FAS-UNet: A Novel FAS-Driven UNet to Learn Variational Image Segmentation
FAS-UNet: A Novel FAS-Driven UNet to Learn Variational Image Segmentation
复制标题
DOI：
10.3390/math10214055
复制
发表时间：
2022-11-01
期刊：
影响因子：
2.4
通讯作者：
Zhang, Jianping
中科院分区：
文献类型：
--
作者：
Zhu, Hui;Shu, Shi;Zhang, Jianping
解决具有隐藏物理的变分图像分割问题通常是昂贵的，并且需要不同的算法和手动调整的模型参数。基于UNet结构的深度学习方法在许多不同的医学图像分割任务中获得了出色的性能，但设计此类网络需要许多参数和训练数据，这些参数和训练数据并不总是可用于实际问题。本文受传统的多相凸性Mumford-Shah变分模型和求解非线性系统的完全逼近方案（FAS）的启发，提出了一种新型的变分模型信息网络（FAS-UNet），该网络利用模型和算法先验知识来提取多尺度特征。所提出的模型通知网络集成了图像数据和数学模型，并通过学习一些卷积核来实现它们。基于变分理论和FAS算法，我们首先设计了一个特征提取子网络（FAS-Solution模块）来求解模型驱动的非线性系统，其中采用跳跃连接来融合多尺度特征。其次，我们进一步设计了一个卷积块来融合前一阶段提取的特征，从而产生最终的分割可能性。三个不同的医学图像分割任务的实验结果表明，所提出的FAS-UNet是非常有竞争力的定性，定量和模型的复杂性评价与其他国家的最先进的方法。此外，还可以训练自动满足其他图像问题中的一些数学和物理定律的专用网络架构，以获得更好的准确性，更快的训练和改进的泛化。
Solving variational image segmentation problems with hidden physics is often expensive and requires different algorithms and manually tuned model parameters. The deep learning methods based on the UNet structure have obtained outstanding performances in many different medical image segmentation tasks, but designing such networks requires many parameters and training data, which are not always available for practical problems. In this paper, inspired by the traditional multiphase convexity Mumford-Shah variational model and full approximation scheme (FAS) solving the nonlinear systems, we propose a novel variational-model-informed network (FAS-UNet), which exploits the model and algorithm priors to extract the multiscale features. The proposed model-informed network integrates image data and mathematical models and implements them through learning a few convolution kernels. Based on the variational theory and FAS algorithm, we first design a feature extraction sub-network (FAS-Solution module) to solve the model-driven nonlinear systems, where a skip-connection is employed to fuse the multiscale features. Secondly, we further design a convolutional block to fuse the extracted features from the previous stage, resulting in the final segmentation possibility. Experimental results on three different medical image segmentation tasks show that the proposed FAS-UNet is very competitive with other state-of-the-art methods in the qualitative, quantitative, and model complexity evaluations. Moreover, it may also be possible to train specialized network architectures that automatically satisfy some of the mathematical and physical laws in other image problems for better accuracy, faster training, and improved generalization.