Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer
Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer
复制标题
DOI：
10.1007/s11547-018-0966-4
复制
发表时间：
2019-06-01
影响因子：
8.9
通讯作者：
Mahdavi, Seied Rabi
中科院分区：
文献类型：
--
作者：
Abdollahi, Hamid;Mofid, Bahram;Mahdavi, Seied Rabi
目的基于磁共振成像（MRI）放射组学特征和机器学习方法建立不同的放射组学模型，预测早期调强放疗（IMRT）反应、Gleason评分（GS）和前列腺癌（Pca）分期。所有患者均接受调强放疗前后T2加权（T2W）和表观弥散系数（ADC）MRI检查。根据ADC值的变化计算IMRT反应，并将患者分为反应者和无反应者。从所有T2W和ADC图像中提取了来自不同特征集的广泛的放射组学特征。进行单变量放射组学分析以找到与IMRT反应高度相关的放射组学特征，并使用配对t检验来找到反应者和无反应者之间的显著特征。要找到高预测放射组学模型，10倍交叉验证作为标准的功能选择和分类上的前，后和三角洲IMRT放射组学功能，并在曲线下面积（AUC）的接收器工作特性计算模型的性能value.ResultsOf 33例患者，15例（45%）被发现作为响应者。单因素分析显示20个放射组学特征与IMRT反应高度相关（20个ADC和20个T2）。2个和15个T2和ADC放射组学特征在应答者和非应答者之间分别被发现为显著特征（P值0.05）。获得了几种交叉组合的预测放射组学模型，发现T2后放射组学模型是高预测模型（AUC 0.632），其次是ADC前（AUC 0.626）和T2前（AUC 0.61）。对于GS预测，T2W放射组学模型被认为是更有预测性的（平均AUC 0.739），而不是ADC模型（平均AUC 0.70），而对于分期预测，ADC模型具有更高的预测性能（平均AUC 0.675）。
Objective To develop different radiomic models based on the magnetic resonance imaging (MRI) radiomic features and machine learning methods to predict early intensity-modulated radiation therapy (IMRT) response, Gleason scores (GS) and prostate cancer (Pca) stages.MethodsThirty-three Pca patients were included. All patients underwent pre- and post-IMRT T2-weighted (T2W) and apparent diffusing coefficient (ADC) MRI. IMRT response was calculated in terms of changes in the ADC value, and patients were divided as responders and non-responders. A wide range of radiomic features from different feature sets were extracted from all T2W and ADC images. Univariate radiomic analysis was performed to find highly correlated radiomic features with IMRT response, and a paired t test was used to find significant features between responders and non-responders. To find high predictive radiomic models, tenfold cross-validation as the criterion for feature selection and classification was applied on the pre-, post- and delta IMRT radiomic features, and area under the curve (AUC) of receiver operating characteristics was calculated as model performance value.ResultsOf 33 patients, 15 patients (45%) were found as responders. Univariate analysis showed 20 highly correlated radiomic features with IMRT response (20 ADC and 20 T2). Two and fifteen T2 and ADC radiomic features were found as significant (P-value0.05) features between responders and non-responders, respectively. Several cross-combined predictive radiomic models were obtained, and post-T2 radiomic models were found as high predictive models (AUC 0.632) followed by pre-ADC (AUC 0.626) and pre-T2 (AUC 0.61). For GS prediction, T2W radiomic models were found as more predictive (mean AUC 0.739) rather than ADC models (mean AUC 0.70), while for stage prediction, ADC models had higher prediction performance (mean AUC 0.675).ConclusionsRadiomic models developed by MR image features and machine learning approaches are noninvasive and easy methods for personalized prostate cancer diagnosis and therapy.