arXiv 2111.139872021-11-27cs.LGeess.SPq-bio.QMstat.AP

使用典型相关分析方法的多模态融合：在组织学和基因组学乳腺癌生存预测中的应用

Multi-modality fusion using canonical correlation analysis methods: Application in breast cancer survival prediction from histology and genomics

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Almaden Research Center（IBM阿尔马登研究中心）

Vaishnavi Subramanian, Tanveer Syeda-Mahmood, Minh N. Do

备注：: This work has been submitted to the IEEE for possible publication

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于惩罚典型相关分析与矩阵收缩的双模态融合及两阶段预测流程，提升潜变量预测，并在乳腺癌组织学与基因组数据中优于同维 PCA。

摘要：

多模态数据集的可用性，为利用多个视角更全面地表征同一关注对象提供了独特机会。在本研究中，我们研究了使用典型相关分析（CCA）及其惩罚变体（pCCA）来融合两种模态。我们研究了一个用于生成双模态数据的简单图形模型。我们通过分析表明，在模型参数已知的情况下，联合使用两种模态的后验均值估计器在潜变量预测中优于单模态后验估计器的任意线性混合。结合领域知识的 CCA 惩罚扩展（pCCA）能够在高维、小样本数据中发现相关性，而传统 CCA 则无法适用。为便于利用 pCCA 生成多维嵌入，我们提出了两种矩阵收缩方案，用于强制实现 CCA 所展现的理想性质。综合上述内容，我们提出了一种使用经收缩生成的 pCCA 嵌入进行潜变量预测的两阶段预测流程。在模拟数据上，我们提出的模型显著降低了潜变量预测的均方误差。当应用于来自癌症基因组图谱（TCGA）乳腺癌患者的公开组织病理学数据和 RNA 测序数据时，我们的模型在生存预测中能够优于相同维度的主成分分析（PCA）嵌入。

英文摘要：

The availability of multi-modality datasets provides a unique opportunity to characterize the same object of interest using multiple viewpoints more comprehensively. In this work, we investigate the use of canonical correlation analysis (CCA) and penalized variants of CCA (pCCA) for the fusion of two modalities. We study a simple graphical model for the generation of two-modality data. We analytically show that, with known model parameters, posterior mean estimators that jointly use both modalities outperform arbitrary linear mixing of single modality posterior estimators in latent variable prediction. Penalized extensions of CCA (pCCA) that incorporate domain knowledge can discover correlations with high-dimensional, low-sample data, whereas traditional CCA is inapplicable. To facilitate the generation of multi-dimensional embeddings with pCCA, we propose two matrix deflation schemes that enforce desirable properties exhibited by CCA. We propose a two-stage prediction pipeline using pCCA embeddings generated with deflation for latent variable prediction by combining all the above. On simulated data, our proposed model drastically reduces the mean-squared error in latent variable prediction. When applied to publicly available histopathology data and RNA-sequencing data from The Cancer Genome Atlas (TCGA) breast cancer patients, our model can outperform principal components analysis (PCA) embeddings of the same dimension in survival prediction.

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。