An Artificial Intelligence Generated Automated Algorithm to Measure Total Kidney Volume in ADPKD
Taylor, Jonathan (Sheffield Teaching Hospitals NHS Foundation Trust)
Thomas, Richard (Sheffield Teaching Hospitals NHS Foundation Trust)
Metherall, Peter (Sheffield Teaching Hospitals NHS Foundation Trust)
van Gastel, Marieke (University Medical Centre Groningen)
Cornec-Le Gall, Emilie (University Brest)
Caroli, Anna (Istituto di Ricerche Farmacologiche Mario Negri IRCCS)
Furlano, Monica (Institut d'Investigació Biomèdica Sant Pau)
Demoulin, Nathalie (Cliniques Universitaires Saint-Luc)
Devuyst, Olivier (Cliniques Universitaires Saint-Luc)
Winterbottom, Jean (Sheffield Teaching Hospitals NHS Foundation Trust)
Torra Balcells, Roser (Institut d'Investigació Biomèdica Sant Pau)
Perico, Norberto (Istituto di Ricerche Farmacologiche Mario Negri IRCCS)
Le Meur, Yannick (University Brest)
Schoenherr, Sebastian (Medical University of Innsbruck)
Forer, Lukas (Medical University of Innsbruck)
Gansevoort, Ron T. (University Medical Centre Groningen)
Simms, Roslyn J. (Sheffield Teaching Hospitals NHS Foundation Trust)
Ong, Albert C. M. (Sheffield Teaching Hospitals NHS Foundation Trust)
Universitat Autònoma de Barcelona

Date:	2023
Abstract:	Accurate tools to inform individual prognosis in patients with autosomal dominant polycystic kidney disease (ADPKD) are lacking. Here, we report an artificial intelligence (AI)-generated method for routinely measuring total kidney volume (TKV). An ensemble U-net algorithm was created using the nnUNet approach. The training and internal cross-validation cohort consisted of all 1. 5T magnetic resonance imaging (MRI) data acquired using 5 different MRI scanners (454 kidneys, 227 scans) in the CYSTic consortium, which was first manually segmented by a single human operator. As an independent validation cohort, we utilized 48 sequential clinical MRI scans with reference results of manual segmentation acquired by 6 individual analysts at a single center. The tool was then implemented for clinical use and its performance analyzed. The training or internal validation cohort was younger (mean age 44. 0 vs. 51. 5 years) and the female-to-male ratio higher (1. 2 vs. 0. 94) compared to the clinical validation cohort. The majority of CYSTic patients had PKD1 mutations (79%) and typical disease (Mayo Imaging class 1, 86%). The median DICE score on the clinical validation data set between the algorithm and human analysts was 0. 96 for left and right kidneys with a median TKV error of −1. 8%. The time taken to manually segment kidneys in the CYSTic data set was 56 (±28) minutes, whereas manual corrections of the algorithm output took 8. 5 (±9. 2) minutes per scan. Our AI-based algorithm demonstrates performance comparable to manual segmentation. Its rapidity and precision in real-world clinical cases demonstrate its suitability for clinical application.
Rights:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Language:	Anglès
Document:	Article ; recerca ; Versió publicada
Subject:	ADPKD ; Artificial intelligence ; Machine learning ; Magnetic resonance imaging ; Total kidney volume
Published in:	Kidney International Reports, Vol. 9 (november 2023) , p. 249-256, ISSN 2468-0249

DOI: 10.1016/j.ekir.2023.10.029
PMID: 38344736

8 p, 1.2 MB

The record appears in these collections:
Research literature > UAB research groups literature > Research Centres and Groups (research output) > Health sciences and biosciences > Institut de Recerca Sant Pau
Articles > Research articles
Articles > Published articles