CT纹理分析在鉴别胰腺浆液性囊腺瘤与黏液性囊腺瘤中的价值-东南大学学报医学版

CT纹理分析在鉴别胰腺浆液性囊腺瘤与黏液性囊腺瘤中的价值

单位：南京大学医学院附属鼓楼医院核医学科, 江苏南京 210008

分类号：R735.9;R814.42

出版年·卷·期（页码）：2022·41·第三期（308-316）

摘要：

目的：探讨术前CT纹理分析在鉴别胰腺浆液性囊腺瘤（SCN）与黏液性囊腺瘤（MCN）中的价值。方法：回顾性分析46例SCN与29例MCN患者的资料，基于术前CT静脉期图像，用半自动分割技术提取肿瘤全容积纹理特征，使用单因素分析、LASSO算法及Logistic回归分析筛选独立预测因子并构建CT纹理特征模型、临床影像学特征模型及综合模型（基于临床影像学特征和纹理特征），使用受试者工作特征（ROC）曲线及曲线下面积（AUC）分析诊断性能。结果：临床影像学特征模型AUC为0.814，CT纹理特征模型AUC为0.866，综合模型AUC为0.938，综合模型诊断性能优于单一CT纹理特征模型。结论：CT纹理分析有助于SCN及MCN的术前鉴别诊断，联合临床影像学特征可以进一步提高诊断效能。

Objective: To explore the value of CT texture analysis in preoperatively differentiating pancreatic serous cystadenoma(SCN) from mucinous cystadenoma(MCN). Methods: Forty six patients with SCN and 29 patients with MCN were analyzed retrospectively. Based on the preoperative CT venous phase images, the full-volume tumor texture features were extracted by the semi-automatic segmentation technique. Univariate analysis, LASSO regression analysis and Logistic regression analysis were applied to select independent predictors and develop a clinical radiological feature model, a CT textural feature model and a combined model(based on clinical radiological features and textural features). The diagnosis efficiency of those models was evaluated by receiver operating characteristic(ROC) curve and the area under the curve(AUC). Results: AUC of CT textural feature and clinical radiological feature model respectively was 0.866 and 0.814. The combined model yielded an AUC of 0.938, which had the better performance than CT textural feature model. Conclusion: CT texture analysis is helpful in the differential diagnosis of SCN and MCN preoperatively; when combined with clinical radiological features, it can further improve the diagnosis efficiency.

