arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.08871stat.MLcs.CVcs.LGeess.IV
收藏

个性化多层张量学习及其在图像分析中的应用

Individualized Multilayer Tensor Learning with An Application in Imaging Analysis

University of Virginia(弗吉尼亚大学);University of Minnesota(明尼苏达大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Xiwei Tang, Xuan Bi, Annie Qu

摘要:

这项工作的动机是多模态乳腺癌成像数据,这是相当具有挑战性的,因为离散的肿瘤相关微泡(TMV)的信号随机分布的异质模式。这对假设同质特征结构的常规成像回归和降维模型提出了重大挑战。我们开发了一种创新的多层张量学习方法,将异质性纳入高阶张量分解,并通过利用受试者成像特征和多模态信息有效地预测疾病状态。具体来说,我们构建了一个多层分解,它利用了个性化的成像层,除了模态特定的张量结构。我们的方法的一个主要优点是,我们能够有效地捕捉信号的异构空间特征,其特征不在于人口结构,以及同时整合多模态信息。为了实现可扩展计算,我们开发了一种新的双层块改进算法。在理论上,我们研究了算法的收敛性,张量信号恢复误差界和预测模型估计的渐近一致性。我们也适用于模拟和人类乳腺癌成像数据所提出的方法。数值结果表明,所提出的方法优于其他现有的竞争方法。

英文摘要:

This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles (TMVs) are randomly distributed with heterogeneous patterns. This imposes a significant challenge for conventional imaging regression and dimension reduction models assuming a homogeneous feature structure. We develop an innovative multilayer tensor learning method to incorporate heterogeneity to a higher-order tensor decomposition and predict disease status effectively through utilizing subject-wise imaging features and multimodality information. Specifically, we construct a multilayer decomposition which leverages an individualized imaging layer in addition to a modality-specific tensor structure. One major advantage of our approach is that we are able to efficiently capture the heterogeneous spatial features of signals that are not characterized by a population structure as well as integrating multimodality information simultaneously. To achieve scalable computing, we develop a new bi-level block improvement algorithm. In theory, we investigate both the algorithm convergence property, tensor signal recovery error bound and asymptotic consistency for prediction model estimation. We also apply the proposed method for simulated and human breast cancer imaging data. Numerical results demonstrate that the proposed method outperforms other existing competing methods.

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。

↑