Albino Eccher, Vincenzo L'Imperio, Liron Pantanowitz, Giorgio Cazzaniga, Fabio Del Carro, Stefano Marletta, Giovanni Gambaro, Antonella Barreca, Jan Ulrich Becker, Stefano Gobbo, Vincenzo Della Mea, Federico Alberici, Fabio Pagni, Angelo Paolo Dei Tos
{"title":"Galileo-an Artificial Intelligence tool for evaluating pre-implantation kidney biopsies.","authors":"Albino Eccher, Vincenzo L'Imperio, Liron Pantanowitz, Giorgio Cazzaniga, Fabio Del Carro, Stefano Marletta, Giovanni Gambaro, Antonella Barreca, Jan Ulrich Becker, Stefano Gobbo, Vincenzo Della Mea, Federico Alberici, Fabio Pagni, Angelo Paolo Dei Tos","doi":"10.1007/s40620-024-02094-4","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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 < 0.001). Galileo-assisted detection of renal structures and quantitative information was directly integrated in the final report.</p><p><strong>Conclusions: </strong>The Galileo AI-assisted tool shows promise in speeding up pre-implantation kidney biopsy interpretation, as well as in reducing inter-observer variability. This tool may represent a starting point for further improvements based on hard endpoints such as graft survival.</p>","PeriodicalId":16542,"journal":{"name":"Journal of Nephrology","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nephrology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s40620-024-02094-4","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: 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.
Methods: 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.
Results: 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 < 0.001). Galileo-assisted detection of renal structures and quantitative information was directly integrated in the final report.
Conclusions: The Galileo AI-assisted tool shows promise in speeding up pre-implantation kidney biopsy interpretation, as well as in reducing inter-observer variability. This tool may represent a starting point for further improvements based on hard endpoints such as graft survival.
期刊介绍:
Journal of Nephrology is a bimonthly journal that considers publication of peer reviewed original manuscripts dealing with both clinical and laboratory investigations of relevance to the broad fields of Nephrology, Dialysis and Transplantation. It is the Official Journal of the Italian Society of Nephrology (SIN).