Differentiating low and high grade mucoepidermoid carcinoma of the salivary glands using CT radiomics.
CT
Salivary gland
grade
mucoepidermoid carcinoma (MEC)
texture analysis
Journal
Gland surgery
ISSN: 2227-684X
Titre abrégé: Gland Surg
Pays: China (Republic : 1949- )
ID NLM: 101606638
Informations de publication
Date de publication:
May 2021
May 2021
Historique:
entrez:
24
6
2021
pubmed:
25
6
2021
medline:
25
6
2021
Statut:
ppublish
Résumé
The purpose of this study is to determine if Haralick texture analysis on CT imaging of mucoepidermoid carcinomas (MEC) can differentiate low-grade and high-grade tumors. A retrospective review of 18 patients with MEC of the salivary glands, corresponding CT imaging and pathology report was performed. Tumors were manually segmented and image analysis was performed to calculate radiomic features. Radiomic features were compared between low-grade and high-grade MEC. A multivariable logistic regression model and receiver operating characteristic analysis was performed. A total of 18 patients (mean age, 51, range 9-83 years, 8 men and 10 women) were included. Nine patients had low-grade pathology and nine patients had high-grade pathology. Of the 18 cases, 7 (39%) occurred in the parotid gland and 11 (61%) occurred in minor salivary glands. No individual feature was significantly different between low-grade and high-grade MEC. A logistic regression model including surface regularity, energy and information measure II of correlation was performed and was able to predict high-grade MEC accurately (sensitivity 89%, specificity 68%). The area under the receiver operating characteristic curve was 0.802. High-grade MEC tend to have a low energy, high correlation texture as well as surface irregularity. Together, these three features may comprise a tumor phenotype that is able to predict high-grade pathology in MECs.
Sections du résumé
BACKGROUND
BACKGROUND
The purpose of this study is to determine if Haralick texture analysis on CT imaging of mucoepidermoid carcinomas (MEC) can differentiate low-grade and high-grade tumors.
METHODS
METHODS
A retrospective review of 18 patients with MEC of the salivary glands, corresponding CT imaging and pathology report was performed. Tumors were manually segmented and image analysis was performed to calculate radiomic features. Radiomic features were compared between low-grade and high-grade MEC. A multivariable logistic regression model and receiver operating characteristic analysis was performed.
RESULTS
RESULTS
A total of 18 patients (mean age, 51, range 9-83 years, 8 men and 10 women) were included. Nine patients had low-grade pathology and nine patients had high-grade pathology. Of the 18 cases, 7 (39%) occurred in the parotid gland and 11 (61%) occurred in minor salivary glands. No individual feature was significantly different between low-grade and high-grade MEC. A logistic regression model including surface regularity, energy and information measure II of correlation was performed and was able to predict high-grade MEC accurately (sensitivity 89%, specificity 68%). The area under the receiver operating characteristic curve was 0.802.
CONCLUSIONS
CONCLUSIONS
High-grade MEC tend to have a low energy, high correlation texture as well as surface irregularity. Together, these three features may comprise a tumor phenotype that is able to predict high-grade pathology in MECs.
Identifiants
pubmed: 34164309
doi: 10.21037/gs-20-830
pii: gs-10-05-1646
pmc: PMC8184388
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1646-1654Subventions
Organisme : NIDCR NIH HHS
ID : K08 DE026500
Pays : United States
Informations de copyright
2021 Gland Surgery. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/gs-20-830). The authors have no conflicts of interest to declare.
Références
JCO Clin Cancer Inform. 2019 Feb;3:1-9
pubmed: 30730765
Head Neck Pathol. 2009 Mar;3(1):69-77
pubmed: 20596994
Am J Surg Pathol. 2019 Jul;43(7):885-897
pubmed: 31021855
J Xray Sci Technol. 2020;28(4):799-808
pubmed: 32538891
Radiol Imaging Cancer. 2020 May 15;2(3):e190039
pubmed: 32550599
Acta Oncol. 2015;54(9):1423-9
pubmed: 26264429
Oral Oncol. 2017 Aug;71:150-155
pubmed: 28688683
Clin Transl Radiat Oncol. 2017 Nov 06;7:49-54
pubmed: 29594229
Front Oncol. 2019 Aug 30;9:821
pubmed: 31544063
EJNMMI Res. 2020 Jul 6;10(1):74
pubmed: 32632638
J Comput Assist Tomogr. 2003 Jan-Feb;27(1):56-61
pubmed: 12544244
Eur Radiol Exp. 2018 Nov 14;2(1):36
pubmed: 30426318
Radiology. 2014 Jan;270(1):141-8
pubmed: 23985274
Sci Rep. 2019 Mar 13;9(1):4329
pubmed: 30867443
Neuroradiology. 2019 Aug;61(8):861-867
pubmed: 31020343
Invest Radiol. 2016 Mar;51(3):177-85
pubmed: 26561049
Cancer Imaging. 2013 Mar 26;13:140-9
pubmed: 23545171
Radiology. 2019 Dec;293(3):583-591
pubmed: 31573400
Oral Oncol. 2019 Aug;95:178-186
pubmed: 31345388
Radiology. 2020 May;295(2):328-338
pubmed: 32154773
Eur Radiol. 2015 Oct;25(10):2840-50
pubmed: 25991476
Strahlenther Onkol. 2019 Sep;195(9):771-779
pubmed: 31123786
AJR Am J Roentgenol. 2018 Nov;211(5):1026-1034
pubmed: 30240304
Cancer. 2008 Oct 15;113(8):2082-9
pubmed: 18720358
Neuroradiology. 2020 Nov;62(11):1451-1458
pubmed: 32621023
AJNR Am J Neuroradiol. 2015 Jul;36(7):1343-8
pubmed: 25836725
Nat Commun. 2014 Jun 03;5:4006
pubmed: 24892406
Sci Rep. 2018 Sep 19;8(1):14036
pubmed: 30232350
Radiology. 2018 Jul;288(1):218-225
pubmed: 29924716
Radiology. 2016 Apr;279(1):185-94
pubmed: 26624973
AJR Am J Roentgenol. 2015 Dec;205(6):1160-6
pubmed: 26587920
Int J Biomed Imaging. 2015;2015:267807
pubmed: 26557845
Diagnostics (Basel). 2020 Nov 03;10(11):
pubmed: 33153140
Otolaryngol Head Neck Surg. 2018 May;158(5):889-895
pubmed: 29313462
J Comput Assist Tomogr. 2016 Jan-Feb;40(1):43-7
pubmed: 26466116
Sci Rep. 2018 Jan 24;8(1):1524
pubmed: 29367653