Artificial intelligence velocimetry and microaneurysm-on-a-chip for three-dimensional analysis of blood flow in physiology and disease.
Artificial Intelligence
Blood Flow Velocity
Computer Simulation
Diabetic Retinopathy
/ diagnosis
Hemodynamics
Humans
Imaging, Three-Dimensional
/ methods
Lab-On-A-Chip Devices
Microaneurysm
/ diagnosis
Microfluidic Analytical Techniques
Regional Blood Flow
Retinal Vessels
/ physiopathology
Rheology
/ methods
blood flow in microaneurysm
deep learning
diabetic retinopathy
image analysis
three-dimensional flow fields
Journal
Proceedings of the National Academy of Sciences of the United States of America
ISSN: 1091-6490
Titre abrégé: Proc Natl Acad Sci U S A
Pays: United States
ID NLM: 7505876
Informations de publication
Date de publication:
30 03 2021
30 03 2021
Historique:
entrez:
25
3
2021
pubmed:
26
3
2021
medline:
27
10
2021
Statut:
ppublish
Résumé
Understanding the mechanics of blood flow is necessary for developing insights into mechanisms of physiology and vascular diseases in microcirculation. Given the limitations of technologies available for assessing in vivo flow fields, in vitro methods based on traditional microfluidic platforms have been developed to mimic physiological conditions. However, existing methods lack the capability to provide accurate assessment of these flow fields, particularly in vessels with complex geometries. Conventional approaches to quantify flow fields rely either on analyzing only visual images or on enforcing underlying physics without considering visualization data, which could compromise accuracy of predictions. Here, we present artificial-intelligence velocimetry (AIV) to quantify velocity and stress fields of blood flow by integrating the imaging data with underlying physics using physics-informed neural networks. We demonstrate the capability of AIV by quantifying hemodynamics in microchannels designed to mimic saccular-shaped microaneurysms (microaneurysm-on-a-chip, or MAOAC), which signify common manifestations of diabetic retinopathy, a leading cause of vision loss from blood-vessel damage in the retina in diabetic patients. We show that AIV can, without any a priori knowledge of the inlet and outlet boundary conditions, infer the two-dimensional (2D) flow fields from a sequence of 2D images of blood flow in MAOAC, but also can infer three-dimensional (3D) flow fields using only 2D images, thanks to the encoded physics laws. AIV provides a unique paradigm that seamlessly integrates images, experimental data, and underlying physics using neural networks to automatically analyze experimental data and infer key hemodynamic indicators that assess vascular injury.
Identifiants
pubmed: 33762307
pii: 2100697118
doi: 10.1073/pnas.2100697118
pmc: PMC8020788
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : NHLBI NIH HHS
ID : R01 HL154150
Pays : United States
Informations de copyright
Copyright © 2021 the Author(s). Published by PNAS.
Déclaration de conflit d'intérêts
Competing interest statement: S.C., H.L., M.D., G.E.K., and S.S. have filed a patent application based on the research presented in this paper.
Références
Phys Rev Lett. 2012 Sep 7;109(10):108102
pubmed: 23005332
Ann Intensive Care. 2020 Nov 12;10(1):152
pubmed: 33184724
Proc Natl Acad Sci U S A. 2011 Jan 4;108(1):35-9
pubmed: 21173269
Curr Diab Rep. 2019 Aug 31;19(10):95
pubmed: 31473838
Biomed Opt Express. 2016 Nov 04;7(12):4958-4973
pubmed: 28078170
Biomicrofluidics. 2018 May 15;12(4):042201
pubmed: 29861812
Platelets. 2017 Jul;28(5):427-433
pubmed: 28594261
J Biomech Eng. 2011 Mar;133(3):031001
pubmed: 21303177
Biorheology. 2007;44(3):161-77
pubmed: 17851165
Wiley Interdiscip Rev Syst Biol Med. 2016 Mar-Apr;8(2):157-68
pubmed: 26695350
Comput Methods Appl Mech Eng. 2009 Sep 15;198(45-46):3514-3523
pubmed: 20161129
Ann N Y Acad Sci. 2000 May;902:230-9; discussion 239-40
pubmed: 10865843
Proc Natl Acad Sci U S A. 2020 Mar 31;117(13):7052-7062
pubmed: 32179694
Annu Rev Fluid Mech. 2005 Jan 1;37:43-69
pubmed: 21151769
Biochem Biophys Res Commun. 1997 Feb 24;231(3):586-90
pubmed: 9070851
J Neurosurg. 2010 Jun;112(6):1240-53
pubmed: 19943737
Stroke. 2008 Nov;39(11):2997-3002
pubmed: 18688012
R Soc Open Sci. 2020 Aug 26;7(8):201102
pubmed: 32968536
Biophys J. 2018 Oct 2;115(7):1371-1382
pubmed: 30224049
Interface Focus. 2013 Apr 6;3(2):20120089
pubmed: 24427532
Proc Natl Acad Sci U S A. 2013 Jan 22;110(4):1357-62
pubmed: 23288905
Integr Biol (Camb). 2016 May 16;8(5):589-602
pubmed: 27068565
Lab Chip. 2009 Sep 7;9(17):2551-67
pubmed: 19680579
Phys Fluids (1994). 2016 Feb;28(2):021304
pubmed: 26909005
Science. 2020 Feb 28;367(6481):1026-1030
pubmed: 32001523
Ann Intern Med. 1975 Jun;82(6):733-8
pubmed: 1138583
Integr Biol (Camb). 2013 Mar;5(3):474-80
pubmed: 23371018
Clin Exp Ophthalmol. 2016 May;44(4):260-77
pubmed: 26716602
Invest Ophthalmol Vis Sci. 2014 Mar 04;55(3):1299-309
pubmed: 24425852
Bull Math Biol. 1985;47(5):613-27
pubmed: 4084694
Br J Ophthalmol. 1995 Apr;79(4):362-7
pubmed: 7742285
Biomed Microdevices. 2008 Apr;10(2):153-67
pubmed: 17885805
J Vasc Surg. 2015 Apr;61(4):1068-80
pubmed: 25704412
PLoS Comput Biol. 2017 Jan 17;13(1):e1005291
pubmed: 28095402
BMB Rep. 2020 Jul;53(7):357-366
pubmed: 32475382
Ann Biomed Eng. 2015 Jan;43(1):238-57
pubmed: 25398331
Front Physiol. 2018 Sep 07;9:989
pubmed: 30245632
Microcirculation. 2005 Jan-Feb;12(1):5-15
pubmed: 15804970
Blood. 2007 Jun 15;109(12):5087-95
pubmed: 17311994
Arteriosclerosis. 1988 Nov-Dec;8(6):819-24
pubmed: 3196226
Br J Ophthalmol. 2018 Jun 20;:
pubmed: 29925511
Physiol Rev. 2017 Apr;97(2):495-528
pubmed: 28151424