A Novel Deep Learning Approach for Analyzing Glomerular Basement Membrane Lesions in a Mouse Model of X-Linked Alport Syndrome.

Abstract

Alport syndrome is a rare kidney disease typically more severe in males due to its X-linked inheritance. However, female patients with heterozygous X-linked Alport syndrome (XLAS) can develop renal failure over time, necessitating accurate pathologic assessment for effective therapy. A key pathologic finding in female patients with XLAS is the mosaic pattern of partial loss of α5 chains of type IV collagen. This study, using a mouse model of XLAS with a nonsense mutation (R471∗) in the Col4a5 gene, analogous to human XLAS, aimed to examine the consistency of this pattern with the glomerular basement membrane (GBM) structure. A modified periodic acid-methenamine silver staining method was developed for clearer GBM visualization. The integrated images from COL4α5-stained fluorescence, periodic acid-methenamine silver, and low-vacuum scanning electron microscopy into a single-slide section and applied supervised deep learning to predict GBM lesions. Results showed significant individual variability in urinary protein levels and histologic lesions. Pathologic parameters, including crescent formation, focal segmental glomerulosclerosis, and the COL4α5/α2 ratio, correlated with clinical parameters like urinary protein and plasma creatinine levels. Integrated low-vacuum scanning electron microscopy analysis revealed dense GBM regions corresponded to areas where COL4α5 was preserved, whereas coarse GBM (basket-weave lesions) occurred in COL4α5-deficient regions. These advanced techniques can enhance biopsy-based diagnosis of Alport syndrome and aid in developing artificial intelligence diagnostic tools for diseases involving basement membrane lesions.