Dinis Fernandes Catarina, Dinh Cuong V, Walraven Iris, Heijmink Stijn W, Smolic Milena, van Griethuysen Joost J M, Simões Rita, Losnegård Are, van der Poel Henk G, Pos Floris J, van der Heide Uulke A
Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, The Netherlands.
Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands.
Phys Imaging Radiat Oncol. 2018 Aug 6;7:9-15. doi: 10.1016/j.phro.2018.06.005. eCollection 2018 Jul.
High-risk prostate cancer patients are frequently treated with external-beam radiotherapy (EBRT). Of all patients receiving EBRT, 15-35% will experience biochemical recurrence (BCR) within five years. Magnetic resonance imaging (MRI) is commonly acquired as part of the diagnostic procedure and imaging-derived features have shown promise in tumour characterisation and biochemical recurrence prediction. We investigated the value of imaging features extracted from pre-treatment T2w anatomical MRI to predict five year biochemical recurrence in high-risk patients treated with EBRT.
In a cohort of 120 high-risk patients, imaging features were extracted from the whole-prostate and a margin surrounding it. Intensity, shape and textural features were extracted from the original and filtered T2w-MRI scans. The minimum-redundancy maximum-relevance algorithm was used for feature selection. Random forest and logistic regression classifiers were used in our experiments. The performance of a logistic regression model using the patient's clinical features was also investigated. To assess the prediction accuracy we used stratified 10-fold cross validation and receiver operating characteristic analysis, quantified by the area under the curve (AUC).
A logistic regression model built using whole-prostate imaging features obtained an AUC of 0.63 in the prediction of BCR, outperforming a model solely based on clinical variables (AUC = 0.51). Combining imaging and clinical features did not outperform the accuracy of imaging alone.
These results illustrate the potential of imaging features alone to distinguish patients with an increased risk of recurrence, even in a clinically homogeneous cohort.
高危前列腺癌患者常接受外照射放疗（EBRT）。在所有接受EBRT的患者中，15% - 35%会在五年内出现生化复发（BCR）。磁共振成像（MRI）通常作为诊断程序的一部分进行采集，并且成像衍生特征在肿瘤特征描述和生化复发预测方面已显示出前景。我们研究了从治疗前T2加权解剖MRI中提取的成像特征对接受EBRT的高危患者五年生化复发的预测价值。
在一组120例高危患者中，从整个前列腺及其周围边缘提取成像特征。从原始和滤波后的T2加权MRI扫描中提取强度、形状和纹理特征。使用最小冗余最大相关算法进行特征选择。在我们的实验中使用了随机森林和逻辑回归分类器。还研究了使用患者临床特征的逻辑回归模型的性能。为了评估预测准确性，我们使用分层10折交叉验证和受试者工作特征分析，并通过曲线下面积（AUC）进行量化。
使用全前列腺成像特征构建的逻辑回归模型在预测BCR时的AUC为0.63，优于仅基于临床变量的模型（AUC = 0.51）。结合成像和临床特征的准确性并未超过单独成像的准确性。
这些结果表明，即使在临床同质性队列中，仅成像特征也有潜力区分复发风险增加的患者。
