Deep learning in head & neck cancer outcome prediction
Deep learning in head & neck cancer outcome prediction
复制标题
DOI：
10.1038/s41598-019-39206-1
复制
发表时间：
2019-02-26
影响因子：
4.6
通讯作者：
Seuntjens, Jan
中科院分区：
文献类型：
--
作者：
Diamant, Andre;Chatterjee, Avishek;Seuntjens, Jan
传统的放射组学涉及从医学图像中提取定量纹理特征，以试图确定与临床终点的相关性。我们假设卷积神经网络（CNN）可以通过检测传统放射组学框架可能无法覆盖的图像模式来增强传统放射组学的性能。我们通过训练CNN来预测头颈部鳞状细胞癌患者的治疗结果来测试这一假设，仅仅基于他们治疗前的计算机断层扫描图像。训练集（194例患者）和验证集（106例患者）相互独立，包括4个机构，来自癌症成像档案。当与应用于相同患者队列的传统放射组学框架相比时，我们的方法在预测远处转移中的AUC为0.88。当将我们的模型与之前的模型相结合时，AUC提高到0.92。我们的框架产生的模型被证明可以明确识别传统的放射组学特征，直接可视化并进行准确的结果预测。
Traditional radiomics involves the extraction of quantitative texture features from medical images in an attempt to determine correlations with clinical endpoints. We hypothesize that convolutional neural networks (CNNs) could enhance the performance of traditional radiomics, by detecting image patterns that may not be covered by a traditional radiomic framework. We test this hypothesis by training a CNN to predict treatment outcomes of patients with head and neck squamous cell carcinoma, based solely on their pre-treatment computed tomography image. The training (194 patients) and validation sets (106 patients), which are mutually independent and include 4 institutions, come from The Cancer Imaging Archive. When compared to a traditional radiomic framework applied to the same patient cohort, our method results in a AUC of 0.88 in predicting distant metastasis. When combining our model with the previous model, the AUC improves to 0.92. Our framework yields models that are shown to explicitly recognize traditional radiomic features, be directly visualized and perform accurate outcome prediction.