Multistain segmentation of renal histology: first steps toward artificial intelligence-augmented digital nephropathology

Roman D Bülow; Jesper Kers; Peter Boor

doi:10.1016/j.kint.2020.08.025

Multistain segmentation of renal histology: first steps toward artificial intelligence-augmented digital nephropathology

Kidney Int. 2021 Jan;99(1):17-19. doi: 10.1016/j.kint.2020.08.025.

Authors

Roman D Bülow¹, Jesper Kers², Peter Boor³

Affiliations

¹ Institute of Pathology, RWTH Aachen University Hospital, Aachen, Germany.
² Department of Pathology, Amsterdam UMC, Amsterdam Infection & Immunity Institute, University of Amsterdam, Amsterdam, The Netherlands; Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands; Van 't Hoff Institute for Molecular Sciences, University of Amsterdam, Amsterdam, The Netherlands.
³ Institute of Pathology, RWTH Aachen University Hospital, Aachen, Germany; Department of Nephrology and Immunology, RWTH Aachen University Hospital, Aachen, Germany. Electronic address: [email protected].

PMID: 33390226
DOI: 10.1016/j.kint.2020.08.025

Abstract

Artificial intelligence (AI), and particularly deep learning (DL), are showing great potential in improving pathology diagnostics in many aspects, 1 of which is the segmentation of histology into (diagnostically) relevant compartments. Although most current studies focus on AI and DL in oncologic pathology, an increasing number of studies explore their application to nephropathology, including the study published in this issue of Kidney International by Jayapandian et al.

Publication types

Research Support, Non-U.S. Gov't
Comment

MeSH terms

Artificial Intelligence*
Coloring Agents
Deep Learning*
Kidney
Kidney Cortex

Substances

Coloring Agents