Categorization of collagen type I and II blend hydrogel using multipolarization SHG imaging with ResNet regression.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
09 11 2023
09 11 2023
Historique:
received:
05
09
2023
accepted:
31
10
2023
medline:
13
11
2023
pubmed:
10
11
2023
entrez:
9
11
2023
Statut:
epublish
Résumé
Previously, the discrimination of collagen types I and II was successfully achieved using peptide pitch angle and anisotropic parameter methods. However, these methods require fitting polarization second harmonic generation (SHG) pixel-wise information into generic mathematical models, revealing inconsistencies in categorizing collagen type I and II blend hydrogels. In this study, a ResNet approach based on multipolarization SHG imaging is proposed for the categorization and regression of collagen type I and II blend hydrogels at 0%, 25%, 50%, 75%, and 100% type II, without the need for prior time-consuming model fitting. A ResNet model, pretrained on 18 progressive polarization SHG images at 10° intervals for each percentage, categorizes the five blended collagen hydrogels with a mean absolute error (MAE) of 0.021, while the model pretrained on nonpolarization images exhibited 0.083 MAE. Moreover, the pretrained models can also generally regress the blend hydrogels at 20%, 40%, 60%, and 80% type II. In conclusion, the multipolarization SHG image-based ResNet analysis demonstrates the potential for an automated approach using deep learning to extract valuable information from the collagen matrix.
Identifiants
pubmed: 37945626
doi: 10.1038/s41598-023-46417-0
pii: 10.1038/s41598-023-46417-0
pmc: PMC10636134
doi:
Substances chimiques
Collagen Type I
0
Hydrogels
0
Collagen
9007-34-5
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
19534Informations de copyright
© 2023. The Author(s).
Références
Analyst. 2019 Feb 25;144(5):1642-1653
pubmed: 30644947
Sci Rep. 2022 Nov 2;12(1):18453
pubmed: 36323698
Acta Biomater. 2014 May;10(5):2036-42
pubmed: 24444774
J Biophotonics. 2020 Oct;13(10):e202000180
pubmed: 32643819
ACS Biomater Sci Eng. 2020 Jun 8;6(6):3464-3476
pubmed: 33463160
Osteoarthritis Cartilage. 2021 May;29(5):762-772
pubmed: 33588085
J Biophotonics. 2013 Feb;6(2):129-42
pubmed: 22791562
Opt Express. 2014 Sep 22;22(19):22561-74
pubmed: 25321725
J R Soc Interface. 2019 Jan 31;16(150):20180611
pubmed: 30958161
J R Soc Interface. 2022 Feb;19(187):20210670
pubmed: 35135299
Biophys J. 2015 Dec 15;109(12):2501-2510
pubmed: 26682809
J Struct Biol. 2008 Oct;164(1):140-5
pubmed: 18664383
Tissue Eng Regen Med. 2017 Jun 30;14(4):383-391
pubmed: 30603494
Biomacromolecules. 2016 Oct 10;17(10):3145-3152
pubmed: 27585034
IEEE Trans Med Imaging. 2020 Dec;39(12):4011-4022
pubmed: 32746142
Comput Biol Med. 2022 Jul;146:105541
pubmed: 35525070
Opt Express. 2009 Jun 22;17(13):11161-71
pubmed: 19550516
Histochem Cell Biol. 2004 Sep;122(3):229-36
pubmed: 15316793
J Biophotonics. 2015 Sep;8(9):730-9
pubmed: 25363416
Biomed Opt Express. 2021 Apr 30;12(5):3050-3065
pubmed: 34168914
Appl Opt. 2020 Jan 1;59(1):151-155
pubmed: 32225281
Tissue Eng Part A. 2016 Jun;22(11-12):899-906
pubmed: 27221620
Biomed Opt Express. 2018 Nov 19;9(12):6350-6358
pubmed: 31065433