Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images.
Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images.
复制标题
用于头颈 CT 图像中小体积结构联合分割的交错 3D-CNN
DOI：
10.1002/mp.12837
复制
发表时间：
2018-05
期刊：
影响因子：
3.8
通讯作者：
Wang Q
中科院分区：
文献类型：
--
作者：
Ren X;Xiang L;Nie D;Shao Y;Zhang H;Shen D;Wang Q
准确的三维图像分割是头颈部肿瘤放射治疗计划的关键步骤。这些分割结果目前是通过手动勾画组织轮廓来获得的，这是一个繁琐且耗时的过程。自动分割提供了一种替代解决方案，然而，其对于小组织（即，头部和颈部CT图像中的视交叉和视神经），因为它们体积小且外观/形状信息高度多样化。在这项工作中，我们提出了交错多个3D卷积神经网络（3D-CNN），以实现自动分割的头部和颈部CT图像中的小组织。3D-CNN旨在分割每个感兴趣的结构。为了充分利用图像的外观信息，提取多尺度补丁来描述所考虑的中心体素，然后输入到CNN架构。接下来，由于相邻组织在生理和解剖学角度上通常高度相关，因此我们将为单个组织指定的CNN交织在一起。以这种方式，特定组织的试验性分割结果可以有助于细化其他相邻组织的分割。最后，随着更多的CNN被交织和级联，可以导出CNN的复杂网络，使得所有组织可以被联合分割和迭代细化。我们的方法在2015年医学图像计算和计算机辅助干预（MICCAI）挑战赛中获得的一组48张CT图像上进行了验证。计算Dice系数（DC）和95% Hausdorff距离（95 HD）来衡量分割结果的准确性。该方法具有较高的分割精度（平均DC：视交叉0.58±0.17，视神经0.71±0.08; 95 HD：视交叉2.81±1.56 mm，视神经2.23±0.90 mm）（平均DC：视交叉0.38，视神经0.68; 95 HD：视交叉3.48，视神经2.48）。针对头颈部CT图像中的小组织，提出了一种精确的自动分割方法，这对放射治疗计划的制定具有重要意义。
Accurate 3D image segmentation is a crucial step in radiation therapy planning of head and neck tumors. These segmentation results are currently obtained by manual outlining of tissues, which is a tedious and time-consuming procedure. Automatic segmentation provides an alternative solution, which, however, is often difficult for small tissues (i.e., chiasm and optic nerves in head and neck CT images) because of their small volumes and highly diverse appearance/shape information. In this work, we propose to interleave multiple 3D Convolutional Neural Networks (3D-CNNs) to attain automatic segmentation of small tissues in head and neck CT images. A 3D-CNN was designed to segment each structure of interest. To make full use of the image appearance information, multi-scale patches are extracted to describe the center voxel under consideration and then input to the CNN architecture. Next, as neighboring tissues are often highly related in the physiological and anatomical perspectives, we interleave the CNNs designated for the individual tissues. In this way, the tentative segmentation result of a specific tissue can contribute to refine the segmentations of other neighboring tissues. Finally, as more CNNs are interleaved and cascaded, a complex network of CNNs can be derived, such that all tissues can be jointly segmented and iteratively refined. Our method was validated on a set of 48 CT images, obtained from the Medical Image Computing and Computer Assisted Intervention (MICCAI) Challenge 2015. The Dice coefficient (DC) and the 95% Hausdorff Distance (95HD) are computed to measure the accuracy of the segmentation results. The proposed method achieves higher segmentation accuracy (with the average DC: 0.58±0.17 for optic chiasm, and 0.71±0.08 for optic nerve; 95HD: 2.81±1.56 mm for optic chiasm, and 2.23±0.90 mm for optic nerve) than the MICCAI challenge winner (with the average DC: 0.38 for optic chiasm, and 0.68 for optic nerve; 95HD: 3.48 for optic chiasm, and 2.48 for optic nerve). An accurate and automatic segmentation method has been proposed for small tissues in head and neck CT images, which is important for the planning of radiotherapy.
登录
查看更多内容
影响因子：
5.7
作者：
Kim M;Wu G;Li W;Wang L;Son YD;Cho ZH;Shen D
通讯作者：
Shen D
影响因子：
10.6
作者：
Sanroma G;Wu G;Gao Y;Shen D
通讯作者：
Shen D
影响因子：
10.6
作者：
Gao Y;Shao Y;Lian J;Wang AZ;Chen RC;Shen D
通讯作者：
Shen D
影响因子：
10.9
作者：
Iglesias JE;Sabuncu MR
通讯作者：
Sabuncu MR
DOI：
10.1016/j.compmedimag.2016.02.001
发表时间：
2016-09
期刊：
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子：
--
作者：
Qian C;Wang L;Gao Y;Yousuf A;Yang X;Oto A;Shen D
通讯作者：
Shen D