Deployed Deep Learning Kidney Segmentation for Polycystic Kidney Disease MRI.
Convolutional Neural Network (CNN)
Kidney
Segmentation
Journal
Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556
Informations de publication
Date de publication:
Mar 2022
Mar 2022
Historique:
received:
21
07
2021
revised:
20
01
2022
accepted:
25
01
2022
entrez:
8
4
2022
pubmed:
9
4
2022
medline:
9
4
2022
Statut:
epublish
Résumé
This study develops, validates, and deploys deep learning for automated total kidney volume (TKV) measurement (a marker of disease severity) on T2-weighted MRI studies of autosomal dominant polycystic kidney disease (ADPKD). The model was based on the U-Net architecture with an EfficientNet encoder, developed using 213 abdominal MRI studies in 129 patients with ADPKD. Patients were randomly divided into 70% training, 15% validation, and 15% test sets for model development. Model performance was assessed using Dice similarity coefficient (DSC) and Bland-Altman analysis. External validation in 20 patients from outside institutions demonstrated a DSC of 0.98 (IQR, 0.97-0.99) and a Bland-Altman difference of 2.6% (95% CI: 1.0%, 4.1%). Prospective validation in 53 patients demonstrated a DSC of 0.97 (IQR, 0.94-0.98) and a Bland-Altman difference of 3.6% (95% CI: 2.0%, 5.2%). Last, the efficiency of model-assisted annotation was evaluated on the first 50% of prospective cases (
Identifiants
pubmed: 35391774
doi: 10.1148/ryai.210205
pmc: PMC8980881
doi:
Banques de données
ClinicalTrials.gov
['NCT00792155']
Types de publication
Journal Article
Langues
eng
Pagination
e210205Subventions
Organisme : NCATS NIH HHS
ID : UL1 TR002384
Pays : United States
Informations de copyright
2022 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Disclosures of Conflicts of Interest: A.G. No relevant relationships. G.S. Leadership roles as co-chair of Society for Imaging Informatics in Medicine machine learning committee, co-chair for Society of Abdominal Radiology AI committee, co-director of Radiological Society of North America AI certificate course; assistant editor of Radiology: Artificial Intelligence. S.R. No relevant relationships. S.J. No relevant relationships. H.D. No relevant relationships. R.H. No relevant relationships. D.R. No relevant relationships. K.T. No relevant relationships. J.D.B. Grants or contracts from Vertex Pharmaceuticals; secretary of American Journal of Hypertension. I.B. No relevant relationships. I.C. No relevant relationships. H.R. No relevant relationships. M.R.P. No relevant relationships.
Références
Kidney Int. 2015 Jul;88(1):17-27
pubmed: 25786098
Kidney Int. 1987 Apr;31(4):1000-5
pubmed: 3295357
Kidney Int. 2018 Mar;93(3):691-699
pubmed: 29290310
Artif Intell Med. 2021 Jul;117:102109
pubmed: 34127239
J Digit Imaging. 2017 Aug;30(4):442-448
pubmed: 28550374
Radiol Artif Intell. 2020 Mar 25;2(2):e200029
pubmed: 33937821
Sci Rep. 2017 May 17;7(1):2049
pubmed: 28515418
Am J Kidney Dis. 2002 Jun;39(6):1127-34
pubmed: 12046022
J Am Soc Nephrol. 2015 Jan;26(1):160-72
pubmed: 24904092
Eur Radiol. 2020 Mar;30(3):1297-1305
pubmed: 31712961
Kidney Int. 2003 Sep;64(3):1035-45
pubmed: 12911554
Kidney Int. 2009 Jan;75(2):235-41
pubmed: 18971924
Clin J Am Soc Nephrol. 2006 Jan;1(1):148-57
pubmed: 17699202
BMC Med Imaging. 2020 Jul 29;20(1):87
pubmed: 32727476
N Engl J Med. 2012 Dec 20;367(25):2407-18
pubmed: 23121377
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
Nephron. 2015;129(4):253-62
pubmed: 25895545