Abstract
Morphologic examination of tissue biopsies is essential for histopathological diagnosis. However, accurate and scalable cellular quantification in human samples remains challenging. Here, we present a deep learning–based approach for antigen-specific cellular morphometrics in human kidney biopsies, which combines indirect immunofluorescence imaging with U-Net–based architectures for image-to-image translation and dual segmentation tasks, achieving human-level accuracy. In the kidney, podocyte loss represents a hallmark of glomerular injury and can be estimated in diagnostic biopsies. Thus, we profiled over 27,000 podocytes from 110 human samples, including patients with antineutrophil cytoplasmic antibody–associated glomerulonephritis (ANCA-GN), an immune-mediated disease with aggressive glomerular damage and irreversible loss of kidney function. We identified previously unknown morphometric signatures of podocyte depletion in patients with ANCA-GN, which allowed patient classification and, in combination with routine clinical tools, showed potential for risk stratification. Our approach enables robust and scalable molecular morphometric analysis of human tissues, yielding deeper biological insights into the human kidney pathophysiology.
Highlights
The kidney continuously filters blood and maintains overall body homeostasis, relying on a delicate balance between a complex vascular network and multiple specialized cell types [1]
Training curves of the U-Net cycleGAN, as well as receiver operating characteristic (ROC) and precision-recall curves for the different combinations of data and segmentation networks, are provided in Supplemental Figure 6, A and B. While these results provide evidence that unannotated data sets can be efficiently segmented using a network trained on the reference data set when they are bias transferred using the U-Net cycleGAN, we obtained slightly better segmentation results using a segmentation U-Net trained on all images, including the 2 control and the antibody–associated glomerulonephritis (ANCA-GN) data sets
We present a deep learning–based approach that automatically identifies morphometric signatures of podocyte depletion in human kidney biopsies, achieving human-level accuracy while saving time and resources
Summary
The kidney continuously filters blood and maintains overall body homeostasis, relying on a delicate balance between a complex vascular network and multiple specialized cell types [1]. Podocytes are kidney epithelial cells with limited capacity for regeneration that function as master regulators of glomerular health [2]. Antineutrophil cytoplasmic antibody–associated glomerulonephritis (ANCA-GN) is primarily a systemic vasculitis with a strong immune-mediated epithelial reaction in the kidney, which leads to the formation of destructive glomerular lesions and a rapid loss of kidney function [14]. While ANCA-GN has well-defined cellular changes [15] that include podocyte injury [16], podocyte loss is yet to be characterized in ANCA-GN patients. Reliable image segmentation for routine clinical analysis remains challenging, mostly due to time constraints for detailed quantitative analysis with cellular resolution and lack of accuracy in available automated methods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
