Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.
Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks.
复制标题
DOI：
10.1002/mp.13147
复制
发表时间：
2018-10
期刊：
影响因子：
3.8
通讯作者：
Sheng K
中科院分区：
文献类型：
--
作者：
Tong N;Gou S;Yang S;Ruan D;Sheng K
强度调节辐射疗法（IMRT）通常用于治疗肿瘤剂量均匀的头颈（H＆N）癌症（H＆N）癌症。因此，在H＆N CT图像上准确描述了器官 - 正风险（OARS）对于治疗质量至关重要。当前临床实践中使用的手动轮廓是乏味的，耗时的，并且会产生不一致的结果。现有的自动分割方法受到实质性的解剖学变异和低CT软组织对比的挑战。为了克服挑战，我们开发了一种新型的自动化H＆N OARS分割方法，该方法将完全卷积神经网络（FCNN）与形状表示模型（SRM）结合在一起。
基于手动分割的H＆N CT，对SRM和FCNN进行了两个步骤培训：1）SRM从培训数据集中学习了H＆N OAR的潜在形状表示； 2）使用固定参数的预训练的SRM来限制FCNN训练。然后，使用组合的分割网络来描绘九个桨，包括脑干，视神经，下颌骨，光神经，腮腺和下颌腺，上看不见的H＆N CT图像。公共领域数据库提供的计算解剖结构（PDDCA）提供了22张和10次H＆N CT扫描，分别用于培训和验证。计算骰子相似性系数（DSC），正预测值（PPV），灵敏度（SEN），平均表面距离（ASD）和95％的最大表面距离（95％SD），以定量评估所提出方法的分割精度。将所提出的方法与一个主动外观模型进行了比较，该模型赢得了基于同一数据集，ATLAS方法和基于不同患者数据集的深度学习方法赢得2015 Miccai H＆N分割挑战。
平均DSC = 0.870（脑干），DSC = 0.583（光学chiASM），DSC = 0.937（下颌），DSC = 0.653（左视神经），DSC = 0.689（右视神经），DSC = 0.835（左Parotid），，DSC = 0.689，， DSC = 0.832（右腮腺），DSC = 0.755（左下颌下）和达到了DSC = 0.813（右下颌下）。分割结果始终优于地图集的结果和基于统计形状的方法以及斑块的卷积神经网络方法。一旦网络受到离线训练，平均将所有9个桨进行看不见的CT扫描的时间为9.5秒。
在H＆N患者的临床数据集上进行的实验证明了对体积CT扫描进行多器官分割的建议深神经网络分割方法的有效性。通过使用SMR合并形状先验，进一步提高了分割的准确性和鲁棒性。所提出的方法表现出竞争性的性能，并且与最新方法相比，花了更短的时间来细分多个器官。
Intensity modulated radiation therapy (IMRT) is commonly employed for treating head and neck (H&N) cancer with uniform tumor dose and conformal critical organ sparing. Accurate delineation of organs-at-risk (OARs) on H&N CT images is thus essential to treatment quality. Manual contouring used in current clinical practice is tedious, time-consuming, and can produce inconsistent results. Existing automated segmentation methods are challenged by the substantial inter-patient anatomical variation and low CT soft tissue contrast. To overcome the challenges, we developed a novel automated H&N OARs segmentation method that combines a fully convolutional neural network (FCNN) with a shape representation model (SRM). Based on manually segmented H&N CT, the SRM and FCNN were trained in two steps: 1) SRM learned the latent shape representation of H&N OARs from the training dataset; 2) the pre-trained SRM with fixed parameters were used to constrain the FCNN training. The combined segmentation network was then used to delineate nine OARs including the brainstem, optic chiasm, mandible, optical nerves, parotids and submandibular glands on unseen H&N CT images. Twenty-two and 10 H&N CT scans provided by the Public Domain Database for Computational Anatomy (PDDCA) were utilized for training and validation, respectively. Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average surface distance (ASD), and 95% maximum surface distance (95%SD) were calculated to quantitatively evaluate the segmentation accuracy of the proposed method. The proposed method was compared with an active appearance model that won the 2015 MICCAI H&N Segmentation Grand Challenge based on the same dataset, an atlas method and a deep learning method based on different patient datasets. An average DSC=0.870 (brainstem), DSC=0.583 (optic chiasm), DSC=0.937 (mandible), DSC=0.653 (left optic nerve), DSC=0.689 (right optic nerve), DSC=0.835 (left parotid), DSC=0.832 (right parotid), DSC=0.755 (left submandibular), and DSC=0.813 (right submandibular) were achieved. The segmentation results are consistently superior to the results of atlas and statistical shape based methods as well as a patch-wise convolutional neural network method. Once the networks are trained off-line, the average time to segment all 9 OARs for an unseen CT scan is 9.5 seconds. Experiments on clinical datasets of H&N patients demonstrated the effectiveness of the proposed deep neural network segmentation method for multi-organ segmentation on volumetric CT scans. The accuracy and robustness of the segmentation were further increased by incorporating shape priors using SMR. The proposed method showed competitive performance and took shorter time to segment multiple organs in comparison to state of the art methods.
登录
查看更多内容
影响因子：
10.6
作者：
Brosch, Tom;Tang, Lisa Y. W.;Tam, Roger
通讯作者：
Tam, Roger
DOI：
10.1016/j.ijrobp.2012.02.003
发表时间：
2012-08-01
影响因子：
7
作者：
Breunig, Jennifer;Hernandez, Sophy;Roeske, John C.
通讯作者：
Roeske, John C.
影响因子：
4.8
作者：
DICE, LR
通讯作者：
DICE, LR
影响因子：
45.3
作者：
Chaturvedi, Anil K.;Anderson, William F.;Gillison, Maura L.
通讯作者：
Gillison, Maura L.
影响因子：
10.9
作者：
Dou, Qi;Yu, Lequan;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann