Cover Image

Assessment of glomerular morphological patterns by deep learning algorithms

Compilation of different morphological lesion signatures is characteristic of renal pathology. Previous studies have documented the potential value of artificial intelligence (AI) in recognizing relatively clear-cut glomerular structures and patterns, such as segmental or global sclerosis or mesangi...

Full description

Saved in:
Bibliographic Details
Main Authors: Weis, Cleo-Aron Thias (Author) , Bindzus, Jan Niklas (Author) , Voigt, Jonas (Author) , Runz, Marlen (Author) , Hetjens, Svetlana (Author) , Gaida, Matthias (Author) , Popovic, Zoran V. (Author) , Porubský, Štefan (Author)
Format: Article (Journal)
Language:English
Published: 04 January 2022
In: Journal of nephrology
Year: 2022, Volume: 35, Issue: 2, Pages: 417-427
ISSN:1724-6059
DOI:10.1007/s40620-021-01221-9
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1007/s40620-021-01221-9
Get full text
Author Notes:Cleo-Aron Weis, Jan Niklas Bindzus, Jonas Voigt, Marlen Runz, Svetlana Hertjens, Matthias M. Gaida, Zoran V. Popovic, Stefan Porubsky
Description
Summary:Compilation of different morphological lesion signatures is characteristic of renal pathology. Previous studies have documented the potential value of artificial intelligence (AI) in recognizing relatively clear-cut glomerular structures and patterns, such as segmental or global sclerosis or mesangial hypercellularity. This study aimed to test the capacity of deep learning algorithms to recognize complex glomerular structural changes that reflect common diagnostic dilemmas in nephropathology.
Item Description:Gesehen am 07.02.2022
Physical Description:Online Resource
ISSN:1724-6059
DOI:10.1007/s40620-021-01221-9

Similar Items