A Clinical-Radiomics Nomogram Based on the Apparent Diffusion Coefficient (ADC) for Individualized Prediction of the Risk of Early Relapse in Advanced Sinonasal Squamous Cell Carcinoma: A 2-Year Follow-Up Study

Abstract

PurposeTo develop and validate a nomogram model combining radiomic features and clinical characteristics to preoperatively predict the risk of early relapse (ER) in advanced sinonasal squamous cell carcinomas (SNSCCs).MethodsA total of 152 SNSCC patients (clinical stage III-IV) who underwent diffusion-weighted imaging (DWI) were included in this study. The training cohort included 106 patients assessed at the headquarters of our hospital using MR scanner 1. The testing cohort included 46 patients assessed at the branch of our hospital using MR scanner 2. Least absolute shrinkage and selection operator (LASSO) regression was applied for feature selection and radiomic signature (radscore) construction. Multivariable logistic regression analysis was applied to identify independent predictors. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA). Furthermore, the patients were classified into high- or low-risk ER subgroups according to the optimal cutoff value of the nomogram using X-tile. The recurrence-free survival probability (RFS) of each subgroup was assessed.ResultsER was noted in 69 patients. The radscore included 8 selected radiomic features. The radscore, T stage and surgical margin were independent predictors. The nomogram showed better performance (AUC = 0.92) than either the radscore or the clinical factors in the training cohort (P < 0.050). In the testing cohort, the nomogram showed better performance (AUC = 0.92) than the clinical factors (P = 0.016) and tended to show better performance than the radscore (P = 0.177). The nomogram demonstrated good calibration and clinical utility. Kaplan-Meier analysis showed that the 2-year RFS rate for low-risk patients was significantly greater than that for high-risk patients in both the training and testing cohorts (P < 0.001).ConclusionsThe ADC-based radiomic nomogram model is potentially useful in predicting the risk of ER in advanced SNSCCs.

An MRI‐Based Radiomics Nomogram to Assess Recurrence Risk in Sinonasal Malignant Tumors

“…Some radiomics studies have assessed nasopharyngeal carcinoma and squamous cell carcinoma recurrence risk in the head and neck with high accuracy, showing the potential of radiomics for improving clinical decision‐making 32–34 . Therefore, we aimed to apply radiomics to assess the recurrence risk of SNMT.…”

“…Some radiomics studies have assessed nasopharyngeal carcinoma and squamous cell carcinoma recurrence risk in the head and neck with high accuracy, showing the potential of radiomics for improving clinical decision-making. [32][33][34] Therefore, we aimed to apply radiomics to assess the recurrence risk of SNMT. We distinguished three radiomics signatures on the basis of plain (T1WI and FS-T2WI), enhanced (T1WI + C), and combined (T1WI, FS-T2WI, and T1WI + C) MRI data.…”

Multiparametric MRI-based radiomics approach with deep transfer learning for preoperative prediction of Ki-67 status in sinonasal squamous cell carcinoma

“…Magnetic resonance imaging (MRI) allows better depiction of tumor due to the high soft tissue resolution and thus has been widely used for preoperative evaluation of the tumors in practice. Radiomics is an emerging method for medical image analysis, which can extract high-dimensional and quantitative features from routine radiological imaging ( 9 ). During the past few years, there have been several studies on the application of MRI based-radiomics to predict Ki-67 proliferation status in malignant tumors.…”