基于无监督多元规范CSC $\ell_4$网的脑图像合成
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net
摘要：
神经科学的最新进展突出了多模态医学数据在研究某些病理和理解人类认知方面的有效性。然而，获得不同模态的完整集合受到各种因素的限制，诸如长采集时间、高检查成本和伪影抑制。此外，神经成像数据的复杂性、高维性和异质性仍然是有效利用现有随机扫描的另一个关键挑战，因为不同机器通常会以不同的方式测量相同模态的数据。显然需要超越传统的依赖成像的过程，并从源输入合成解剖学上特定的目标模态数据。在本文中，我们建议使用一种新的CSC $\ell_4$ Net来学习跨模态内和模态内变化的专用功能。通过初始统一的模态内数据的特征映射和多变量规范的适应，CSC $\ell_4$ Net有利于特征级的相互转换。正定黎曼流形惩罚数据保真度项进一步使CSC $\ell_4$ Net能够根据变换的特征重建缺失的测量。最后，最大化$\ell_4$ -范数归结为计算上有效的优化问题。大量的实验验证了我们的CSC $\ell_4$ Net的能力和鲁棒性相比，国家的最先进的方法在多个数据集。
英文摘要：
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obtaining full sets of different modalities is limited by various factors, such as long acquisition times, high examination costs and artifact suppression. In addition, the complexity, high dimensionality and heterogeneity of neuroimaging data remains another key challenge in leveraging existing randomized scans effectively, as data of the same modality is often measured differently by different machines. There is a clear need to go beyond the traditional imaging-dependent process and synthesize anatomically specific target-modality data from a source input. In this paper, we propose to learn dedicated features that cross both intre- and intra-modal variations using a novel CSC$\ell_4$Net. Through an initial unification of intra-modal data in the feature maps and multivariate canonical adaptation, CSC$\ell_4$Net facilitates feature-level mutual transformation. The positive definite Riemannian manifold-penalized data fidelity term further enables CSC$\ell_4$Net to reconstruct missing measurements according to transformed features. Finally, the maximization $\ell_4$-norm boils down to a computationally efficient optimization problem. Extensive experiments validate the ability and robustness of our CSC$\ell_4$Net compared to the state-of-the-art methods on multiple datasets.
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。
