In Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association
BACKGROUND : Though the MEST-C classification is among the best prognostic tools in IgA nephropathy, it has a wide inter-observer variability between specialized pathologists and others. Therefore, we trained and evaluated a tool using Neural Network to automate the MEST-C grading.
METHODS : Biopsies of patients with IgA nephropathy 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, more than 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 ROC curves were 0.88, 0.91, 0.88, 0.94, 0.96, 0.96 and 0.92 to respectively predict M1, E1, S1, T1, T2, C1 and C2. The kappa coefficients between pathologists and the Network assessments were substantial for E, S, T and C scores (kappa scores respectively of 0.68, 0.79, 0.73 and 0.70) 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 Ratio respectively of 9.67, P = 0.006 and 7.67, P<0.001).
CONCLUSIONS : This work highlights the possibility of automated recognition and quantification of each element of the MEST-C classification using Deep Learning methods.
Jaugey Adrien, Maréchal Elise, Tarris Georges, Paindavoine Michel, Martin Laurent, Chabannes Melchior, de la Vega Mathilde Funes, Chaintreuil Mélanie, Robier Coline, Ducloux Didier, Crépin Thomas, Felix Sophie, Jacq Amélie, Calmo Doris, Tinel Claire, Zanetta Gilbert, Rebibou Jean-Michel, Legendre Mathieu
2023-Feb-15
IgA nephropathy, MEST-C classification, convolutional neural network, deep learning, kidney biopsy
