphologically and its correlations with clinico-pathological parameters were further analysed.

RESULTS

The podocyte foot processes of most LN patients significantly effaced, reflected by the median foot process width (FPW) of 1397.39 nm, and 13 patients met the histological criteria of lupus podocytopathy. The FPW was correlated with proteinuria (r = 0.509, P < 0.001) and the cut-off value of FPW, >1240 nm, could differentiate nephrotic proteinuria from non-nephrotic proteinuria with sensitivity 81.5% and specificity 62.7%. The FPW varied significantly with different types of LN, and the patients with combined LN presented with the most severe lesions. The complete remission rate was significantly higher and the long-term renal outcome was better in the group with calcineurin inhibitors than that with other regimens in patients with FPW >1240 nm.

CONCLUSION

Podocyte damage was common in LN. Pure lupus podocytopathy might act as an extreme form of lupus podocyte lesion, and more patients might present with severe podocyte effacement concealed in different types of LN, which needs further investigation.