Immunoexpression of oral brush biopsy enhances the accuracy of diagnosis for oral lichen planus and lichenoid lesions.
cell-blocks
computer-assisted diagnosis
epithelial dysplasia
liquid-based brush cytology
oral lichen planus
Journal
Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology
ISSN: 1600-0714
Titre abrégé: J Oral Pathol Med
Pays: Denmark
ID NLM: 8911934
Informations de publication
Date de publication:
Jul 2022
Jul 2022
Historique:
received:
12
04
2022
accepted:
14
04
2022
pubmed:
24
4
2022
medline:
19
7
2022
entrez:
23
4
2022
Statut:
ppublish
Résumé
This study assessed the efficacy of using oral liquid-based brush cytology (OLBC) coupled with immunostained cytology-derived cell-blocks, quantified using machine-learning, in the diagnosis of oral lichen planus (OLP). Eighty-two patients diagnosed clinically with either OLP or oral lichenoid lesion (OLL) were included. OLBC samples were obtained from all patients before undergoing surgical biopsy. Liquid-based cytology slides and cell-blocks were prepared and assessed by cytomorphology and immunocytochemistry for four antibodies (Ki-67, BAX, NF-κB-p65, and AMACR). For comparison purposes, a sub-group of 31 matched surgical biopsy samples were selected randomly and assessed by immunohistochemistry. Patients were categorized according to their definitive diagnoses into OLP, OLL, and clinically lichenoid, but histopathologically dysplastic lesions (OEDL). Machine-learning was utilized to provide automated quantification of positively stained protein expression. Cytomorphological assessment was associated with an accuracy of 77.27% in the distinction between OLP/OLL and OEDL. A strong concordance of 92.5% (κ = 0.84) of immunostaining patterns was evident between cell-blocks and tissue sections using machine-learning. A diagnostic index using a Ki-67-based model was 100% accurate in detecting lichenoid cases with epithelial dysplasia. A BAX-based model demonstrated an accuracy of 92.16%. The accuracy of cytomorphological assessment was greatly improved when it was combined with BAX immunoreactivity (95%). Cell-blocks prepared from OLBC are reliable and minimally-invasive alternatives to surgical biopsies to diagnose OLLs with epithelial dysplasia when combined with Ki-67 immunostaining. Machine-learning has a promising role in the automated quantification of immunostained protein expression.
Sections du résumé
BACKGROUND
BACKGROUND
This study assessed the efficacy of using oral liquid-based brush cytology (OLBC) coupled with immunostained cytology-derived cell-blocks, quantified using machine-learning, in the diagnosis of oral lichen planus (OLP).
METHODS
METHODS
Eighty-two patients diagnosed clinically with either OLP or oral lichenoid lesion (OLL) were included. OLBC samples were obtained from all patients before undergoing surgical biopsy. Liquid-based cytology slides and cell-blocks were prepared and assessed by cytomorphology and immunocytochemistry for four antibodies (Ki-67, BAX, NF-κB-p65, and AMACR). For comparison purposes, a sub-group of 31 matched surgical biopsy samples were selected randomly and assessed by immunohistochemistry. Patients were categorized according to their definitive diagnoses into OLP, OLL, and clinically lichenoid, but histopathologically dysplastic lesions (OEDL). Machine-learning was utilized to provide automated quantification of positively stained protein expression.
RESULTS
RESULTS
Cytomorphological assessment was associated with an accuracy of 77.27% in the distinction between OLP/OLL and OEDL. A strong concordance of 92.5% (κ = 0.84) of immunostaining patterns was evident between cell-blocks and tissue sections using machine-learning. A diagnostic index using a Ki-67-based model was 100% accurate in detecting lichenoid cases with epithelial dysplasia. A BAX-based model demonstrated an accuracy of 92.16%. The accuracy of cytomorphological assessment was greatly improved when it was combined with BAX immunoreactivity (95%).
CONCLUSIONS
CONCLUSIONS
Cell-blocks prepared from OLBC are reliable and minimally-invasive alternatives to surgical biopsies to diagnose OLLs with epithelial dysplasia when combined with Ki-67 immunostaining. Machine-learning has a promising role in the automated quantification of immunostained protein expression.
Identifiants
pubmed: 35460123
doi: 10.1111/jop.13301
pmc: PMC9542982
doi:
Substances chimiques
Ki-67 Antigen
0
bcl-2-Associated X Protein
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
563-572Subventions
Organisme : Australian Dental Research Foundation
Organisme : University of Western Australia
Informations de copyright
© 2022 The Authors. Journal of Oral Pathology & Medicine published by John Wiley & Sons Ltd.
Références
J Oral Pathol Med. 2022 Jul;51(6):563-572
pubmed: 35460123
J Oral Pathol Med. 2018 Feb;47(2):104-116
pubmed: 29130527
Inflammation. 2015 Aug;38(4):1683-9
pubmed: 25761427
Oral Dis. 2015 May;21(4):478-82
pubmed: 25482285
Oral Dis. 2021 Nov;27(8):1862-1880
pubmed: 33128420
Exp Ther Med. 2018 May;15(5):4157-4166
pubmed: 29731815
J Oral Pathol Med. 2021 Oct;50(9):946-953
pubmed: 34358361
Nat Immunol. 2014 Jan;15(1):15-25
pubmed: 24352326
Oral Oncol. 2006 May;42(5):475-80
pubmed: 16364678
J Oral Pathol Med. 2021 May;50(5):520-527
pubmed: 33730381
Diagn Cytopathol. 2020 Apr;48(4):291-299
pubmed: 31930724
Asian Pac J Cancer Prev. 2018 Nov 29;19(11):3279-3286
pubmed: 30486632
Oral Oncol. 2021 Jun;117:105282
pubmed: 33838504
Sci Rep. 2019 Sep 16;9(1):13341
pubmed: 31527658
PLoS One. 2014 Sep 26;9(9):e108762
pubmed: 25259861
Med Oral Patol Oral Cir Bucal. 2009 Nov 01;14(11):e563-7
pubmed: 19680198
Head Neck. 2020 Mar;42(3):539-555
pubmed: 31803979
Oral Dis. 2021 May;27(4):813-828
pubmed: 32144836
J Oral Pathol Med. 2021 Mar;50(3):287-298
pubmed: 31981238
Arab J Gastroenterol. 2016 Sep;17(3):121-126
pubmed: 27567189
Oral Oncol. 2006 Nov;42(10):987-93
pubmed: 16731030
Oral Dis. 2021 Nov;27(8):1947-1976
pubmed: 34418233
Oral Oncol. 2021 Aug;119:105362
pubmed: 34062399
J Oral Pathol Med. 2018 Oct;47(9):887-894
pubmed: 29957892
Lab Invest. 2021 Apr;101(4):412-422
pubmed: 33454724
J Oral Pathol Med. 2019 Aug;48(7):538-545
pubmed: 31172588
Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2007 Aug;104(2):217-25
pubmed: 17560138
J Oral Pathol Med. 2019 Aug;48(7):566-573
pubmed: 31172614
J Oral Pathol Med. 2021 May;50(5):451-458
pubmed: 33368584
Oral Surg Oral Med Oral Pathol Oral Radiol. 2016 Sep;122(3):332-54
pubmed: 27401683