Multi-View Spatial Aggregation Framework for Joint Localization and Segmentation of Organs at Risk in Head and Neck CT Images
Multi-View Spatial Aggregation Framework for Joint Localization and Segmentation of Organs at Risk in Head and Neck CT Images
复制标题
用于头颈 CT 图像中危险器官联合定位和分割的多视图空间聚合框架
DOI：
10.1109/tmi.2020.2975853
复制
发表时间：
2020-09-01
影响因子：
10.6
通讯作者：
Shen, Dinggang
中科院分区：
文献类型：
--
作者：
Liang, Shujun;Kim-Han Thung;Shen, Dinggang
准确分割头颈部CT图像中的危险器官是头颈部肿瘤放射治疗的关键。然而，现有的深度学习方法往往不是以端到端的方式训练的，即它们在器官分割之前独立地预先确定目标器官的区域，导致相关任务之间的信息共享有限，从而导致次优的分割结果。此外，当使用传统的分割网络同时分割所有桨时，结果往往偏向于大桨而不是小桨。因此，现有的方法往往为每个OAR训练一个特定的模型，忽略了不同分割任务之间的相关性。为了解决这些问题，我们提出了一种新的多视角空间聚合框架，用于基于H&N CT图像的多桨联合定位和分割。该框架的核心是提出了一种基于感兴趣区域(ROI)的细粒度表示卷积神经网络(CNN)，用于从CT图像的每个2D视图(即轴向、冠状面和矢状面)生成多OAR概率图。具体地说，我们的基于ROI的细粒度表示CNN(1)统一了桨的定位和分割任务，并以端到端的方式训练它们，(2)通过一种新的基于ROI的细粒度表示来改善不同大小的桨的分割结果。然后，我们的多视点空间聚合框架对生成的多视点多桨概率图进行空间聚合和组装，以同时分割所有桨。我们使用两组H&N CT图像对我们的框架进行了评估，对于不同大小的桨取得了具有竞争力和高度健壮性的分割性能。
Accurate segmentation of organs at risk (OARs) from head and neck (H&N) CT images is crucial for effective H&N cancer radiotherapy. However, the existing deep learning methods are often not trained in an end-to-end fashion, i.e., they independently predetermine the regions of target organs before organ segmentation, causing limited information sharing between related tasks and thus leading to suboptimal segmentation results. Furthermore, when conventional segmentation network is used to segment all the OARs simultaneously, the results often favor big OARs over small OARs. Thus, the existing methods often train a specific model for each OAR, ignoring the correlation between different segmentation tasks. To address these issues, we propose a new multi-view spatial aggregation framework for joint localization and segmentation of multiple OARs using H&N CT images. The core of our framework is a proposed region-of-interest (ROI)-based fine-grained representation convolutional neural network (CNN), which is used to generate multi-OAR probability maps from each 2D view (i.e., axial, coronal, and sagittal view) of CT images. Specifically, our ROI-based fine-grained representation CNN (1) unifies the OARs localization and segmentation tasks and trains them in an end-to-end fashion, and (2) improves the segmentation results of various-sized OARs via a novel ROI-based fine-grained representation. Our multi-view spatial aggregation framework then spatially aggregates and assembles the generated multi-view multi-OAR probability maps to segment all the OARs simultaneously. We evaluate our framework using two sets of H&N CT images and achieve competitive and highly robust segmentation performance for OARs of various sizes.