Galileo-an Artificial Intelligence tool for evaluating pre-implantation kidney biopsies

Pre-transplant procurement biopsy interpretation is challenging, also because of the low number of renal pathology experts. Artificial intelligence (AI) can assist by aiding pathologists with kidney donor biopsy assessment. Herein we present the "Galileo" AI tool, designed specifically to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of nephrology 2024-10
Hauptverfasser: Eccher, Albino, L'Imperio, Vincenzo, Pantanowitz, Liron, Cazzaniga, Giorgio, Del Carro, Fabio, Marletta, Stefano, Gambaro, Giovanni, Barreca, Antonella, Becker, Jan Ulrich, Gobbo, Stefano, Della Mea, Vincenzo, Alberici, Federico, Pagni, Fabio, Dei Tos, Angelo Paolo
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Pre-transplant procurement biopsy interpretation is challenging, also because of the low number of renal pathology experts. Artificial intelligence (AI) can assist by aiding pathologists with kidney donor biopsy assessment. Herein we present the "Galileo" AI tool, designed specifically to assist the on-call pathologist with interpreting pre-implantation kidney biopsies. A multicenter cohort of whole slide images acquired from core-needle and wedge biopsies of the kidney was collected. A deep learning algorithm was trained to detect the main findings evaluated in the pre-implantation setting (normal glomeruli, globally sclerosed glomeruli, ischemic glomeruli, arterioles and arteries). The model obtained on the Aiforia Create platform was validated on an external dataset by three independent pathologists to evaluate the performance of the algorithm. Galileo demonstrated a precision, sensitivity, F1 score and total area error of 81.96%, 94.39%, 87.74%, 2.81% and 74.05%, 71.03%, 72.5%, 2% in the training and validation sets, respectively. Galileo was significantly faster than pathologists, requiring 2 min overall in the validation phase (vs 25, 22 and 31 min by 3 separate human readers, p 
ISSN:1724-6059
1724-6059
DOI:10.1007/s40620-024-02094-4