一种用于医学图像非配对循环翻译的严格有界深度网络
A Strictly Bounded Deep Network for Unpaired Cyclic Translation of Medical Images
AI总结：
针对医学图像翻译不适定问题，提出嵌入自适应字典学习的patch级拼接循环条件GAN，通过跨邻域上下文特征约束翻译空间，在真实CT和MRI数据上取得优异的双向翻译效果。
摘要：
医学图像翻译是一个不适定问题。与现有的基于配对数据的无界单向翻译网络不同，本文针对非配对医学图像，提出了一种可实现稳定双向翻译的严格有界网络。我们提出了嵌入自适应字典学习的patch级拼接循环条件生成对抗网络（pCCGAN）。该网络由两个循环连接的条件生成对抗网络（CGAN）组成，每个CGAN包含47层；其中两个生成器（各32层）均以同一器官的输入模态与目标模态图像（非真值）的交替非配对图像块拼接结果作为条件。核心思路是利用跨邻域上下文特征信息约束翻译空间并提升泛化能力。生成器还配备了从上下文图像块中学习到的自适应字典，以减少可能的退化。判别器为15层深度网络，采用极小极大函数验证翻译图像。我们构建了包含对抗损失、非对抗损失、前向后向循环损失和身份损失的组合损失函数，进一步降低所提学习机的方差。定性、定量及消融实验表明，该方法在真实CT和MRI数据上取得了优异结果。
英文摘要：
Medical image translation is an ill-posed problem. Unlike existing paired unbounded unidirectional translation networks, in this paper, we consider unpaired medical images and provide a strictly bounded network that yields a stable bidirectional translation. We propose a patch-level concatenated cyclic conditional generative adversarial network (pCCGAN) embedded with adaptive dictionary learning. It consists of two cyclically connected CGANs of 47 layers each; where both generators (each of 32 layers) are conditioned with concatenation of alternate unpaired patches from input and target modality images (not ground truth) of the same organ. The key idea is to exploit cross-neighborhood contextual feature information that bounds the translation space and boosts generalization. The generators are further equipped with adaptive dictionaries learned from the contextual patches to reduce possible degradation. Discriminators are 15-layer deep networks that employ minimax function to validate the translated imagery. A combined loss function is formulated with adversarial, non-adversarial, forward-backward cyclic, and identity losses that further minimize the variance of the proposed learning machine. Qualitative, quantitative, and ablation analysis show superior results on real CT and MRI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
