Amsterdam UMC, Location Vrije Universiteit Amsterdam, Department of Radiology and Nuclear Medicine, De Boelelaan 1117, Amsterdam, the Netherlands.
Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, the Netherlands; Amsterdam UMC, Location Vrije Universiteit Amsterdam, Department of Otolaryngology - Head and Neck Surgery, De Boelelaan 1117, Amsterdam, the Netherlands.
Oral Oncol. 2023 Feb;137:106307. doi: 10.1016/j.oraloncology.2023.106307. Epub 2023 Jan 18.
Human papillomavirus- (HPV) positive oropharyngeal squamous cell carcinoma (OPSCC) differs biologically and clinically from HPV-negative OPSCC and has a better prognosis. This study aims to analyze the value of magnetic resonance imaging (MRI)-based radiomics in predicting HPV status in OPSCC and aims to develop a prognostic model in OPSCC including HPV status and MRI-based radiomics.
Manual delineation of 249 primary OPSCCs (91 HPV-positive and 159 HPV-negative) on pretreatment native T1-weighted MRIs was performed and used to extract 498 radiomic features per delineation. A logistic regression (LR) and random forest (RF) model were developed using univariate feature selection. Additionally, factor analysis was performed, and the derived factors were combined with clinical data in a predictive model to assess the performance on predicting HPV status. Additionally, factors were combined with clinical parameters in a multivariable survival regression analysis.
Both feature-based LR and RF models performed with an AUC of 0.79 in prediction of HPV status. Fourteen of the twenty most significant features were similar in both models, mainly concerning tumor sphericity, intensity variation, compactness, and tumor diameter. The model combining clinical data and radiomic factors (AUC = 0.89) outperformed the radiomics-only model in predicting OPSCC HPV status. Overall survival prediction was most accurate using the combination of clinical parameters and radiomic factors (C-index = 0.72).
Predictive models based on MR-radiomic features were able to predict HPV status with sufficient performance, supporting the role of MRI-based radiomics as potential imaging biomarker. Survival prediction improved by combining clinical features with MRI-based radiomics.
人乳头瘤病毒（HPV）阳性口咽鳞状细胞癌（OPSCC）在生物学和临床上与 HPV 阴性 OPSCC 不同，且预后更好。本研究旨在分析基于磁共振成像（MRI）的放射组学在预测 OPSCC 中 HPV 状态的价值，并旨在开发包括 HPV 状态和基于 MRI 的放射组学的 OPSCC 预后模型。
对 249 例原发 OPSCC（91 例 HPV 阳性和 159 例 HPV 阴性）的预处理原始 T1 加权 MRI 进行手动勾画，并对每个勾画区域提取 498 个放射组学特征。使用单变量特征选择建立逻辑回归（LR）和随机森林（RF）模型。此外，还进行了因子分析，并将得出的因子与临床数据相结合，构建预测模型，以评估其预测 HPV 状态的性能。此外，还将因子与多变量生存回归分析中的临床参数相结合。
基于特征的 LR 和 RF 模型在预测 HPV 状态方面的 AUC 均为 0.79。两种模型的 20 个最重要特征中有 14 个是相似的，主要涉及肿瘤球形度、强度变化、紧致度和肿瘤直径。将临床数据与放射组学因素相结合的模型（AUC=0.89）在预测 OPSCC HPV 状态方面优于仅基于放射组学的模型。使用临床参数和放射组学因素的组合进行总体生存预测最为准确（C 指数=0.72）。
基于 MRI 放射组学特征的预测模型能够以足够的性能预测 HPV 状态，支持 MRI 为基础的放射组学作为潜在的影像学生物标志物的作用。通过将临床特征与基于 MRI 的放射组学相结合，提高了生存预测的准确性。
