解剖学报

解剖学报 ›› 2019, Vol. 50 ›› Issue (4): 495-500.doi: 10.16098/j.issn.0529-1356.2019.04.015

• 解剖学 • 上一篇    下一篇

基于影像组学的肺癌分型预测

梁伟1* 赵艳秋2 桂东奇3 丁小凤1   

  1. 1.安徽医科大学第一附属医院肿瘤放疗科， 合肥 230022; 2.合肥市第二人民医院广德路院区医院老年医学科， 合肥 230000; 3.中国科学技术大学电子科学与技术系， 合肥 230027
  • 收稿日期:2019-04-01 修回日期:2019-05-15 出版日期:2019-08-06 发布日期:2019-08-06
  • 通讯作者: 梁伟 E-mail:34316801@qq.com

Prediction of lung cancer typing based on radiomics

 LIANG Wei 1* ZHAO Yan-qiu2 GUI Dong-qi3 DING Xiao-feng1   

  1. 1.Department of Radiology Oncology, the First Affiliated Hospital，An’ hui Medical University, Hefei 230022, China; 2.Department of Geriatrics the Second People’s Hospital of Hefei, Hefei 230000, China; 3.Department of Electronic Science and Technology，University of Science and Technology of China， Hefei 230027, China
  • Received:2019-04-01 Revised:2019-05-15 Online:2019-08-06 Published:2019-08-06
  • Contact: LIANG Wei E-mail:34316801@qq.com

PDF

摘要：

目的 基于影像组学特征对肺癌中的两大亚型分类（小细胞肺癌与非小细胞肺癌）进行分型预测。 方法 在131名小细胞肺癌与非小细胞肺癌患者中(其中训练集包含119人，测试集中包含12人)，从手动分割的病灶区域提取107维组学特征，使用R统计学软件中的FSelector包对影像组学特征进行关键特征筛选，构建支持向量机模型和k折交叉验证模型对肺癌患者的病理进行表型分类和验证，通过绘制受试者工作特征曲线（ROC曲线）图和计算曲线下面积（AUC）数值来对训练集和测试集中的肺癌分型预测效果进行评估。 结果 挑选出20个主要的影像组学特征用于小细胞肺癌与非小细胞肺癌的分型鉴别，这些特征对于训练集和测试集中的小细胞肺癌与非小细胞肺癌均有较好的区分能力。在测试集中，预肺癌亚型分类的准确率为75%，组学特征的AUC结果为0.69。 结论 通过构建独特的影像组学特征，以用作区分小细胞肺癌与非小细胞肺癌的诊断因素。这对实现非侵入性的肺癌病理有效分型预测，指导肺癌患者后续治疗方案的选择具有重要指导意义。

关键词: 影像组学, 肺癌, 支持向量机, k折交叉验证, 分型预测, 人

Abstract:

Objective To predict the classification of small cell lung cancer and nonsmall cell lung cancer based on Radiomics. Methods This study involved 131 patients with small cell lung cancer and non-small cell lung cancer (including 119 in the training cohort and 12 in the validation cohort). The 107-dimensional omics features were extracted from the manually segmented lesions. The FSelector package in R statistical software was used to screen the key features of the phenomenological features. The support vector machines model and the k-fold cross-validation model were used to classify the pathology of lung cancer patients. The effect of lung cancer typing prediction in the training cohort and validation cohort was evaluated by plotting the receiver operating characteristic curve(ROC) and calculating the area under curve(AUC) values. Results This study selected 20 major Radiomics features for the differential diagnosis of small cell lung cancer and non-small cell lung cancer. These features were well differentiated between small cell lung cancer and non-small cell lung cancer in the training cohort and validation cohort. In the validation cohort, the accuracy of the pre-lung cancer subtype classification was 75%, and the AUC result of the radiomics characteristics was 0.69. Conclusion This paper constructs a unique radiomics feature to be used as a diagnostic factor for distinguishing between small cell lung cancer and nonsmall cell lung cancer, which has important guiding significance for the realization of non-invasive pathologically effective classification of lung cancer and guiding the selection of follow-up treatment options for lung cancer patients.

Key words: Radiomics, Lung cancer, Support vector machine, k-fold cross-validation, Typing prediction, Human