A recursive ensemble organ segmentation (REOS) framework: application in brain radiotherapy
A recursive ensemble organ segmentation (REOS) framework: application in brain radiotherapy
复制标题
DOI：
10.1088/1361-6560/aaf83c
复制
发表时间：
2019-01-01
影响因子：
3.5
通讯作者：
Gu, Xuejun
中科院分区：
文献类型：
--
作者：
Chen, Haibin;Lu, Weiguo;Gu, Xuejun
这项工作的目的是开发一种新颖的递归集成 OAR 分割 (REOS) 框架，用于准确的危及器官 (OAR) 自动分割。 REOS 通过集成从器官定位模块和轮廓检测模块提取的图像特征来递归地分割各个 OAR。这两个模块均基于 3D U-Net 架构。器官定位模块经过训练进行粗分割，以定位包含待描绘的 OAR 的感兴趣区域 (ROI)，而轮廓检测模块经过训练以在已识别的 ROI 内分割 OAR。在这项研究中，开发的REOS框架应用于脑放射治疗，对包括眼睛、脑干（BS）、视神经和视交叉在内的六个OARS进行分段。收集了 80 名脑癌患者病例中具有 OAR 金标准轮廓的 80 张 T1 加权磁共振图像 (MRI)，用于训练和测试 REOS。在 20 个测试案例中，REOS 实现了较高的分割精度，左眼、右眼和 BS 的 Dice 相似系数 (DSC) 平均值和标准差分别为 93.9% +/- 1.4%、94.5% +/- 2.0%、90.6% +/- 2.7%。在小型且难以分割的器官、左右视神经和视交叉上，REOS 实现的 DSC 为 78.0% +/- 10.5%、82.2% +/- 5.9% 和 71.1% +/- 9.1%。令人满意的性能证明了 REOS 在 OARS 分割中的有效性。
The aim of this work is to develop a novel recursive ensemble OARs segmentation (REOS) framework for accurate organs-at-risk (OARs) automatic segmentation. The REOS recursively segment individual OARs by ensembling images features extracted from an organ localization module and a contour detection module. Both modules are based on a 3D U-Net architecture. The organ localization module is trained for rough segmentation to localize a region of interest (ROI) that encompasses the to-be-delineated OAR, while the contour detection module is trained to segment the OAR within the identified ROI. In this study, the developed REOS framework is applied for brain radiotherapy on segmenting six OARS including the eyes, the brainstem (BS), the optical nerves and the chiasm. Eighty T1-weighted magnetic resonance images (MRI) from 80 brain cancer patients' cases with OARs' gold standard contours were collected for training and testing REOS. On 20 testing cases, the REOS achieve a high segmentation accuracy with Dice similarity coefficient (DSC) mean and standard deviation of 93.9% +/- 1.4%, 94.5% +/- 2.0%, 90.6% +/- 2.7%, on the left and right eyes and the BS, respectively. On small and segmentation-challenging organs, the left and right optical nerves and the chiasm, the REOS achieves DSC of 78.0% +/- 10.5%, 82.2% +/- 5.9% and 71.1% +/- 9.1%. The satisfactory performances demonstrated the effectiveness of the REOS in OARS segmentation.