Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China.
Department of Pharmaceutical Diagnostics, General Electric Company Healthcare, Beijing 100176, China.
World J Gastroenterol. 2022 Aug 21;28(31):4363-4375. doi: 10.3748/wjg.v28.i31.4363.
The biological behavior of carcinoma of the esophagogastric junction (CEGJ) is different from that of gastric or esophageal cancer. Differentiating squamous cell carcinoma of the esophagogastric junction (SCCEG) from adenocarcinoma of the esophagogastric junction (AEG) can indicate Siewert stage and whether the surgical route for patients with CEGJ is transthoracic or transabdominal, as well as aid in determining the extent of lymph node dissection. With the development of neoadjuvant therapy, preoperative determination of pathological type can help in the selection of neoadjuvant radiotherapy and chemotherapy regimens.
To establish and evaluate computed tomography (CT)-based multiscale and multiphase radiomics models to distinguish SCCEG and AEG preoperatively.
We retrospectively analyzed the preoperative contrasted-enhanced CT imaging data of single-center patients with pathologically confirmed SCCEG ( = 130) and AEG ( = 130). The data were divided into either a training ( = 182) or a test group ( = 78) at a ratio of 7:3. A total of 1409 radiomics features were separately extracted from two dimensional (2D) or three dimensional (3D) regions of interest in arterial and venous phases. Intra-/inter-observer consistency analysis, correlation analysis, univariate analysis, least absolute shrinkage and selection operator regression, and backward stepwise logical regression were applied for feature selection. Totally, six logistic regression models were established based on 2D and 3D multi-phase features. The receiver operating characteristic curve analysis, the continuous net reclassification improvement (NRI), and the integrated discrimination improvement (IDI) were used for assessing model discrimination performance. Calibration and decision curves were used to assess the calibration and clinical usefulness of the model, respectively.
The 2D-venous model (5 features, AUC: 0.849) performed better than 2D-arterial (5 features, AUC: 0.808). The 2D-arterial-venous combined model could further enhance the performance (AUC: 0.869). The 3D-venous model (7 features, AUC: 0.877) performed better than 3D-arterial (10 features, AUC: 0.876). And the 3D-arterial-venous combined model (AUC: 0.904) outperformed other single-phase-based models. The venous model showed a positive improvement compared with the arterial model (NRI > 0, IDI > 0), and the 3D-venous and combined models showed a significant positive improvement compared with the 2D-venous and combined models ( < 0.05). Decision curve analysis showed that combined 3D-arterial-venous model and 3D-venous model had a higher net clinical benefit within the same threshold probability range in the test group.
The combined arterial-venous CT radiomics model based on 3D segmentation can improve the performance in differentiating EGJ squamous cell carcinoma from adenocarcinoma.
食管胃结合部癌（EGJ）的生物学行为不同于胃癌或食管癌。区分食管胃结合部鳞状细胞癌（SCCEG）和食管胃结合部腺癌（AEG）可以提示 Siewert 分期，以及患者 EGJ 的手术路径是经胸还是经腹，还可以帮助确定淋巴结清扫的范围。随着新辅助治疗的发展，术前确定病理类型有助于选择新辅助放化疗方案。
建立并评估基于 CT 的多尺度、多期影像组学模型，以术前区分 SCCEG 和 AEG。
我们回顾性分析了单中心经病理证实的 SCCEG（n=130）和 AEG（n=130）患者术前增强 CT 成像数据。数据以 7:3 的比例分为训练组（n=182）和测试组（n=78）。分别从动脉期和静脉期二维（2D）或三维（3D）感兴趣区提取 1409 个影像组学特征。采用组内/组间一致性分析、相关性分析、单因素分析、最小绝对收缩和选择算子回归以及向后逐步逻辑回归进行特征选择。基于 2D 和 3D 多期特征共建立了 6 个逻辑回归模型。受试者工作特征曲线分析、连续净重新分类改善（NRI）和综合判别改善（IDI）用于评估模型的判别性能。校准和决策曲线分别用于评估模型的校准和临床实用性。
2D-静脉模型（5 个特征，AUC：0.849）的性能优于 2D-动脉模型（5 个特征，AUC：0.808）。2D-动脉-静脉联合模型可以进一步提高性能（AUC：0.869）。3D-静脉模型（7 个特征，AUC：0.877）的性能优于 3D-动脉模型（10 个特征，AUC：0.876）。3D-动脉-静脉联合模型（AUC：0.904）优于其他单期模型。与动脉模型相比，静脉模型的改善呈阳性（NRI>0，IDI>0），与 2D-静脉和联合模型相比，3D-静脉和联合模型的改善呈显著阳性（<0.05）。决策曲线分析表明，在测试组相同阈值概率范围内，联合 3D-动脉-静脉模型和 3D-静脉模型具有更高的净临床获益。
基于 3D 分割的联合动脉-静脉 CT 影像组学模型可以提高区分 EGJ 鳞状细胞癌和腺癌的性能。
