Deep learning automation of MEST-C classification in IgA nephropathy
Nephrology Dialysis Transplantation · 30.06.2023 · 38 (7) · 1741-1751
DOI: 10.1093/ndt/gfad039 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nephrology Dialysis Transplantation, online erschienen am 15.02.2023. Verfasst von Adrien Jaugey und 17 weiteren Autor:innen. Beteiligte Einrichtung: ESIREM School, Dijon, France. Hauptthemen laut MEDLINE: Glomerulonephritis, IGA, Deep Learning. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: GIRCI.
Abstract (Originalsprache)
Background
Although the MEST-C classification is among the best prognostic tools in immunoglobulin A nephropathy (IgAN), it has a wide interobserver variability between specialized pathologists and others. Therefore we trained and evaluated a tool using a neural network to automate the MEST-C grading.
Methods
Biopsies of patients with IgAN were divided into three independent groups: the Training cohort (n = 42) to train the network, the Test cohort (n = 66) to compare its pixel segmentation to that made by pathologists and the Application cohort (n = 88) to compare the MEST-C scores computed by the network or by pathologists.
Results
In the Test cohort, >73% of pixels were correctly identified by the network as M, E, S or C. In the Application cohort, the neural network area under the receiver operating characteristics curves were 0.88, 0.91, 0.88, 0.94, 0.96, 0.96 and 0.92 to predict M1, E1, S1, T1, T2, C1 and C2, respectively. The kappa coefficients between pathologists and the network assessments were substantial for E, S, T and C scores (kappa scores of 0.68, 0.79, 0.73 and 0.70, respectively) and moderate for M score (kappa score of 0.52). Network S and T scores were associated with the occurrence of the composite survival endpoint (death, dialysis, transplantation or doubling of serum creatinine) [hazard ratios 9.67 (P = .006) and 7.67 (P < .001), respectively].
Conclusions
This work highlights the possibility of automated recognition and quantification of each element of the MEST-C classification using deep learning methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ESIREM School, Dijon, France.
- LEAD Laboratoire de l'étude de l'apprentissage et du Développement, Dijon, France.
- Department of Nephrology, CHU Dijon, Dijon, France.
- Université de Bourgogne Franche Comté, France.
- Department of Pathology, CHU Dijon, Dijon, France.
- Department of Nephrology, CHU Besançon, Besançon, France.
Förderung
- GIRCI
Zitieren
APA
Jaugey, A., Maréchal, E., Tarris, G., Paindavoine, M., Martin, L., Chabannes, M., Funes de la Vega, M., Chaintreuil, M., Robier, C., Ducloux, D., Crépin, T., Felix, S., Jacq, A., Calmo, D., Tinel, C., Zanetta, G., Rebibou, J. M., & Legendre, M. (2023). Deep learning automation of MEST-C classification in IgA nephropathy. Nephrology Dialysis Transplantation, 38(7), 1741-1751. https://doi.org/10.1093/ndt/gfad039
Vancouver
Jaugey A, Maréchal E, Tarris G, Paindavoine M, Martin L, Chabannes M, et al. Deep learning automation of MEST-C classification in IgA nephropathy. Nephrology Dialysis Transplantation. 2023;38(7):1741-1751. doi:10.1093/ndt/gfad039
BibTeX
@article{Jaugey2023,
author = {Jaugey, Adrien and Maréchal, Elise and Tarris, Georges and Paindavoine, Michel and Martin, Laurent and Chabannes, Melchior and Funes de la Vega, Mathilde and Chaintreuil, Mélanie and Robier, Coline and Ducloux, Didier and Crépin, Thomas and Felix, Sophie and Jacq, Amélie and Calmo, Doris and Tinel, Claire and Zanetta, Gilbert and Rebibou, Jean-Michel and Legendre, Mathieu},
title = {Deep learning automation of MEST-C classification in IgA nephropathy},
journal = {Nephrology Dialysis Transplantation},
year = {2023},
volume = {38},
number = {7},
pages = {1741--1751},
doi = {10.1093/ndt/gfad039}
}
EUVIMED