Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks.
Loss Weightings for Improving Imbalanced Brain Structure Segmentation Using Fully Convolutional Networks.
复制标题
使用完全卷积网络改善大脑结构分割不平衡的权重。
DOI：
10.3390/healthcare9080938
复制
发表时间：
2021-07-26
期刊：
影响因子：
--
通讯作者：
Nakajima Y
中科院分区：
文献类型：
--
作者：
Sugino T;Kawase T;Onogi S;Kin T;Saito N;Nakajima Y
磁共振（MR）图像上的脑结构分割对于各种临床应用是重要的。它是通过使用完全卷积网络自动执行的。然而，它存在着阶级不平衡的问题。为了解决这个问题，我们研究了损失加权策略如何在MR图像上处理具有不同类别不平衡情况的脑结构分割任务。在这项研究中，我们采用的分割任务的大脑，小脑，脑干，血管MR脑池造影和血管造影图像作为目标分割任务。我们使用具有交叉熵和Dice损失函数的U-网络架构作为基线，并评估了以下损失加权策略的效果：逆频率加权、中值逆频率加权、焦点加权、基于距离图的加权和基于距离惩罚项的加权。在实验中，焦点加权的Dice损失函数表现出最好的性能，在二值分割任务中具有92.8%的高平均Dice得分，而基于距离图加权的交叉熵损失函数在多类分割任务中实现了高达93.1%的Dice得分。结果表明，基于距离图和焦点权重可以提高交叉熵和Dice损失函数在类不平衡分割任务中的性能。
Brain structure segmentation on magnetic resonance (MR) images is important for various clinical applications. It has been automatically performed by using fully convolutional networks. However, it suffers from the class imbalance problem. To address this problem, we investigated how loss weighting strategies work for brain structure segmentation tasks with different class imbalance situations on MR images. In this study, we adopted segmentation tasks of the cerebrum, cerebellum, brainstem, and blood vessels from MR cisternography and angiography images as the target segmentation tasks. We used a U-net architecture with cross-entropy and Dice loss functions as a baseline and evaluated the effect of the following loss weighting strategies: inverse frequency weighting, median inverse frequency weighting, focal weighting, distance map-based weighting, and distance penalty term-based weighting. In the experiments, the Dice loss function with focal weighting showed the best performance and had a high average Dice score of 92.8% in the binary-class segmentation tasks, while the cross-entropy loss functions with distance map-based weighting achieved the Dice score of up to 93.1% in the multi-class segmentation tasks. The results suggested that the distance map-based and the focal weightings could boost the performance of cross-entropy and Dice loss functions in class imbalanced segmentation tasks, respectively.
登录
查看更多内容
DOI：
10.1007/978-3-319-67558-9_28
发表时间：
2017-09-09
期刊：
Deep learning in medical image analysis and multimodal learning for clinical decision support : Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, held in conjunction with MICCAI 2017 Quebec City, QC,..
影响因子：
--
作者：
Sudre CH;Li W;Vercauteren T;Ourselin S;Jorge Cardoso M
通讯作者：
Jorge Cardoso M
影响因子：
5.7
作者：
Huo, Yuankai;Xu, Zhoubing;Landman, Bennett A.
通讯作者：
Landman, Bennett A.
影响因子：
--
作者：
Despotović I;Goossens B;Philips W
通讯作者：
Philips W
影响因子：
10.6
作者：
Karimi, Davood;Salcudean, Septimiu E.
通讯作者：
Salcudean, Septimiu E.
影响因子：
5
作者：
Chawla, NV;Bowyer, KW;Kegelmeyer, WP
通讯作者：
Kegelmeyer, WP