Relationship between number of annotations and accuracy in segmentation of the erector spinae muscle using Bayesian U-Net in torso CT images
Relationship between number of annotations and accuracy in segmentation of the erector spinae muscle using Bayesian U-Net in torso CT images
复制标题
躯干 CT 图像中使用贝叶斯 U-Net 进行竖脊肌分割的注释数量与准确性之间的关系
DOI：
10.1117/12.2590780
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Fujita Hiroshi
中科院分区：
文献类型：
--
作者：
Wakamatsu Yuichi;Kamiya Naoki;Zhou Xiangrong;Hara Takeshi;Fujita Hiroshi
用于图像分割的监督学习需要带标注的图像。然而，图像标注存在耗时长的问题。这一问题在竖脊肌分割中尤其明显，因为肌肉的尺寸很大。因此，本研究考虑了用于训练的标注图像数目与躯干CT图像中竖脊肌分割精度之间的关系。我们使用贝叶斯U网络对竖脊肌进行分割，该方法在大腿肌肉分割中表现出很高的准确率。在网络训练中，我们将每个案例的切片数量和案例数量限制在100%、50%、25%和10%。在实验中，我们使用了30幅躯干CT图像，其中6例作为测试数据集。实验结果通过测试数据集的平均骰子值来评估。对于每例100%的切片，100%、50%、25%和10%的分割准确率分别为0.934、0.927、0.926和0.890。另一方面，在100%的情况下，每个病例100%、50%、25%和10%切片的分割准确率分别为0.934、0.934、0.933和0.931。此外，对于100%的案例和10%的切片，分割的准确率比以前的方法更高。实验表明，通过从有限的案例中选择几个切片进行训练，可以在有限数量的标注图像上达到较高的分割精度。
Supervised learning for image segmentation requires annotated images. However, image annotation has the problem that it is time-consuming. This problem is particularly significant in the erector spinae muscle segmentation due to the large size of the muscle. Therefore, this study considers the relationship between the number of annotated images used for training and segmentation accuracy of the erector spinae muscle in torso CT images. We use Bayesian U-Net, which has shown high accuracy in thigh muscle segmentation, for the segmentation of the erector spinae muscle. In the network training, we limit the number of slices for each case and the number of cases to 100%, 50%, 25%, and 10%. In the experiment, we use 30 torso CT images, including 6 cases for the test dataset. Experimental results are evaluated by the mean Dice value of the test dataset. Using 100% of the slices per case, the segmentation accuracy with 100%, 50%, 25%, and 10% of the cases was 0.934, 0.927, 0.926, and 0.890, respectively. On the other hand, using 100% of the cases, the segmentation accuracy with 100%, 50%, 25%, and 10% of the slices per case was 0.934, 0.934, 0.933, and 0.931, respectively. Furthermore, the segmentation accuracy with 100% of the cases and 10% of the slices per case was higher than that of the previous method. We showed that it is feasible to achieve high segmentation accuracy with a limited number of annotated images by selecting several slices from a limited number of cases for training.