Adding automated decision-tree models to multiparametric MRI for parotid tumours improves clinical performance

•Addition of multiparametric sequences and automated decision-tree models to conventional morphological sequences increases the diagnostic performance for parotid tumours.•Apparent diffusion coefficient is the best parameter to discriminate most of parotid tumours.•Extracellular-extravascular space...

Full description

Saved in:

Bibliographic Details
Published in:	European journal of radiology Vol. 166; p. 110999
Main Authors:	Graber, Matthieu, Cadour, Farah, El Ahmadi, Ahmed Ali, Khati, Idir, Del Grande, Jean, Chagnaud, Christophe, Fakhry, Nicolas, Guye, Maxime, Varoquaux, Arthur
Format:	Journal Article
Language:	English
Published:	Ireland Elsevier B.V 01-09-2023
Subjects:	Classification and regression tree Decision-tree model Diffusion magnetic resonance imaging Dynamic contrast-enhancement Multiparametric magnetic resonance imaging Parotid neoplasms ADC SER C Diffusion magnetic resonance imaging MRI Parotid neoplasms Spe FNAC L AUC Ve Sens SD WASHout OB NPV DWI PPV W Vp CI DCE TSE Decision-tree model Classification and regression tree FOV ROI TME Ktrans TIC Multiparametric magnetic resonance imaging PA TE EES WASHin Dynamic contrast-enhancement Kep TR CART
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•Addition of multiparametric sequences and automated decision-tree models to conventional morphological sequences increases the diagnostic performance for parotid tumours.•Apparent diffusion coefficient is the best parameter to discriminate most of parotid tumours.•Extracellular-extravascular space volume coefficient, derived from dynamic contrast-enhanced sequences, is the best parameter to discriminate Warthin tumours. Therapeutic management of parotid gland tumours depends on their histological type. To aid its characterisation, we sought to develop automated decision-tree models based on multiparametric magnetic resonance imaging (MRI) parameters and to evaluate their added diagnostic value compared with morphological sequences. 206 MRIs from 206 patients with histologically proven parotid gland tumours were included from January 2009 to January 2018. Multiparametric MRI findings (including parameters derived from diffusion-weighted imaging [DWI] and dynamic contrast-enhanced [DCE]) were used to build predictive classification and regression tree (CART) models for each histological type. All MRIs were read twice: first, based on morphological sequence findings only, and second, with the addition of multiparametric sequences and CART findings. The diagnostic performance between these two readings was compared using ROC curves. Compared to morphological sequences alone, the addition of multiparametric analysis significantly increased the diagnostic performance for all histological types (p < 0.001 to p = 0.011), except for lymphomas, where the increase was not significant (AUC 1.00 vs. 0.99, p = 0.066). ADCmean was the best parameter to identify pleomorphic adenomas, carcinomas and lymphomas with respective cut-offs of 1.292 × 10–3 mm2/s, 1.181 × 10–3 mm2/s and 0.611 × 10–3 mm2/s, respectively. × 10–3 mm2/s. The mean extracellular-extravascular space coefficient was the best parameter to Warthin tumours from the others, with a cut-off of 0.07. The addition of decision tree prediction models based on multiparametric sequences improves the non-invasive diagnostic performance of parotid gland tumours. ADC and extracellular-extravascular space coefficient are the two best parameters for decision making.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0720-048X 1872-7727
DOI:	10.1016/j.ejrad.2023.110999