Pre-treatment ADC image-based random forest classifier for identifying resistant rectal adenocarcinoma to neoadjuvant chemoradiotherapy
Pre-treatment ADC image-based random forest classifier for identifying resistant rectal adenocarcinoma to neoadjuvant chemoradiotherapy
复制标题
基于预处理 ADC 图像的随机森林分类器，用于识别对新辅助放化疗耐药的直肠腺癌
DOI：
10.1007/s00384-019-03455-3
复制
发表时间：
2019-12-01
影响因子：
2.8
通讯作者：
Zeng, Meng-Su
中科院分区：
文献类型：
--
作者：
Yang, Chun;Jiang, Ze-Kun;Zeng, Meng-Su
目的：利用治疗前表观扩散系数（ADC）图像衍生的影像组学特征，建立局部晚期直肠癌（LARC）对新辅助放化疗（NCRT）耐药的预测模型。方法：将89例LARC患者按3∶1的比例随机分为训练组（n = 66）和测试组（n = 23）。影像组学特征来自于治疗前ADC图像中手动确定的肿瘤区域。采用随机森林算法确定最相关的特征，进而构建识别耐药肿瘤的预测模型。用测试组评估随机森林模型的稳定性和诊断性能。结果：从临床特征和133个影像组学特征中确定了10个最相关的特征（平均熵、逆方差、平均能量、小区域强调、ADC最小值、ADC平均值、sdGa02、小梯度强调、年龄和大小）。在测试组对耐药肿瘤的预测中，基于这些最相关特征构建的随机森林模型的受试者工作特征曲线下面积为0.83，最高准确率为91.3%，敏感度为88.9%，特异度为92.8%。结论：基于治疗前ADC图像衍生的影像组学特征的随机森林分类器有可能预测LARC患者对NCRT的肿瘤耐药性，预测模型的使用可能有助于直肠癌的个体化治疗。
ObjectiveTo develop a predicting model for tumor resistance to neoadjuvant chemoradiotherapy (NCRT) in locally advanced rectal cancer (LARC) by using pre-treatment apparent diffusion coefficient (ADC) image-derived radiomics features.MethodA total of 89 patients with LARC were randomly assigned into training (N= 66) and testing cohorts (N= 23) at the ratio of 3:1. Radiomics features were derived from manually determined tumor region of pre-treatment ADC images. Random forest algorithm was used to determine the most relevant features and then to construct a predicting model for identifying resistant tumor. Stability and diagnostic performance of the random forest model was evaluated with the testing cohort.ResultsThe top 10 most relevant features (entropymean, inverse variance, energymean, small area emphasis, ADCmin, ADCmean, sdGa02, small gradient emphasis, age, and size) were determined from clinical characteristics and 133 radiomics features. In the prediction of resistant tumor of the testing cohort, the random forest model constructed based on these most relevant features achieved an area under the receiver operating characteristic curve of 0.83, with the highest accuracy of 91.3%, a sensitivity of 88.9%, and a specificity of 92.8%.ConclusionThe random forest classifier based on radiomics features derived from pre-treatment ADC images have the potential to predict tumor resistance to NCRT in patients with LARC, and the use of predicting model may facilitate individualized management of rectal cancer.