Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks
Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks
复制标题
使用深度扩张卷积神经网络自动分割直肠癌计划 CT 中的临床靶区和危险器官
DOI：
10.1002/mp.12602
复制
发表时间：
2017-12-01
期刊：
影响因子：
3.8
通讯作者：
Li, Yexiong
中科院分区：
文献类型：
--
作者：
Men, Kuo;Dai, Jianrong;Li, Yexiong
目的：临床靶区（CTV）和危险器官（OAR）的勾画对放射治疗非常重要，但耗时且易于观察者间的变化。在这里，我们提出了一种新的基于深度扩张卷积神经网络（DDCNN）的方法，用于快速和一致的自动分割这些structures.Methods：我们的DDCNN方法是一种端到端架构，可以快速训练和测试。具体来说，它采用了一种新的多尺度卷积架构来提取早期层中的多尺度上下文特征，这些特征包含了关于精细纹理和边界的原始信息，并且对于精确的自动分割非常有用。此外，该算法扩大了网络末端扩张卷积的感受野，以捕获互补的上下文特征。然后，用全卷积层替换全连通层，实现逐像素分割。我们使用了278例直肠癌患者的数据进行评估。CTV和OAR由资深放射肿瘤学家在计划的计算机断层扫描（CT）图像中描绘和验证。随机选择的218名患者用于训练，其余60名用于验证。Dice相似性系数（DSC）被用来衡量分割精度。结果：性能进行了评估的CTV和OAR的分割。此外，还将DDCNN与U-Net进行了性能比较。对于所有分割，所提出的DDCNN方法都优于U-Net，DDCNN的平均DSC值比U-Net高3.8%。DDCNN的平均DSC值为：CTV为87.7%，膀胱为93.4%，左股骨头为92.1%，右股骨头为92.3%，肠为65.3%，结肠为61.8%。测试时间为45 s/例患者，用于分割所有CTV、膀胱、左右股骨头、结肠和肠。我们还评估了我们的方法和结果与那些在文献中：我们的系统表现出上级性能和更快的speeds.Conclusions：这些数据表明，DDCNN可以用来分割CTV和OARs准确，有效。它与患者的体型、体型和年龄无关。DDCNN可以提高轮廓的一致性并简化放射治疗工作流程。(C)2017年美国医学物理学家协会
Purpose: Delineation of the clinical target volume (CTV) and organs at risk (OARs) is very important for radiotherapy but is time-consuming and prone to inter-observer variation. Here, we proposed a novel deep dilated convolutional neural network (DDCNN)-based method for fast and consistent auto-segmentation of these structures.Methods: Our DDCNN method was an end-to-end architecture enabling fast training and testing. Specifically, it employed a novel multiple-scale convolutional architecture to extract multiple-scale context features in the early layers, which contain the original information on fine texture and boundaries and which are very useful for accurate auto-segmentation. In addition, it enlarged the receptive fields of dilated convolutions at the end of networks to capture complementary context features. Then, it replaced the fully connected layers with fully convolutional layers to achieve pixel-wise segmentation. We used data from 278 patients with rectal cancer for evaluation. The CTV and OARs were delineated and validated by senior radiation oncologists in the planning computed tomography (CT) images. A total of 218 patients chosen randomly were used for training, and the remaining 60 for validation. The Dice similarity coefficient (DSC) was used to measure segmentation accuracy.Results: Performance was evaluated on segmentation of the CTV and OARs. In addition, the performance of DDCNN was compared with that of U-Net. The proposed DDCNN method outperformed the U-Net for all segmentations, and the average DSC value of DDCNN was 3.8% higher than that of U-Net. Mean DSC values of DDCNN were 87.7% for the CTV, 93.4% for the bladder, 92.1% for the left femoral head, 92.3% for the right femoral head, 65.3% for the intestine, and 61.8% for the colon. The test time was 45 s per patient for segmentation of all the CTV, bladder, left and right femoral heads, colon, and intestine. We also assessed our approaches and results with those in the literature: our system showed superior performance and faster speed.Conclusions: These data suggest that DDCNN can be used to segment the CTV and OARs accurately and efficiently. It was invariant to the body size, body shape, and age of the patients. DDCNN could improve the consistency of contouring and streamline radiotherapy workflows. (C) 2017 American Association of Physicists in Medicine