基于影像组学方法术前预测结直肠癌淋巴血管侵犯  

Preoperative Prediction of Lymphovascular Invasion of Colorectal Cancer Based on Radiomics Approach

作　　者：梁翠珊 黄燕琪[2] 何兰[2,3] 黄晓媚 程梓轩 刘再毅 LIANG Cuishan;HUANG Yanqi;HE Lan;HUANG Xiaomei;CHENG Zixuan;LIU Zaiyi(Department of Radiology,Guangdong General Hospital,Guangdong Academy of Medical Sciences,Guangzhou 510080,China)

机构地区：[1]南方医科大学研究生院,广东广州510515 [2]广东省人民医院,广东省医学科学院放射科,广东广州510080 [3]华南理工大学医学院,广东广州510006

出　　处：《中国医学影像学杂志》2018年第3期191-196,201,共7页Chinese Journal of Medical Imaging

基　　金：国家重点研究发展计划资助(2017YFC1309100); 国家自然科学基金(81771912,81701782,81601469)

摘　　要：目的淋巴血管侵犯(LVI)是影响结直肠癌预后的危险因素,治疗前评价淋巴血管状态有重要价值。本研究拟基于影像组学方法术前预测结直肠癌LVI。资料与方法从回顾性收集的结直肠癌术前CT图像中提取影像组学特征,并构建影像组学标签。评估影像组学标签的预测效能,并对其预测效能进行内部验证。联合具有独立预测效能的临床因素与影像组学标签,建立联合预测因子,并评价其预测效能。结果由58个影像组学特征构成的影像组学标签与LVI状态有关(P<0.0001)。构建的影像组学标签显示了较好的辨别能力[一致性指数(C-index)为0.719,95%CI 0.715～0.723]及分类能力(敏感度为0.726,特异度为0.628),内部验证(C-index为0.720)。包含影像组学标签及癌胚抗原的联合预测因子进一步提高了影像组学标签的预测能力(C-index为0.751,敏感度为0.788,特异度为0.667)。结论本研究构建的影像组学标签可于术前个体化预测结直肠癌患者的LVI状态。联合临床危险因素后的联合预测因子进一步提高了预测效能。Purpose Lymph-vascular invasion（LVI） is a risk factor for the prognosis of colorectal cancer, and it is of great value to evaluate the status of lymphatic vessels before treatment. This study aims to predict colorectal cancer LVI preoperatively based on radiomics. Materials and Methods Radiomics features were extracted from preoperative CT images of colorectal cancer retrospectively collected and radiomics labels were constructed. The predictive efficacy of radiomics labels were assessed and internally verified. Joint predictive factors were established by combining clinical factors with independent predictive efficacy and radiomics labels, and their predictive efficacy was evaluated. Results Radiomics labels consisted of 58 radiomics features were correlated with LVI status（P0.0001） with the former showing good discrimination ability [C-index 0.719, 95% CI： 0.715-0.723] and classification ability（sensitivity 0.726, specificity 0.628） with internal validation（C-index 0.720）. Joint predictive factors containing radiomics labels and carcinoembryonic antigen further enhanced the predictability of radiomics labels（C-index 0.751, sensitivity 0.788, specificity 0.667）. Conclusion The radiomics labels built in this study can provide individualized prediction of LVI status of patients with colorectal cancer before surgery. Joint predictive factors in combination with clinical risk factors further improved predictive efficacy.

关 键 词：结直肠肿瘤 淋巴 血管 体层摄影术 螺旋计算机 图像处理 计算机辅助 预测 影像组学 

分 类 号：R735.35[医药卫生—肿瘤]