参考文献：

[1] YEH T,JAN Y,CHIU C,et al.Characterisation of oestrogen receptor,progesterone receptor,trefoil factor 1,and epidermal growth factor and its receptor in pancreatic cystic neoplasms and pancreatic ductal adenocarcinoma[J].Gut,2002,51(5):712-716.
[2] VALSANGKAR N P,MORALES-OYARVIDE V,THAYER S P,et al.851 resected cystic tumors of the pancreas:a 33-year experience at the Massachusetts General Hospital[J].Surgery,2012,152(3):S4-S12.
[3] JAIS B,REBOURS V,MALLEO G,et al.Serous cystic neoplasm of the pancreas:a multinational study of 2622 patients under the auspices of the International Association of Pancreatology and European Pancreatic Club(European Study Group on Cystic Tumors of the Pancreas)[J].Gut,2016,65(2):305-312.
[4] POSTLEWAIT L M,ETHUN C G,MCINNIS M R,et al.Association of preoperative risk factors with malignancy in pancreatic mucinous cystic neoplasms[J].JAMA Surg, 2017,152(1):19-25.
[5] TANAKA M,FERNÁNDEZ-DEL CASTILLO C,ADSAY V,et al.International consensus guidelines 2012 for the management of IPMN and MCN of the pancreas[J].Pancreatology, 2012,12(3):183-197.
[6] 陈朝晖.胰腺浆液性囊腺瘤与黏液性囊腺瘤的CT表现分析[J].中国中西医结合影像学杂志,2018,16(1):67-68.
[7] CHO C S,RUSS A J,LOEFFLER A G,et al.Preoperative classification of pancreatic cystic neoplasms:the clinical significance of diagnostic inaccuracy[J].Ann Surg Oncol,2013,20(9):3112-3119.
[8] 吴文川.中国胰腺囊性肿瘤外科诊治现状分析:2251例报告[J].中华外科杂志,2018,56(1):24-29.
[9] 雷爱春,杨殿香,李光芒,等.CT影像纹理分析对肺磨玻璃样小结节良恶性的鉴别诊断[J].现代医学,2021,49(9):1075-1079.
[10] 吴宇强,靳激扬,冯银波.甲状腺意外结节增强CT的纹理特征分析对良恶性鉴别的价值研究[J].东南大学学报(医学版),2016,35(1):112-116.
[11] KIM B R,KIM J H,AHN S J,et al.CT prediction of resectability and prognosis in patients with pancreatic ductal adenocarcinoma after neoadjuvant treatment using image findings and texture analysis[J].Eur Radiol,2019,29(1):362-372.
[12] BELEÙ A,RIZZO G,DE ROBERTIS R,et al.Liver tumor burden in pancreatic neuroendocrine tumors:CT features and texture analysis in the prediction of tumor grade and 18F-FDG uptake[J].Cancers,2020,12(6):1486.
[13] LV P,MAHYOUB R,LIN X,et al.Differentiating pancreatic ductal adenocarcinoma from pancreatic serous cystadenoma,mucinous cystadenoma,and a pseudocyst with detailed analysis of cystic features on CT scans:a preliminary study[J].Korean J Radiol,2011,12(2):187-195.
[14] MA J,HE J,YANG X.Learning geodesic active contours for embedding object global information in segmentation CNNs[J].IEEE Trans Med Imaging,2021,40(1):93-104.
[15] VAN GRIETHUYSEN J J M,FEDOROV A,PARMAR C,et al.Computational radiomics system to decode the radiographic phenotype[J].Cancer Res,2017,77(21):e104-e107.
[16] YANG J,GUO X,ZHANG H,et al.Differential diagnosis of pancreatic serous cystadenoma and mucinous cystadenoma:utility of textural features in combination with morphological characteristics[J].BMC Cancer,2019,19(1):1223
[17] YANG J,GUO X,OU X,et al.Discrimination of pancreatic serous cystadenomas from mucinous cystadenomas with CT textural features:based on machine learning[J].Front Oncol,2019,9:494.
[18] XIE H,MA S,GUO X,et al.Preoperative differentiation of pancreatic mucinous cystic neoplasm from macrocystic serous cystic adenoma using radiomics:preliminary findings and comparison with radiological model[J].Eur J Radiol,2020,122:108747.
[19] XIE T,WANG X,ZHANG Z,et al.CT-based radiomics analysis for preoperative diagnosis of pancreatic mucinous cystic neoplasm and atypical serous cystadenomas[J].Front Oncol,2021,11:621520.
[20] GUO J,LI Z,QU X,et al.Value of MRI-based radiomics analysis for differentiation of benign and malignant epithelial neoplasms in the lacrimal gland:a retrospective study[J].Acta Radiol,2021,62(6):743-751.
[21] NAGANAWA S,KIM J,YIP S S F,et al.Texture analysis of T2-weighted MRI predicts SDH mutation in paraganglioma[J].Neuroradiology,2021,63(4):547-554.
[22] 王波涛,何蕾,刘刚,等.磁共振成像纹理特征分析在胰腺浆液性囊腺瘤及黏液性囊腺瘤鉴别诊断中的价值[J].中国医学科学院学报,2018,40(2):187-193.
[23] HA S,CHOI H,CHEON G J,et al.Autoclustering of non-small cell lung carcinoma subtypes on 18F-FDG PET using texture analysis:a preliminary result[J].Nucl Med Mol Imaging,2014,48(4):278-286.
[24] 吴梦龙.胰腺浆液性微囊型囊腺瘤的影像学及病理对照分析[J].中国中西医结合影像学杂志,2019,17(1):41-43.
[25] 洪理文,赵治锋,张俊,等.胰腺囊性肿瘤术前恶性预测(附342例报告)[J].外科理论与实践,2017,22(2):134-138.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录