Marginal radiomics features as imaging biomarkers for pathological invasion in lung adenocarcinoma
Marginal radiomics features as imaging biomarkers for pathological invasion in lung adenocarcinoma
复制标题
DOI：
10.1007/s00330-019-06581-2
复制
发表时间：
2020-05-01
影响因子：
5.9
通讯作者：
Park, Hyunjin
中科院分区：
文献类型：
--
作者：
Cho, Hwan-ho;Lee, Geewon;Park, Hyunjin
目的以磨玻璃结节(GGNs)为表现的肺腺癌具有不同程度的病理侵袭，鉴别诊断是治疗的关键。我们的目标是评估在计算机断层扫描(CT)图像的基线放射组学模型中添加边缘特征来预测病理侵袭程度。方法我们从两个队列(训练组，n=189；验证组，n=47)中确定了236名接受GGNs手术的患者。所有GGNs均经病理证实为原位腺癌(AIS)、微侵袭性腺癌(MIA)或侵袭性腺癌(IA)。对感兴趣的区域进行半自动注释，并计算40个放射组学特征。我们使用L1范数正则化选择特征来构建基线放射组学模型。使用肿瘤内信号的累积分布函数(CDF)显示附加的边缘特征。将基线模型与CDF特征相结合，建立了改进的CDF模型。对这两个模型都测试了三个分类器。结果基线放射组学模型包括5个特征，三个分类器的平均曲线下面积(AUC)分别为0.8419(训练)和0.9142(验证)。第二个模型，加上附加的边缘特征，得到0.8560(训练)和0.9581(验证)的AUC值。所有这三个分类器在添加特征时都表现得更好。支持向量机的性能改善最大(AuC改善=0.0790)，Logistic分类器的性能最佳(验证AuC=0.9825)。结论我们新的边缘特征与基线放射组学模型相结合，有助于在术前CT扫描上区分IA与AIS和MIA。
Objectives Lung adenocarcinomas which manifest as ground-glass nodules (GGNs) have different degrees of pathological invasion and differentiating among them is critical for treatment. Our goal was to evaluate the addition of marginal features to a baseline radiomics model on computed tomography (CT) images to predict the degree of pathologic invasiveness. Methods We identified 236 patients from two cohorts (training, n = 189; validation, n = 47) who underwent surgery for GGNs. All GGNs were pathologically confirmed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IA). The regions of interest were semi-automatically annotated and 40 radiomics features were computed. We selected features using L1-norm regularization to build the baseline radiomics model. Additional marginal features were developed using the cumulative distribution function (CDF) of intratumoral intensities. An improved model was built combining the baseline model with CDF features. Three classifiers were tested for both models. Results The baseline radiomics model included five features and resulted in an average area under the curve (AUC) of 0.8419 (training) and 0.9142 (validation) for the three classifiers. The second model, with the additional marginal features, resulted in AUCs of 0.8560 (training) and 0.9581 (validation). All three classifiers performed better with the added features. The support vector machine showed the most performance improvement (AUC improvement = 0.0790) and the best performance was achieved by the logistic classifier (validation AUC = 0.9825). Conclusion Our novel marginal features, when combined with a baseline radiomics model, can help differentiate IA from AIS and MIA on preoperative CT scans.