Department of Otolaryngology Head and Neck Surgery, Xiangya Hospital, Central South University, 87 Xiangya Road, Changsha, Hunan, 410008, People's Republic of China.
Otolaryngology Major Disease Research, Key Laboratory of Hunan Province, 87 Xiangya Road, Changsha, Hunan, 410008, People's Republic of China.
Eur Radiol. 2022 Dec;32(12):8099-8110. doi: 10.1007/s00330-022-08943-9. Epub 2022 Jun 24.
To evaluate the effectiveness of machine learning models based on morphological magnetic resonance imaging (MRI) radiomics in the classification of parotid tumors.
In total, 298 patients with parotid tumors were randomly assigned to a training and test set at a ratio of 7:3. Radiomics features were extracted from the morphological MRI images and screened using the Select K Best and LASSO algorithm. Three-step machine learning models with XGBoost, SVM, and DT algorithms were developed to classify the parotid neoplasms into four subtypes. The ROC curve was used to measure the performance in each step. Diagnostic confusion matrices of these models were calculated for the test cohort and compared with those of the radiologists.
Six, twelve, and eight optimal features were selected in each step of the three-step process, respectively. XGBoost produced the highest area under the curve (AUC) for all three steps in the training cohort (0.857, 0.882, and 0.908, respectively), and for the first step in the test cohort (0.826), but produced slightly lower AUCs than SVM in the latter two steps in the test cohort (0.817 vs. 0.833, and 0.789 vs. 0.821, respectively). The total accuracies of XGBoost and SVM in the confusion matrices (70.8% and 59.6%) outperformed those of DT and the radiologist (46.1% and 49.2%).
This study demonstrated that machine learning models based on morphological MRI radiomics might be an assistive tool for parotid tumor classification, especially for preliminary screening in absence of more advanced scanning sequences, such as DWI.
• Machine learning algorithms combined with morphological MRI radiomics could be useful in the preliminary classification of parotid tumors. • XGBoost algorithm performed better than SVM and DT in subtype differentiation of parotid tumors, while DT seemed to have a poor validation performance. • Using morphological MRI only, the XGBoost and SVM algorithms outperformed radiologists in the four-type classification task for parotid tumors, thus making these models a useful assistant diagnostic tool in clinical practice.
评估基于形态磁共振成像（MRI）放射组学的机器学习模型在腮腺肿瘤分类中的有效性。
共纳入 298 例腮腺肿瘤患者，按 7:3 的比例随机分配到训练集和测试集。从形态 MRI 图像中提取放射组学特征，并使用 Select K Best 和 LASSO 算法进行筛选。采用 XGBoost、SVM 和 DT 算法建立三步骤机器学习模型，将腮腺肿瘤分为四种亚型。使用 ROC 曲线测量各步骤的性能。计算这些模型的测试队列诊断混淆矩阵，并与放射科医生的结果进行比较。
在三步骤过程的每一步中，分别选择了六个、十二个和八个最佳特征。XGBoost 在训练队列的所有三个步骤中均产生了最高的曲线下面积（AUC）（分别为 0.857、0.882 和 0.908），在测试队列的第一步中也产生了较高的 AUC（0.826），但在测试队列的后两步中，XGBoost 的 AUC 略低于 SVM（分别为 0.817 比 0.833 和 0.789 比 0.821）。XGBoost 和 SVM 在混淆矩阵中的总准确率（70.8%和 59.6%）优于 DT 和放射科医生（46.1%和 49.2%）。
本研究表明，基于形态 MRI 放射组学的机器学习模型可能是腮腺肿瘤分类的辅助工具，尤其是在缺乏更高级扫描序列（如 DWI）的情况下，可用于初步筛查。
机器学习算法结合形态 MRI 放射组学可用于初步腮腺肿瘤分类。
XGBoost 算法在腮腺肿瘤亚型分化中优于 SVM 和 DT，而 DT 在验证性能方面似乎较差。
仅使用形态 MRI，XGBoost 和 SVM 算法在腮腺肿瘤的四型分类任务中优于放射科医生，因此这些模型成为临床实践中有用的辅助诊断工具。
