基于基因影像学方法的肝细胞癌预后影像标记物研究

发布时间：2018-04-30 16:18

  本文选题：肝细胞癌 + 基因影像学　； 参考：《航天医学与医学工程》2017年06期

【摘要】：目的通过肝细胞癌影像特征和基因模块关联的基因影像学方法,获取生物可解释的影像学标记物。方法从癌症基因组数据库获取371例肝细胞癌基因表达数据,其中37例有对应的术前增强CT数据。从勾画的肿瘤区域提取639维定量影像特征,基于一致性指数标准,筛选出12个影像特征。对肝细胞癌基因表达数据进行聚类,得到聚类基因模块,并与影像特征构建Spearman相关图,筛选出与基因模块关联的影像特征,最后用Cox回归模型评估其是否具有预后功能。结果 12个影像特征中,4个与预后的基因模块显著相关,3个与生存预后显著相关。其中,小波分量高灰度级小区域增强特征,与代表糖链生物合成的基因模块显著相关,且该影像特征与病人的总体生存周期(P=0.006,风险比=0.16)显著相关;低灰度级长游程增强纹理特征,与代表血管生成的基因模块显著相关,且与总体生存周期(P=0.049,风险比=3.21)显著相关。结论描述肿瘤小波频率和纹理的影像特征有可解释的生物学含义,并且与生存周期显著相关,这些特征可作为肝细胞癌潜在的影像学标记物。
[Abstract]:Objective to obtain biodegradable imaging markers from hepatocellular carcinoma (HCC) by genetic imaging method associated with gene module. Methods 371 hepatocellular carcinoma gene expression data were obtained from the cancer genome database, 37 of which had corresponding preoperative enhanced CT data. Six hundred and thirty-nine dimensional quantitative image features were extracted from the delineated tumor area, and 12 image features were selected based on the consistency index standard. After clustering the gene expression data of hepatocellular carcinoma, the cluster gene module was obtained, and the Spearman correlation map was constructed with the image features, and the image features associated with the gene module were screened out. Finally, the Cox regression model was used to evaluate whether the model had prognostic function. Results of the 12 imaging features, 4 were significantly correlated with prognostic gene modules, and 3 were significantly correlated with survival and prognosis. Among them, the enhancement feature of small region with high gray level of wavelet component was significantly correlated with the gene module representing the biosynthesis of sugar chain, and the feature of the image was significantly correlated with the patient's total life cycle (P0. 006) and the risk ratio (0. 16). Low gray level long run length enhanced texture features were significantly correlated with the gene modules that represented angiogenesis, and with the total life cycle of P0. 049 with a risk ratio of 3. 21). Conclusion the image features describing the wavelet frequency and texture of the tumor have explainable biological implications and are significantly related to the survival cycle. These features can be used as potential imaging markers for hepatocellular carcinoma.
【作者单位】： 上海大学通信与信息工程学院生物医学工程研究所;中国科学院苏州生物医学工程技术研究所;
【基金】：国家自然科学基金资助项目(81571772) 江苏省科技计划(BE2017671)
【分类号】：R735.7
，

本文编号：1825260