Objective 

The aim of the study is to investigate the value of computed tomography (CT) radiomics features to discriminate the liver metastases (LMs) of digestive system neuroendocrine tumors (NETs) from neuroendocrine carcinoma (NECs).

Methods 

Ninety-nine patients with LMs of digestive system neuroendocrine neoplasms from 2 institutions were included. Radiomics features were extracted from the portal venous phase CT images by the Pyradiomics and then selected by using the t test, Pearson correlation analysis, and least absolute shrinkage and selection operator method. The radiomics score (Rad score) for each patient was constructed by linear combination of the selected radiomics features. The radiological model was constructed by radiological features using the multivariable logistic regression. Then, the combined model was constructed by combining Rad score and the radiological model into logistic regression. The performance of all models was evaluated by the receiver operating characteristic curves with the area under curve (AUC).

Results 

In the radiological model, only the enhancement degree (odds ratio, 8.299; 95% confidence interval, 2.070–32.703; P = 0.003) was an independent predictor for discriminating the LMs of digestive system NETs from those of NECs. The combined model constructed by the Rad score in combination with the enhancement degree showed good discrimination performance, with AUCs of 0.893, 0.841, and 0.740 in the training, testing, and external validation groups, respectively. In addition, it performed better than radiological model in the training and testing groups (AUC, 0.893 vs 0.726; AUC, 0.841 vs 0.621).

Conclusions 

The CT radiomics might be useful for discrimination LMs of digestive system NECs from NETs.

中文翻译：

---

基于计算机断层扫描的放射组学分析区分消化系统神经内分泌肿瘤和神经内分泌癌的肝转移

客观的 

该研究的目的是探讨计算机断层扫描（CT）放射组学特征在区分消化系统神经内分泌肿瘤（NET）和神经内分泌癌（NEC）的肝转移（LM）方面的价值。

方法 

纳入来自2家机构的99例消化系统神经内分泌肿瘤LM患者。通过Pyradiomics从门静脉期CT图像中提取放射组学特征，然后使用t检验、Pearson相关分析、最小绝对收缩和选择算子方法选择放射组学特征。通过所选放射组学的线性组合构建每位患者的放射组学评分（Rad 评分）特征。使用多变量逻辑回归根据放射学特征构建放射学模型。然后，将Rad评分和放射学模型结合到逻辑回归中构建组合模型。所有模型的性能均通过受试者工作特征曲线和曲线下面积（AUC）进行评估。

结果 

在放射学模型中，只有增强程度（比值比，8.299；95% 置信区间，2.070-32.703；P = 0.003）是区分消化系统 NET 的 LM 与 NEC 的独立预测因子。Rad评分结合增强度构建的组合模型表现出良好的判别性能，训练组、测试组和外部验证组的AUC分别为0.893、0.841和0.740。此外，它在训练组和测试组中的表现优于放射学模型（AUC，0.893 vs 0.726；AUC，0.841 vs 0.621）。

结论 

CT放射组学可能有助于区分消化系统 NEC 和 NET 的 LM。