The utility of texture analysis based on quantitative synthetic magnetic resonance imaging in nasopharyngeal carcinoma: a preliminary study

Abstract

Background: Magnetic resonance imaging (MRI) is commonly used for the diagnosis of nasopharyngeal carcinoma (NPC) and occipital clivus (OC) invasion, but a proportion of lesions may be missed using non-enhanced MRI. The purpose of this study is to investigate the diagnostic performance of synthetic magnetic resonance imaging (SyMRI) in differentiating NPC from nasopharyngeal hyperplasia (NPH), as well as evaluating OC invasion.

Methods: Fifty-nine patients with NPC and 48 volunteers who underwent SyMRI examination were prospectively enrolled. Eighteen first-order features were extracted from VOIs (primary tumours, benign mucosa, and OC). Statistical comparisons were conducted between groups using the independent-samples t-test and the Mann-Whitney U test to select significant parameters. Multiple diagnostic models were then constructed using multivariate logistic analysis. The diagnostic performance of the models was calculated by receiver operating characteristics (ROC) curve analysis and compared using the DeLong test. Bootstrap and 5-folds cross-validation were applied to avoid overfitting.

Results: The T1, T2 and PD map-derived models had excellent diagnostic performance in the discrimination between NPC and NPH in volunteers, with area under the curves (AUCs) of 0.975, 0.972 and 0.986, respectively. Besides, SyMRI models also showed excellent performance in distinguishing OC invasion from non-invasion (AUC: 0.913-0.997). Notably, the T1 map-derived model showed the highest diagnostic performance with an AUC, sensitivity, specificity, and accuracy of 0.997, 96.9%, 97.9% and 97.5%, respectively. By using 5-folds cross-validation, the bias-corrected AUCs were 0.965-0.984 in discriminating NPC from NPH and 0.889-0.975 in discriminating OC invasion from OC non-invasion.

Conclusions: SyMRI combined with first-order parameters showed excellent performance in differentiating NPC from NPH, as well as discriminating OC invasion from non-invasion.

Keywords: Differential diagnosis; Magnetic resonance imaging; Nasopharyngeal carcinoma.

Fig. 1

SyMRI of a 48-year-old male NPC patient. a Axial T2WI shows uniform thickening with heterogeneous iso-slightly high signal in the posterior wall of the nasopharyngeal cavity, and bilateral pharyngeal recess are collapsed. VOI was manually delineated along the border of the tumour slice by slice. T1 map (b), T2 map (c) and PD map (d) at the same level as in (a). SyMRI, synthetic magnetic resonance imaging; NPC, nasopharyngeal carcinoma; T2WI, T2-weighted image; VOI, volume of interest; PD, proton density

Fig. 2

SyMRI of a 38-year-old female volunteer. a Axial T2WI shows hyperenhancing tissue along the posterior nasopharyngeal wall and bilateral lateral nasopharyngeal wall. Bilateral pharyngeal recess are collapsed and show symmetric wall thickness. VOI was manually delineated along the border of the benign mucosa slice by slice. Derived T1 map (b), T2 map (c) and PD map (d). SyMRI, synthetic magnetic resonance imaging; T2WI, T2-weighted image; VOI, volume of interest; PD, proton density

Fig. 3

Representative images of OC invasion and OC non-invasion. Invaded OC in 56-year-old NPC patient (a) shows low signal on axial T1WI of SyMRI, which shows similar signal characteristics with non-invaded OC in 38-year-old volunteer (b). VOI was manually delineated along the border of invaded OC and non-invaded OC on axial T1WI of SyMRI. OC, occipital clivus; NPC, nasopharyngeal carcinoma; T1WI, T-weighted image; SyMRI, synthetic magnetic resonance imaging; VOI, volume of interest

Fig. 4

ROC curves (a, e) and calibration curves (b-d, f–h) of models in all sample. a ROC curves of diagnostic models based on T1, T2 and PD maps for differentiating NPC from NPH in volunteers. Calibration curves of nomogram developed in T1 map (b), T2 map (c) and PD map (d) derived model. e ROC curves of diagnostic models based on T1, T2 and PD maps for the differentiation between OC invasion and OC non-invasion. Calibration curves of nomogram developed in T1 map (f), T2 map (g) and PD map (h) derived model. ROC, receiver operating characteristic; PD, proton density; NPC, nasopharyngeal carcinoma; OC, occipital clivus