生物医学工程学杂志

生物医学工程学杂志

基于影像组学预测胰腺囊性肿瘤 Ki67 分子标记物的可行性研究

查看全文

本文基于影像组学预测胰腺囊性肿瘤(PCN)的 Ki67 分子标记物表达情况。首先手动分割患者术前多排螺旋断层扫描(MDCT)图像中的肿瘤区域,然后根据肿瘤特点设计并提取 409 个高通量特征,再利用最小化的绝对收缩与选择算子(LASSO)回归模型进行多因素分析筛选特征,最后将筛选后的特征输入支持向量机(SVM)实现分类判别。通过重复 200 次 LASSO 筛选,记录每次被选择的特征,并将特征按照被选择的次数从高到低排序。使用十折交叉验证的 SVM,测试不同的特征数量下的分类效果,重复 200 次并将结果取平均值以降低误差。实验结果表明,被选择次数最多的前 20 个特征构成最优特征子集,预测的 AUC 达到 91.54%,准确率达到 85.29%,敏感度为 81.88%,特异性为 86.75%。实验结果证明了通过影像组学方法预测 Ki67 分子标记物的可行性。

This study aims to predict expression of Ki67 molecular marker in pancreatic cystic neoplasm using radiomics. We firstly manually segmented tumor area in multi-detector computed tomography (MDCT) images. Then 409 high-throughput features were automatically extracted and the least absolute shrinkage selection operator (LASSO) regression model was used for feature selection. After 200 bootstrapping repetitions of LASSO, 20 most frequently selected features made up the optimal feature set. Then 200 bootstrapping repetitions of support vector machine (SVM) classifier with 10-fold cross-validation were used to avoid overfitting and accurately predict the Ki67 expression. The highest prediction accuracy could achieve 85.29% and the highest area under the receiver operating characteristic curve (AUC) was 91.54% with a sensitivity (SENS) of 81.88% and a specificity (SPEC) of 86.75%. According to the results of experiment, the feasibility of predicting expression of Ki67 in pancreatic cystic neoplasm based on radiomics was verified.

关键词: 影像组学; 胰腺囊性肿瘤; 多排螺旋计算机断层成像; Ki67 分子标记物

Key words: radiomics; pancreatic cystic neoplasms; multi-detector computed tomography; Ki67 molecular marker

登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Rahib L, Smith B D, Aizenberg R, et al. Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States. Cancer Res, 2014, 74(11): 2913-2921.
2. Galanis C, Zamani A, Cameron J L, et al. Resected serous cystic neoplasms of the pancreas: a review of 158 patients with recommendations for treatment. J Gastrointest Surg, 2007, 11(7): 820-826.
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). Gut, 2015, 65(2): 305-312.
4. Sawhney M S, Al-Bashir S, Cury M S, et al. International consensus guidelines for surgical resection of mucinous neoplasms cannot be applied to all cystic lesions of the pancreas. Clin Gastroenterol Hepatol, 2009, 7(12): 1373-1376.
5. 陈梦云, 张翠翠, 轩菡, 等. Ki67 在肿瘤中的表达及其临床指导意义. 现代生物医学进展, 2015, 15(16): 3193-3196.
6. 何淑蓉, 崔娣, 宫环, 等. 以 Ki-67 阳性指数行胰腺神经内分泌肿瘤细针穿刺细胞学分级及其与组织学分级的比较. 中华病理学杂志, 2017, 46(6): 393-399.
7. 庞旭峰, 王祖森, 吴力群. Ki-67 在肝细胞肝癌患者根治性肝切除术后短期肿瘤复发预测中的价值. 中华肝脏外科手术学电子杂志, 2012, 1(2): 123-128.
8. Sainani N I, Saokar A, Deshpande V, et al. Comparative performance of MDCT and MRI with MR cholangiopancreatography in characterizing small pancreatic cysts. AJR Am J Roentgenol, 2009, 193(3): 722-731.
9. Kickingereder P, Götz M, Muschelli J, et al. Large-scale radiomic profiling of recurrent glioblastoma identifies an imaging predictor for stratifying anti-angiogenic treatment response. Clin Cancer Res, 2016, 22(23): 5765-5771.
10. Guo Yi, Hu Yuzhou, Qiao Mengyun, et al. Radiomics analysis on ultrasound for prediction of biologic behavior in breast invasive ductal carcinoma. Clin Breast Cancer, 2018, 18(3): E335-E344.
11. 刘桐桐, 李佳伟, 胡雨舟, 等. 基于影像组学预测乳腺癌雌激素受体表达情况的可行性分析. 生物医学工程学杂志, 2017, 34(4): 597-601.
12. Cameron A, Khalvati F, Haider M A, et al. MAPS: A quantitative radiomics approach for prostate Cancer detection. IEEE Trans Biomed Eng, 2016, 63(6): 1145-1156.
13. 胡玉川, 张欣, 崔光彬. 影像组学在肺癌中的应用研究进展. 放射学实践, 2017, 32(12): 1239-1241.
14. Permuth J B, Choi J, Balarunathan Y, et al. Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms. Oncotarget, 2016, 7(52): 85785-85797.
15. Sahani D V, Kambadakone A, Macari M, et al. Diagnosis and management of cystic pancreatic lesions. Am J Roentgenol, 2013, 200(2): 343-354.
16. Cohen-Scali F, Vilgrain V, Brancatelli G, et al. Discrimination of unilocular macrocystic serous cystadenoma from pancreatic pseudocyst and mucinous cystadenoma with CT: initial observations. Radiology, 2003, 228(3): 727-733.
17. Li Chao, Lin Xiaozhu, Hui Chun, et al. Computer-aided diagnosis for distinguishing pancreatic mucinous cystic neoplasms from serous oligocystic adenomas in spectral CT images. Technol Cancer Res Treat, 2016, 15(1): 44-54.
18. Lv Peijie, Mahyoub R, Lin Xiaozhu, 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. Korean J Radiol, 2011, 12(2): 187-195.
19. Zhao Peng, Yu Bin. On model selection consistency of lasso. J Mach Learn Res, 2006, 7(12): 2541-2563.