Department of Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, No.107 Wenhuaxi Road, Jinan, 250012, Shandong, China.
Department of Radiology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, No.440 Jiyan Road, Jinan, 250117, Shandong, China.
Esophagus. 2022 Apr;19(2):269-277. doi: 10.1007/s10388-021-00886-2. Epub 2021 Oct 12.
CT is the most commonly used method to stage esophageal cancer (EC). However, the reported CT T-staging criteria for EC are controversial.
To determine and validate the optimal esophageal wall thickness (EWT) threshold on CT to distinguish lesions with different T stages in esophageal squamous cell carcinoma (ESCC) patients.
One thousand, one hundred-two consecutive patients with histopathologically confirmed ESCC between July 2014 and April 2020 were retrospectively reviewed. All patients underwent a preoperative CT examination and surgical treatment. The maximal EWT of the lesions on CT was measured. Patients were divided into pT1, pT2, pT3 and pT4 subgroups according to the pathologic stage. We employed the support vector machine, where linear kernels were leveraged to determine the optimal threshold to classify samples with different T stages. 90% of samples from each subgroup were randomly selected as the training set, while the remainder comprised the testing set.
The mean EWTs of the pT1, pT2, pT3 and pT4 subgroups were 4.9 ± 2.6 mm, 8.1 ± 2.3 mm, 12.4 ± 3.6 mm, and 18.6 ± 4.4 mm, respectively. Differences in the EWT between the four subgroups or between adjacent subgroups were significant (p < 0.001), and esophageal wall became thicker with increasing pT stage. We utilized MATLAB 2020a to implement the SVM model and ran the code 10 times. The accuracy of the model was 60.29 ± 2.33%. The thresholds between samples from pT1/pT2, pT2/pT3 and pT3/pT4 lesions were 5.5 ± 0.3 mm, 10.8 ± 0.8 mm and 15.9 ± 0.5 mm, respectively.
Possibility of predicting T stage of ESCC by EWT on CT scans was limited to 60% by model examination with large sample size.
CT 是食管癌（EC）分期最常用的方法。然而，报道的 EC CT T 分期标准存在争议。
确定并验证 CT 上食管壁厚度（EWT）的最佳阈值，以区分食管鳞癌（ESCC）患者不同 T 分期的病变。
回顾性分析 2014 年 7 月至 2020 年 4 月期间经病理证实的 1102 例连续 ESCC 患者。所有患者均行术前 CT 检查和手术治疗。测量病变的最大 EWT。根据病理分期，患者分为 pT1、pT2、pT3 和 pT4 亚组。我们采用支持向量机，利用线性核确定最佳阈值来分类不同 T 分期的样本。每个亚组的 90%的样本被随机选为训练集，其余的组成测试集。
pT1、pT2、pT3 和 pT4 亚组的平均 EWT 分别为 4.9±2.6mm、8.1±2.3mm、12.4±3.6mm 和 18.6±4.4mm。四个亚组之间或相邻亚组之间的 EWT 差异均有统计学意义（p<0.001），随着 pT 分期的增加，食管壁逐渐增厚。我们利用 MATLAB 2020a 实现 SVM 模型，并运行代码 10 次。模型的准确率为 60.29±2.33%。pT1/pT2、pT2/pT3 和 pT3/pT4 病变样本之间的阈值分别为 5.5±0.3mm、10.8±0.8mm 和 15.9±0.5mm。
利用大样本量的模型检查，通过 EWT 预测 ESCC T 分期的可能性仅为 60%。
