Assessment of blood perfusion quality in laparoscopic colorectal surgery by means of Machine Learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
29 08 2022
29 08 2022
Historique:
received:
30
11
2021
accepted:
04
07
2022
entrez:
29
8
2022
pubmed:
30
8
2022
medline:
1
9
2022
Statut:
epublish
Résumé
An innovative algorithm to automatically assess blood perfusion quality of the intestinal sector in laparoscopic colorectal surgery is proposed. Traditionally, the uniformity of the brightness in indocyanine green-based fluorescence consists only in a qualitative, empirical evaluation, which heavily relies on the surgeon's subjective assessment. As such, this leads to assessments that are strongly experience-dependent. To overcome this limitation, the proposed algorithm assesses the level and uniformity of indocyanine green used during laparoscopic surgery. The algorithm adopts a Feed Forward Neural Network receiving as input a feature vector based on the histogram of the green band of the input image. It is used to (i) acquire information related to perfusion during laparoscopic colorectal surgery, and (ii) support the surgeon in assessing objectively the outcome of the procedure. In particular, the algorithm provides an output that classifies the perfusion as adequate or inadequate. The algorithm was validated on videos captured during surgical procedures carried out at the University Hospital Federico II in Naples, Italy. The obtained results show a classification accuracy equal to [Formula: see text], with a repeatability of [Formula: see text]. Finally, the real-time operation of the proposed algorithm was tested by analyzing the video streaming captured directly from an endoscope available in the OR.
Identifiants
pubmed: 36038561
doi: 10.1038/s41598-022-16030-8
pii: 10.1038/s41598-022-16030-8
pmc: PMC9424219
doi:
Substances chimiques
Indocyanine Green
IX6J1063HV
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
14682Informations de copyright
© 2022. The Author(s).
Références
NPJ Digit Med. 2020 Sep 11;3:118
pubmed: 32984550
Surg Today. 2021 Sep;51(9):1415-1428
pubmed: 33428000
Surg Endosc. 2016 Jul;30(7):2736-42
pubmed: 26487209
Int J Colorectal Dis. 2020 Mar;35(3):471-480
pubmed: 31907595
Surg Endosc. 2020 Jan;34(1):202-208
pubmed: 30877565
Br J Surg. 2021 Jan 27;108(1):5-9
pubmed: 33640921
Sci Rep. 2019 Jul 31;9(1):11132
pubmed: 31366903
Colorectal Dis. 2021 Jul;23(7):1848-1859
pubmed: 33894016
Surg Endosc. 2022 Apr;36(4):2245-2257
pubmed: 35024926
Nat Rev Cardiol. 2020 Jan;17(1):1-3
pubmed: 31605093
Surg Endosc. 2020 Dec;34(12):5223-5233
pubmed: 32696147
Sci Rep. 2021 May 31;11(1):11349
pubmed: 34059705
Br J Surg. 2015 Jan;102(2):e169-76
pubmed: 25627131
Ann Surg. 2015 Jul;262(1):74-8
pubmed: 25029436
Gastrointest Endosc. 2020 Oct;92(4):807-812
pubmed: 32565184
Nat Biomed Eng. 2018 Oct;2(10):719-731
pubmed: 31015651
Sci Rep. 2019 Jun 10;9(1):8421
pubmed: 31182746
Surg Endosc. 2020 Jan;34(1):53-60
pubmed: 30903276
Ann Ital Chir. 2012 Jan-Feb;83(1):1-5
pubmed: 22352208
Cathet Cardiovasc Diagn. 1989 Aug;17(4):231-3
pubmed: 2670244
Surg Endosc. 2020 Sep;34(9):4041-4047
pubmed: 31617088
World J Gastroenterol. 2021 Oct 14;27(38):6374-6386
pubmed: 34720528
Clin Chem. 1989 May;35(5):899-900
pubmed: 2720998
J Clin Invest. 1960 Apr;39:592-600
pubmed: 13809697
Surg Endosc. 2017 Oct;31(10):4184-4193
pubmed: 28281123
Sci Rep. 2020 Aug 31;10(1):14274
pubmed: 32868829
Int J Surg. 2020 Jul;79:88-94
pubmed: 32413503
Dis Colon Rectum. 2022 May 1;65(5):e329-e333
pubmed: 35170546
Transplant Proc. 2006 Apr;38(3):801-2
pubmed: 16647475
World J Gastroenterol. 2020 Nov 28;26(44):6945-6962
pubmed: 33311942
Artif Intell Med. 2020 Aug;108:101923
pubmed: 32972656