Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Department of Gastrointestinal Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Biomed Res Int. 2021 Apr 2;2021:5519144. doi: 10.1155/2021/5519144. eCollection 2021.
To explore the application of computed tomography (CT) texture analysis in differentiating lymphomas from other malignancies of the small bowel.
Arterial and venous CT images of 87 patients with small bowel malignancies were retrospectively analyzed. The subjective radiological features were evaluated by the two radiologists with a consensus agreement. The region of interest (ROI) was manually delineated along the edge of the lesion on the largest slice, and a total of 402 quantified features were extracted automatically from AK software. The inter- and intrareader reproducibility was evaluated to select highly reproductive features. The univariate analysis and minimum redundancy maximum relevance (mRMR) algorithm were applied to select the feature subsets with high correlation and low redundancy. The multivariate logistic regression analysis based on texture features and radiological features was employed to construct predictive models for identification of small bowel lymphoma. The diagnostic performance of multivariate models was evaluated using receiver operating characteristic (ROC) curve analysis.
The clinical data (age, melena, and abdominal pain) and radiological features (location, shape, margin, dilated lumen, intussusception, enhancement level, adjacent peritoneum, and locoregional lymph node) differed significantly between the nonlymphoma group and lymphoma group ( < 0.05). The areas under the ROC curve of the clinical model, arterial texture model, and venous texture model were 0.93, 0.92, and 0.87, respectively.
The arterial texture model showed a great diagnostic value and fitted performance in preoperatively discriminating lymphoma from nonlymphoma of the small bowel.
探讨 CT 纹理分析在鉴别小肠淋巴瘤与其他恶性肿瘤中的应用。
回顾性分析 87 例小肠恶性肿瘤患者的动脉期和静脉期 CT 图像。两名放射科医生通过共识协议评估主观放射学特征。在最大层面上手动勾画病变边缘的感兴趣区（ROI），并从 AK 软件中自动提取 402 个定量特征。评估了组内和组间的可重复性，以选择高重复性特征。应用单变量分析和最小冗余最大相关性（mRMR）算法选择具有高相关性和低冗余性的特征子集。基于纹理特征和放射学特征的多元逻辑回归分析用于构建用于识别小肠淋巴瘤的预测模型。使用接收者操作特征（ROC）曲线分析评估多元模型的诊断性能。
非淋巴瘤组和淋巴瘤组之间的临床数据（年龄、黑便和腹痛）和放射学特征（位置、形状、边界、扩张的管腔、肠套叠、强化水平、相邻腹膜和局部区域淋巴结）存在显著差异（<0.05）。临床模型、动脉纹理模型和静脉纹理模型的 ROC 曲线下面积分别为 0.93、0.92 和 0.87。
动脉纹理模型在术前鉴别小肠淋巴瘤与非淋巴瘤中具有很好的诊断价值和拟合性能。
