MRI-based radiomics analysis for preoperative evaluation of lymph node metastasis in hypopharyngeal squamous cell carcinoma

Abstract

ObjectiveTo investigate the role of pre-treatment magnetic resonance imaging (MRI) radiomics for the preoperative prediction of lymph node (LN) metastasis in patients with hypopharyngeal squamous cell carcinoma (HPSCC).MethodsA total of 155 patients with HPSCC were eligibly enrolled from single institution. Radiomics features were extracted from contrast-enhanced axial T-1 weighted (CE-T1WI) sequence. The most relevant features of LN metastasis were selected by the least absolute shrinkage and selection operator (LASSO) method. Univariate and multivariate logistic regression analysis was adopted to determine the independent clinical risk factors. Three models were constructed to predict the LN metastasis status: one using radiomics only, one using clinical factors only, and the other one combined radiomics and clinical factors. Receiver operating characteristic (ROC) curves and calibration curve were used to evaluate the discrimination and the accuracy of the models, respectively. The performances were tested by an internal validation cohort (n=47). The clinical utility of the models was assessed by decision curve analysis.ResultsThe nomogram consisted of radiomics scores and the MRI-reported LN status showed satisfactory discrimination in the training and validation cohorts with AUCs of 0.906 (95% CI, 0.840 to 0.972) and 0.853 (95% CI, 0.739 to 0.966), respectively. The nomogram, i.e., the combined model, outperformed the radiomics and MRI-reported LN status in both discrimination and clinical usefulness.ConclusionsThe MRI-based radiomics nomogram holds promise for individual and non-invasive prediction of LN metastasis in patients with HPSCC.

The application of nomogram model integrating clinical factors and multi-modal MRI radiomics features for predicting cervical lymph nodes metastasis for patients with oral tongue squamous cell carcinoma: a multicenter study

“…Yiwei Zhong et al established arti cial network model based on CT radiomics signature, with the AUC of 0.943 (0.891-0.996), but they ignored the effect of clinical risk factors [36]. Previous studies also have con rmed that MRI radiomics can evaluate preoperative CLNM for HNSCC and other sites cancers [20][21][22][23][37][38][39]. But they mostly were single-center studies or single-sequence MRI studies.…”

“…MRI has an excellent resolution for diseases of soft tissue, and radiomics based on MRI has been successfully reported to predicted lymph nodes metastasis for other anatomic site cancers [15][16][17][18][19]. Radiomics also has been successfully reported to predicted CLNM for head and neck squamous cell carcinoma (HNSCC) [20][21][22][23]. But they were all single-center studies or single-modal MRI studies and did not well apply to OTSCC patients in different tumor staging subgroup.…”

Longitudinal and Multimodal Radiomics Models for Head and Neck Cancer Outcome Prediction

“…It has been applied for several tumor entities and treatment endpoints, such as overall survival (OS) [5][6][7][8], loco-regional tumor control (LRC) [6,9,10], progression-free survival (PFS) [11][12][13], and distant metastasis (DM)-free survival [9,14,15]. In a radiomics approach, routinely obtained medical images such as computed tomography (CT) [6,8,9,16], magnetic resonance imaging (MRI) [17][18][19], or positron emission tomography (PET) scans [10,[20][21][22] can be used to compute quantitative features that describe, e.g., a tumor's size, shape, or texture. These features are then used in the creation of statistical models to predict the endpoint of interest.…”