Department of Radiology and Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, South Korea.
Laryngoscope. 2021 Mar;131(3):E851-E856. doi: 10.1002/lary.28889. Epub 2020 Jul 13.
To investigate whether a radiomic MRI feature-based prediction model can differentiate oropharyngeal squamous cell carcinoma (SCC) according to the human papillomavirus (HPV) status.
Retrospective cohort study.
Pretreatment MRI data from 62 consecutive patients with oropharyngeal SCC were retrospectively reviewed, and chronologically allocated to training (n = 43) and test sets (n = 19). Enhancing tumors were semi-automatically segmented on each slice of the postcontrast T1WI to span the entire tumor volume, after registration of T2WI to postcontrast T1WI; 170 radiomic features were extracted from the entire tumor volume. Relevant features were selected and radiomics models were trained using least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation, after subsampling of training sets using synthetic minority over-sampling technique to mitigate data imbalance. The selected features, weighted by their respective coefficients, were combined linearly to yield a radiomics score. The diagnostic performance of the radiomic score was evaluated using the area under the receiver operating characteristic curve (AUC).
Six radiomic features, which revealed strong association with HPV status of oropharyngeal SCC, were selected using LASSO. The radiomics model yielded excellent performance on the training set (AUC, 0.982 [95% CI, 0.942-1.000]) and moderate performance on the test set (AUC, 0.744 [95% CI, 0.496-0.991]) for differentiating oropharyngeal SCC according to HPV status.
Radiomics-based MRI phenotyping differentiates oropharyngeal SCC according to HPV status, and thus, is a potential imaging biomarker.
3 Laryngoscope, 131:E851-E856, 2021.
探究基于放射组学 MRI 特征的预测模型是否能根据人乳头瘤病毒（HPV）状态区分口咽鳞状细胞癌（SCC）。
回顾性队列研究。
回顾性分析 62 例连续的口咽 SCC 患者的预处理 MRI 数据，按照时间顺序分为训练集（n=43）和测试集（n=19）。在 T2WI 与对比后 T1WI 配准后，对每个对比后 T1WI 切片上的增强肿瘤进行半自动分割，以覆盖整个肿瘤体积；从整个肿瘤体积中提取 170 个放射组学特征。使用 10 折交叉验证的最小绝对收缩和选择算子（LASSO）逻辑回归模型选择相关特征并进行放射组学模型训练，然后使用合成少数过采样技术对训练集进行抽样，以减轻数据不平衡。选择的特征根据其各自的系数进行线性组合，得到放射组学评分。使用受试者工作特征曲线（ROC）下面积（AUC）评估放射组学评分的诊断性能。
使用 LASSO 选择了与口咽 SCC 的 HPV 状态有很强关联的 6 个放射组学特征。放射组学模型在训练集上表现出优异的性能（AUC，0.982[95%CI，0.942-1.000]），在测试集上表现出中等性能（AUC，0.744[95%CI，0.496-0.991]），可根据 HPV 状态区分口咽 SCC。
基于放射组学的 MRI 表型可根据 HPV 状态区分口咽 SCC，因此是一种潜在的影像学生物标志物。
3级喉镜，131：E851-E856，2021。
