Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques
Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques
复制标题
DOI：
10.1016/j.compbiomed.2020.103767
复制
发表时间：
2020-06-01
影响因子：
7.7
通讯作者：
Togashi, Kaori
中科院分区：
文献类型：
--
作者：
Noguchi, Shunjiro;Nishio, Mizuho;Togashi, Kaori
背景：本研究的目的是开发和评估一种基于卷积神经网络(CNN)的全身CT骨分割算法。为了评估其性能和稳健性，我们准备了三个不同的数据集：(1)包含16名患者32次扫描的16,218个CT图像的内部数据集；(2)从癌症成像档案馆收集的包含20个患者的20个扫描的12,529个CT图像的二级数据集；以及(3)公开可用的标记数据集，该数据集包含来自20个患者的27个扫描的270个CT图像。为了提高网络的性能和稳健性，我们评估了三种数据增强技术的有效性：传统方法、混合和随机图像裁剪和修补。结果：在内部数据集上训练的网络与内部数据集的交叉验证平均骰子系数为0.983+/-0.005，与二级数据集的交叉验证平均骰子系数为0.943+/-0.007。在公共数据集上训练的网络在10个随机生成的公共数据集的15-3-9个分割上获得了0.947+/-0.013的平均骰子系数。这些结果超过了之前报道的结果。在增强技术方面，常规方法、RICAP方法以及两者的结合都是有效的。结论：基于CNN的模型在全身CT上实现了准确的骨分割，具有对各种扫描条件的通用性。数据增强技术使构建准确和稳健的模型成为可能，即使是使用较小的数据集。
Background: The purpose of this study was to develop and evaluate an algorithm for bone segmentation on whole-body CT using a convolutional neural network (CNN).Methods: Bone segmentation was performed using a network based on U-Net architecture. To evaluate its performance and robustness, we prepared three different datasets: (1) an in-house dataset comprising 16,218 slices of CT images from 32 scans in 16 patients; (2) a secondary dataset comprising 12,529 slices of CT images from 20 scans in 20 patients, which were collected from The Cancer Imaging Archive; and (3) a publicly available labelled dataset comprising 270 slices of CT images from 27 scans in 20 patients. To improve the network's performance and robustness, we evaluated the efficacy of three types of data augmentation technique: conventional method, mixup, and random image cropping and patching (RICAP).Results: The network trained on the in-house dataset achieved a mean Dice coefficient of 0.983 +/- 0.005 on cross validation with the in-house dataset, and 0.943 +/- 0.007 with the secondary dataset. The network trained on the public dataset achieved a mean Dice coefficient of 0.947 +/- 0.013 on 10 randomly generated 15-3-9 splits of the public dataset. These results outperform those reported previously. Regarding augmentation technique, the conventional method, RICAP, and a combination of these were effective.Conclusions: The CNN-based model achieved accurate bone segmentation on whole-body CT, with generalizability to various scan conditions. Data augmentation techniques enabled construction of an accurate and robust model even with a small dataset.