Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma
Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma
复制标题
DOI：
10.1016/j.ejrad.2019.108755
复制
发表时间：
2020-01-01
影响因子：
3.3
通讯作者：
Chen, Bihong T.
中科院分区：
文献类型：
--
作者：
Wang, Hao;Song, Bin;Chen, Bihong T.
目的：探讨基于机器学习的多参数磁共振 (MR) 成像放射组学的预测能力，用于术前评估甲状腺乳头状癌 (PTC) 的侵袭性。 方法：这项前瞻性研究连续纳入了在研究间隔期间接受颈部 MR 扫描和随后的甲状腺切除术的患者。 PTC的诊断和侵袭性通过甲状腺切除标本的病理学评估来确定。在 MR 图像上手动分割甲状腺结节，然后提取放射组学特征。使用预测机器学习模型来评估 PTC 攻击性的预测。获得模型性能的受试者工作特征曲线下面积 (AUC) 值的放射组学特征、临床特征以及放射组学特征和临床特征的组合。 结果：研究队列包括 120 名经病理证实的 PTC 患者（训练队列 n = 96；测试队列 n = 24）。从每位患者的 T2 加权、表观扩散系数 (ADC) 和对比增强 T1 加权 MR 图像中总共提取了 1393 个特征。用于放射组学特征选择的最小绝对收缩和选择算子与用于对 PTC 侵袭性进行分类的梯度增强分类器的组合，实现了 0.92 的 AUC。相比之下，仅凭临床特征很难预测 PTC 侵袭性，AUC 为 0.56。结论：我们的研究表明，基于机器学习的多参数 MR 成像放射组学可以在术前准确区分侵袭性和非侵袭性 PTC。这种方法可能有助于了解侵袭性 PTC 患者的治疗策略和预后。
Purpose: To investigate the predictive capability of machine learning-based multiparametric magnetic resonance (MR) imaging radiomics for evaluating the aggressiveness of papillary thyroid carcinoma (PTC) preoperatively.Methods: This prospective study enrolled consecutive patients who underwent neck MR scans and subsequent thyroidectomy during the study interval. The diagnosis and aggressiveness of PTC were determined by pathological evaluation of thyroidectomy specimens. Thyroid nodules were segmented manually on the MR images, and radiomic features were then extracted. Predictive machine learning modelling was used to evaluate the prediction of PTC aggressiveness. Area under the receiver operating characteristic curve (AUC) values for the model performance were obtained for radiomic features, clinical characteristics, and combinations of radiomic features and clinical characteristics.Results: The study cohort included 120 patients with pathology-confirmed PTC (training cohort n = 96; testing cohort n = 24). A total of 1393 features were extracted from T2-weighted, apparent diffusion coefficient (ADC) and contrast-enhanced T1-weighted MR images for each patient. The combination of Least Absolute Shrinkage and Selection Operator for radiomic feature selection and Gradient Boosting Classifier for classifying PTC aggressiveness achieving the AUC of 0.92. In contrast, clinical characteristics alone poorly predicted PTC aggressiveness, with an AUC of 0.56.Conclusions: Our study showed that machine learning-based multiparametric MR imaging radiomics could accurately distinguish aggressive from non-aggressive PTC preoperatively. This approach may be helpful for informing treatment strategies and prognosis of patients with aggressive PTC.