Department of Biotherapy, Cancer Center, State Key Laboratory of Biotherapy, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu, 610041, People's Republic of China.
West China School of Medicine, West China Hospital, Sichuan University, Chengdu, 610041, People's Republic of China.
BMC Cancer. 2019 Dec 16;19(1):1223. doi: 10.1186/s12885-019-6421-7.
Texture analysis of medical images has been reported to be a reliable method for differential diagnosis of neoplasms. This study was to investigate the performance of textural features and the combined performance of textural features and morphological characteristics in the differential diagnosis of pancreatic serous and mucinous cystadenomas.
We retrospectively reviewed 59 patients with pancreatic serous cystadenoma and 32 patients with pancreatic mucinous cystadenoma at our hospital. A three-dimensional region of interest (ROI) around the margin of the lesion was drawn manually in the CT images of each patient, and textural parameters were retrieved from the ROI. Textural features were extracted using the LifeX software. The least absolute shrinkage and selection operator (LASSO) method was applied to select the textural features. The differential diagnostic capabilities of morphological features, textural features, and their combination were evaluated using receiver operating characteristic (ROC) analysis, and the area under the receiver operating characteristic curve (AUC) was used as the main indicator. The diagnostic accuracy based on the AUC value is defined as follows: 0.9-1.0, excellent; 0.8-0.9, good; 0.7-0.8, moderate; 0.6-0.7, fair; 0.5-0.6, poor.
In the differential diagnosis of pancreatic serous and mucinous cystadenomas, the combination of morphological characteristics and textural features (AUC 0.893, 95% CI 0.816-0.970) is better than morphological characteristics (AUC 0.783, 95% CI 0.665-0.900) or textural features (AUC 0.777, 95% CI 0.673-0.880) alone.
In conclusion, our preliminary results highlighted the potential of CT texture analysis in discriminating pancreatic serous cystadenoma from mucinous cystadenoma. Furthermore, the combination of morphological characteristics and textural features can significantly improve the diagnostic performance, which may provide a reliable method for selecting patients with surgical intervention indications in consideration of the different treatment principles of the two diseases.
医学图像纹理分析已被报道为鉴别肿瘤的可靠方法。本研究旨在探讨纹理特征及其与形态学特征联合在鉴别胰腺浆液性和黏液性囊腺瘤中的性能。
我们回顾性分析了我院 59 例胰腺浆液性囊腺瘤和 32 例胰腺黏液性囊腺瘤患者的资料。每位患者的 CT 图像上均手动勾画病变边缘的三维感兴趣区(ROI),并从 ROI 中提取纹理参数。使用 LifeX 软件提取纹理特征。采用最小绝对值收缩和选择算子(LASSO)方法选择纹理特征。采用受试者工作特征(ROC)分析评价形态学特征、纹理特征及其联合的鉴别诊断能力,以ROC 曲线下面积(AUC)作为主要指标。基于 AUC 值的诊断准确性定义如下:0.9-1.0,优秀;0.8-0.9,良好;0.7-0.8,中等;0.6-0.7,尚可;0.5-0.6,差。
在鉴别胰腺浆液性和黏液性囊腺瘤时,形态学特征联合纹理特征(AUC 0.893,95%CI 0.816-0.970)的诊断效能优于形态学特征(AUC 0.783,95%CI 0.665-0.900)或纹理特征(AUC 0.777,95%CI 0.673-0.880)单独使用。
初步结果表明 CT 纹理分析在鉴别胰腺浆液性囊腺瘤和黏液性囊腺瘤方面具有一定潜力。此外,形态学特征联合纹理特征可显著提高诊断效能,这可能为考虑两种疾病不同治疗原则选择具有手术干预指征的患者提供一种可靠方法。