Improving accuracy and robustness of deep convolutional neural network based thoracic OAR segmentation.
Improving accuracy and robustness of deep convolutional neural network based thoracic OAR segmentation.
复制标题
DOI：
10.1088/1361-6560/ab7877
复制
发表时间：
2020-03-31
影响因子：
3.5
通讯作者：
Chen Q
中科院分区：
文献类型：
--
作者：
Feng X;Bernard ME;Hunter T;Chen Q
深度卷积神经网络(DCNN)在各种医学图像分割任务中取得了巨大的成功，包括从CT图像中分割危险器官(OAR)。然而，大多数研究使用来自相同来源(S)的数据集进行训练和测试，因此没有很好地研究训练后的数据网对不同数据集的泛化能力，以及解决不同数据集上性能下降的策略。在这项研究中，我们研究了一个来自公共数据集的训练有素的DCNN模型在本地数据集上分割胸部OAR的性能，并探索了数据集之间的系统差异。我们观察到，在图像采集过程中，由于腹部压缩技术导致患者体内器官的细微移位，导致在局部数据集上的性能显著降低。此外，我们通过整合来自当地机构的不同数量的新病例并使用转移学习来提高训练的DCNN模型的准确性和稳健性，从而制定了一种最优策略。我们发现，只要添加本地机构的10个案例，性能就可以达到与原始数据集中相同的水平。使用转移学习，可以显著缩短训练时间，但心脏分割的性能略有下降。
Deep convolutional neural network (DCNN) has shown great success in various medical image segmentation tasks, including organ-at-risk (OAR) segmentation from computed tomography (CT) images. However, most studies use the dataset from the same source(s) for training and testing so that the ability of a trained DCNN to generalize to a different dataset is not well studied, as well as the strategy to address the issue of performance drop on a different dataset. In this study we investigated the performance of a well-trained DCNN model from a public dataset for thoracic OAR segmentation on a local dataset and explored the systematic differences between the datasets. We observed that a subtle shift of organs inside patient body due to the abdominal compression technique during image acquisition caused significantly worse performance on the local dataset. Furthermore, we developed an optimal strategy via incorporating different numbers of new cases from the local institution and using transfer learning to improve the accuracy and robustness of the trained DCNN model. We found that by adding as few as 10 cases from the local institution, the performance can reach the same level as in the original dataset. With transfer learning, the training time can be significantly shortened with slightly worse performance for heart segmentation.
登录
查看更多内容
影响因子：
3.8
作者：
Tong N;Gou S;Yang S;Ruan D;Sheng K
通讯作者：
Sheng K
影响因子：
10.6
作者：
Gibson E;Giganti F;Hu Y;Bonmati E;Bandula S;Gurusamy K;Davidson B;Pereira SP;Clarkson MJ;Barratt DC
通讯作者：
Barratt DC
使用深度扩张卷积神经网络自动分割直肠癌计划 CT 中的临床靶区和危险器官
影响因子：
3.8
作者：
Men, Kuo;Dai, Jianrong;Li, Yexiong
通讯作者：
Li, Yexiong
影响因子：
3.5
作者：
Cardenas, Carlos E.;Yang, Jinzhong;Brock, Kristy B.
通讯作者：
Brock, Kristy B.
影响因子：
2.4
作者：
Trullo, Roger;Petitjean, Caroline;Ruan, Su
通讯作者：
Ruan, Su