中国普外基础与临床杂志

中国普外基础与临床杂志

CT图像纹理分析鉴别不典型胰腺实性假乳头状肿瘤与胰腺导管腺癌的初步研究

查看全文

目的 探讨采用 CT 图像纹理分析鉴别不典型的胰腺实性假乳头状肿瘤(pancreatic solid pseudopapillary tumor,SPT)和胰腺导管腺癌(pancreatic ductal adenocarcinoma,PDAC)的可行性。 方法 回顾性分析四川大学华西医院经病理学检查证实的不典型 SPT(共计 26 个病灶)和 PDAC(共 52 个病灶)患者的 CT 资料。利用 ITK-Snap 软件于动脉期(arterial phase,AP)及门静脉期(portal venous phase,PVP)CT 图像上勾画三维(three-dimensional,3D)感兴趣区(region of interest,ROI),利用 A.K.软件(GE 公司,美国)自动提取 ROI 处的图像纹理特征。应用 R 软件行参数间的相关性分析以去除冗余的纹理特征后,剩余的纹理特征应用单因素及多因素二分类 logistic 回归筛选纹理特征,并建立回归模型。应用受试者工作特征(receiver operating characteristic,ROC)曲线分析比较纹理特征与模型鉴别不典型 SPT 及 PDAC 的诊断效能。 结果 共提取了 792 个纹理特征(AP 396 个,PVP 396 个),去冗余后剩余 61 个特征(AP 35 个,PVP 26 个)。二分类 logistic 回归分析选择出 2 个纹理特征为独立危险因素(AP 下为 MinIntensity,PVP 下为 Correlation_AllDirection_offset1_SD),其鉴别不典型的 SPT 和 PDAC 的灵敏度、特异度分别为 71.15%、76.92% 和 63.46%、76.92%,曲线下面积(AUC)分别为 0.740 和 0.754。应用上述 2 个纹理特征建立二分类 logistic 模型后,其模型灵敏度和特异度分别为 73.08% 及 80.77%,AUC 值为 0.796。2 个纹理特征和 logistic 模型的诊断效能比较差异无统计学意义(P>0.05)。 结论 CT 图像纹理分析鉴别不典型 SPT 与 PDAC 是可行的,具有中等的诊断效能。

Objective To access the diagnostic performance of CT texture analysis to differentiate atypical pancreatic solid pseudopapillary tumor (SPT) from pancreatic ductal adenocarcinoma (PDAC). Methods CT images of 26 patients with pathologically proved atypical SPT and 52 patients with PDAC were analyzed. 3D regions of interest (ROIs) on arterial phase (AP) and portal venous phase (PVP) images were drawn by ITK-Snap software. A.K. software (GE company, USA) was used to extract texture features for the discrimination of atypical SPT and PDAC. After removing redundancy (by a correlation analysis through R software), texture features were selected by single-factor and multi-factor logistic regression, and logistic regression model was finally established. Receiver operating characteristic (ROC) analysis was performed to assess the diagnostic performance of single texture feature and logistic model. Results A total of 792 texture features [396 of AP, 396 of PVP] from AP and PVP CT images were obtained by A.K. software. Of these, 61 texture features (35 of AP, 26 of PVP) were selected by R software (result of correlation analysis showed that correlation coefficient >0.7). Two texture features, including MinIntensity and Correlation_AllDirection_offset1_SD, were selected to establish logistic model. The sensitivity and specificity of these 2 texture features were 71.15% and 76.92%, 63.46% and 76.92% respectively, the area under curve ( AUC) were 0.740 and 0.754 respectively. The model’s sensitivity and specificity were 73.08% and 80.77% respectively, the AUC value was 0.796. There was no significance among the model, MinIntensity, and Correlation_AllDirection_offset1_SD (P>0.05). Conclusions CT texture analysis of 3D ROI is a quantitative method for differential diagnosis of atypical SPT from PDAC.

关键词: CT图像; 纹理分析; 胰腺实性假乳头状肿瘤; 胰腺导管腺癌

Key words: computer tomography image; texture analysis; pancreatic solid pseudopapillary tumor; pancreatic ductal adenocarcinoma

引用本文: 黄子星, 李谋, 于浩鹏, 汪翊, 宋彬. CT图像纹理分析鉴别不典型胰腺实性假乳头状肿瘤与胰腺导管腺癌的初步研究. 中国普外基础与临床杂志, 2018, 25(10): 1249-1253. doi: 10.7507/1007-9424.201809007 复制

