Li Jinyan, Jiang Nan, Zhang Juntao, Sun Wenyue, Wang Zhan, Sun Lixin, Wang Ximing
Department of Radiology, Shandong Provincial ENT Hospital, Shandong University, Jinan, China.
Department of Pathology, Shandong Provincial ENT Hospital, Shandong University, Jinan, China.
Eur J Radiol. 2025 Feb;183:111912. doi: 10.1016/j.ejrad.2024.111912. Epub 2025 Jan 5.
To assess the efficacy of computed tomography (CT)-based radiomics nomogram in predicting perineural invasion (PNI) in patients with hypopharyngeal squamous cell carcinoma (HPSCC).
Overall, 146 patients were retrospectively recruited and divided into training and test cohorts at a 7:3 ratio. Radiomics features were extracted and delta and absolute delta radiomics features were calculated. Feature selection was performed using maximum relevance minimum redundancy and least absolute shrinkage and selection operator methods. Preliminary models were built using logistic regression, and the optimal one was selected as the radiomics signature. A nomogram was constructed by combining independent clinical factors and the radiomics signature. Its performance was evaluated using the area under the curve (AUC) values of receiver operating characteristic curves, decision curve analysis (DCA), and calibration curves.
The radiomics signature comprised 14 absolute delta radiomics features. The nomogram, incorporating tumor thickness and radiomics signature, outperformed the other models (AUC = 0.79 and 0.78, training and test cohorts, respectively). The Delong test demonstrated that the nomogram's predictive performance was significantly higher than that of the clinical model (p < 0.05) in both cohorts. Calibration curves indicated good calibration, and the Hosmer-Lemeshow test confirmed a good fit (p = 0.969 and 0.429, training and test cohorts, respectively). DCA highlighted the nomogram's considerable clinical usefulness.
The CT-based absolute delta radiomics nomogram can noninvasively and preoperatively predict PNI status in patients with HPSCC, providing a valuable tool for clinical decision making and individualized treatment plans.
评估基于计算机断层扫描（CT）的影像组学列线图预测下咽鳞状细胞癌（HPSCC）患者神经周围侵犯（PNI）的效能。
本研究共回顾性纳入146例患者，按照7:3的比例分为训练组和测试组。提取影像组学特征并计算增量和绝对增量影像组学特征。采用最大相关最小冗余法和最小绝对收缩选择算子法进行特征选择。使用逻辑回归建立初步模型，并选择最优模型作为影像组学特征。通过结合独立临床因素和影像组学特征构建列线图。采用受试者操作特征曲线的曲线下面积（AUC）值、决策曲线分析（DCA）和校准曲线评估其性能。
影像组学特征由14个绝对增量影像组学特征组成。纳入肿瘤厚度和影像组学特征的列线图在训练组和测试组中的表现均优于其他模型（AUC分别为0.79和0.78）。德龙检验表明，在两个队列中，列线图的预测性能均显著高于临床模型（p<0.05）。校准曲线显示校准良好，Hosmer-Lemeshow检验证实拟合良好（训练组和测试组的p值分别为0.969和0.429）。DCA突出了列线图具有相当大的临床实用性。
基于CT的绝对增量影像组学列线图能够在术前无创预测HPSCC患者的PNI状态，为临床决策和个体化治疗方案提供了有价值的工具。
