MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation.
DWI
MRI
head and neck (H&N) cancer
radiomics
salivary gland (SG) tumors
Journal
Frontiers in oncology
ISSN: 2234-943X
Titre abrégé: Front Oncol
Pays: Switzerland
ID NLM: 101568867
Informations de publication
Date de publication:
2021
2021
Historique:
received:
21
01
2021
accepted:
08
04
2021
entrez:
14
5
2021
pubmed:
15
5
2021
medline:
15
5
2021
Statut:
epublish
Résumé
The differentiation between benign and malignant parotid lesions is crucial to defining the treatment plan, which highly depends on the tumor histology. We aimed to evaluate the role of MRI-based radiomics using both T2-weighted (T2-w) images and Apparent Diffusion Coefficient (ADC) maps in the differentiation of parotid lesions, in order to develop predictive models with an external validation cohort. A sample of 69 untreated parotid lesions was evaluated retrospectively, including 37 benign (of which 13 were Warthin's tumors) and 32 malignant tumors. The patient population was divided into three groups: benign lesions (24 cases), Warthin's lesions (13 cases), and malignant lesions (32 cases), which were compared in pairs. First- and second-order features were derived for each lesion. Margins and contrast enhancement patterns (CE) were qualitatively assessed. The model with the final feature set was achieved using the support vector machine binary classification algorithm. Models for discriminating between Warthin's and malignant tumors, benign and Warthin's tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. After the feature selection process, four parameters for each model were used, including histogram-based features from ADC and T2-w images, shape-based features and types of margins and/or CE. Comparable accuracies were obtained after validation with the external cohort. Radiomic analysis of ADC, T2-w images, and qualitative scores evaluating margins and CE allowed us to obtain good to excellent diagnostic accuracies in differentiating parotid lesions, which were confirmed with an external validation cohort.
Sections du résumé
BACKGROUND
BACKGROUND
The differentiation between benign and malignant parotid lesions is crucial to defining the treatment plan, which highly depends on the tumor histology. We aimed to evaluate the role of MRI-based radiomics using both T2-weighted (T2-w) images and Apparent Diffusion Coefficient (ADC) maps in the differentiation of parotid lesions, in order to develop predictive models with an external validation cohort.
MATERIALS AND METHODS
METHODS
A sample of 69 untreated parotid lesions was evaluated retrospectively, including 37 benign (of which 13 were Warthin's tumors) and 32 malignant tumors. The patient population was divided into three groups: benign lesions (24 cases), Warthin's lesions (13 cases), and malignant lesions (32 cases), which were compared in pairs. First- and second-order features were derived for each lesion. Margins and contrast enhancement patterns (CE) were qualitatively assessed. The model with the final feature set was achieved using the support vector machine binary classification algorithm.
RESULTS
RESULTS
Models for discriminating between Warthin's and malignant tumors, benign and Warthin's tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. After the feature selection process, four parameters for each model were used, including histogram-based features from ADC and T2-w images, shape-based features and types of margins and/or CE. Comparable accuracies were obtained after validation with the external cohort.
CONCLUSIONS
CONCLUSIONS
Radiomic analysis of ADC, T2-w images, and qualitative scores evaluating margins and CE allowed us to obtain good to excellent diagnostic accuracies in differentiating parotid lesions, which were confirmed with an external validation cohort.
Identifiants
pubmed: 33987092
doi: 10.3389/fonc.2021.656918
pmc: PMC8111169
doi:
Types de publication
Journal Article
Langues
eng
Pagination
656918Informations de copyright
Copyright © 2021 Piludu, Marzi, Ravanelli, Pellini, Covello, Terrenato, Farina, Campora, Ferrazzoli and Vidiri.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
AJR Am J Roentgenol. 2018 Jun;210(6):1330-1337
pubmed: 29667889
AJNR Am J Neuroradiol. 2010 May;31(5):809-16
pubmed: 20395383
Clin Radiol. 2020 Nov;75(11):877.e15-877.e23
pubmed: 32703544
Radiology. 2020 May;295(2):328-338
pubmed: 32154773
J Clin Imaging Sci. 2018 Nov 15;8:48
pubmed: 30546932
Br J Radiol. 2016;89(1060):20150912
pubmed: 26892378
AJNR Am J Neuroradiol. 2009 Mar;30(3):591-6
pubmed: 19131405
Jpn J Radiol. 2017 Feb;35(2):78-85
pubmed: 28074380
Diagnostics (Basel). 2020 Nov 03;10(11):
pubmed: 33153140
J Magn Reson Imaging. 2020 Jul;52(1):11-32
pubmed: 32065489
Dentomaxillofac Radiol. 2003 Sep;32(5):295-9
pubmed: 14709603
J Magn Reson Imaging. 2019 Jun;49(7):e101-e121
pubmed: 30451345
Gynecol Oncol. 2020 Jan;156(1):107-114
pubmed: 31685232
Int J Oral Maxillofac Surg. 2017 Mar;46(3):343-349
pubmed: 27769738
ORL J Otorhinolaryngol Relat Spec. 2017;79(1-2):54-64
pubmed: 28231589
J Magn Reson Imaging. 2020 Aug;52(2):608-609
pubmed: 32333824
Dentomaxillofac Radiol. 2019 Oct;48(7):20190100
pubmed: 31265331
Eur J Radiol. 2020 Jun;127:108991
pubmed: 32334372
Neuroimaging Clin N Am. 2018 May;28(2):303-317
pubmed: 29622121
NMR Biomed. 2013 Nov;26(11):1372-9
pubmed: 23703801
Med Phys. 2015 Mar;42(3):1341-53
pubmed: 25735289
Magn Reson Imaging. 2008 Nov;26(9):1316-22
pubmed: 18448302
Eur Ann Otorhinolaryngol Head Neck Dis. 2013 Feb;130(1):30-5
pubmed: 22819222
Radiology. 1987 May;163(2):405-9
pubmed: 3562818
Magn Reson Imaging. 2019 Nov;63:55-59
pubmed: 31422165
AJNR Am J Neuroradiol. 2004 Aug;25(7):1256-62
pubmed: 15313720
Diagn Interv Imaging. 2016 Jan;97(1):37-43
pubmed: 25543869
J Med Invest. 2019;66(1.2):35-37
pubmed: 31064950
AJNR Am J Neuroradiol. 2011 Aug;32(7):1202-7
pubmed: 21724574
J Magn Reson Imaging. 2020 Sep;52(3):873-882
pubmed: 32112598
Acta Radiol. 2020 May;61(5):629-635
pubmed: 31542938
Int J Radiat Oncol Biol Phys. 2018 Nov 15;102(4):1074-1082
pubmed: 30170101
NMR Biomed. 2021 Jan;34(1):e4408
pubmed: 32886955
Eur Radiol. 2020 Nov 19;:
pubmed: 33211145
Med Phys. 2020 Mar;47(3):1167-1173
pubmed: 31830303
Dentomaxillofac Radiol. 2018 Jul;47(5):20170343
pubmed: 29412748
Eur J Nucl Med Mol Imaging. 2019 Oct;46(11):2228-2234
pubmed: 31372671
J Neuroradiol. 2007 Jul;34(3):183-9
pubmed: 17568674
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762
pubmed: 28975929