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Huang HL, Shih SC, Chang WH, et al. Solid-pseudopapillary tumor of the pancreas: clinical experience and literature review. World J Gastroenterol, 2005, 11(9): 1403-1409.
2. Reddy S, Cameron JL, Scudiere J, et al. Surgical management of solid-pseudopapillary neoplasms of the pancreas (Franz or Hamoudi tumors): a large single-institutional series. J Am Coll Surg, 2009, 208(5): 950-957.
3. 朱碧云, 陈卉. 医学图像纹理分析的方法及应用. 中国医学装备, 2013, 10(8): 77-81.
4. Lubner MG, Smith AD, Sandrasegaran K, et al. CT texture analysis: definitions, applications, biologic correlates, and challenges. Radiographics, 2017, 37(5): 1483-1503.
5. Castellano G, Bonilha L, Li LM, et al. Texture analysis of medical images. Clin Radiol, 2004, 59(12): 1061-1069.
6. 潘立阳. 原发性肝癌相关因素1∶ 2病例对照研究. 大连: 大连医科大学, 2008.
7. 谢欢, 印隆林, 苟文枭, 等. 胰腺实性假乳头状瘤的CT和MRI表现. 中国普外基础与临床杂志, 2016, 23(4): 493-498.
8. 杨世平, 鲁昌立, 黄子星, 等. 胰腺实性假乳头状瘤的CT表现与病理对照(附8例分析). 中国普外基础与临床杂志, 2011, 18(1): 85-88.
9. 陈绍勤, 邹声泉, 李宏, 等. 胰腺实性假乳头状瘤与胰岛细胞瘤的临床病理对比研究. 中国普外基础与临床杂志, 2008, 15(11): 835-839.
10. 陈磊, 曹苇, 赵鑫, 等. 胰腺实性假乳头状瘤诊治分析(附8例报道). 中国普外基础与临床杂志, 2011, 18(7): 764-766.
11. 张益军, 翁永强, 袁祖荣. 胰腺实性假乳头状瘤临床治疗体会. 中国普外基础与临床杂志, 2010, 17(6): 611-612.
12. 李开宇, 徐福军, 徐雷. 胰腺实性假乳头状瘤的诊治进展. 中国普外基础与临床杂志, 2009, 16(5): 418-420.
13. 范俊, 郭肖陵, 李佽, 等. 胰腺实性假乳头状瘤2例报道. 中国普外基础与临床杂志, 2008, 15(5): 385-386.
14. 何贤禄, 张尚福, 卢强, 等. 胰腺实性假乳头状瘤的诊断与治疗. 中国普外基础与临床杂志, 2008, 15(8): 564-565.
15. 郝建朋, 姚俊超, 郭大伟, 等. 胰腺囊性肿瘤19例诊治分析. 中国普外基础与临床杂志, 2013, 20(11): 1295-1297.
16. 王亚军, 李非, 孙家邦, 等. 胰腺囊性肿瘤临床诊治分析. 中国普外基础与临床杂志, 2012, 19(4): 424-428.
17. 吴昕, 张立阳, 廖泉, 等. 胰腺实性假乳头状瘤再手术4例报道. 中国普外基础与临床杂志, 2012, 19(12): 1335-1337.
18. Lee ES, Lee JM. Imaging diagnosis of pancreatic cancer: a state-of-the-art review. World J Gastroenterol, 2014, 20(24): 7864-7877.
19. 任继亮, 吴颖为, 陶晓峰. 常规MRI纹理分析鉴别诊断眼眶淋巴瘤与炎性假瘤. 中国医学影像技术, 2017, 33(7): 980-984.
20. Chae HD, Park CM, Park SJ, et al. Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas. Radiology, 2014, 273(1): 285-293.
21. Dennie C, Thornhill R, Sethi-Virmani V, et al. Role of quantitative computed tomography texture analysis in the differentiation of primary lung cancer and granulomatous nodules. Quant Imaging Med Surg, 2016, 6(1): 6-15.
22. 刘露, 吴霜, 伍兵. CT图像纹理分析鉴别肝上皮样血管内皮瘤与结肠癌肝转移瘤的初步研究. 中国普外基础与临床杂志, 2018, 25(4): 483-487.
23. Ferreira Junior JR, Koenigkam-Santos M, Cipriano FEG, et al. Radiomics-based features for pattern recognition of lung cancer histopathology and metastases. Comput Methods Programs Biomed, 2018, 159: 23-30.
24. Weiss GJ, Ganeshan B, Miles KA, et al. Noninvasive image texture analysis differentiates K-ras mutation from pan-wildtype NSCLC and is prognostic. PLoS One, 2014, 9(7): e100244.
25. Fu XB, Hao ZQ, He JY, et al. Pathology comparative study on the characteristic CT signs in solid pseudopapillary neoplasm of the pancreas. Exp Ther Med, 2017, 13(6): 3523-3528.
26. Hackeng WM, Hruban RH, Offerhaus GJ, et al. Surgical and molecular pathology of pancreatic neoplasms. Diagn Pathol, 2016, 11(1): 47.
27. Esposito I, Konukiewitz B, Schlitter AM, et al. Pathology of pancreatic ductal adenocarcinoma: facts, challenges and future developments. World J Gastroenterol, 2014, 20(38): 13833-13841.