Individualized Multilayer Tensor Learning With an Application in Imaging Analysis

Xiwei Tang, Xuan Bi, Annie Qu

Research output: Contribution to journalArticle

Abstract

This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles 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. Supplementary materials for this article are available online.

Original languageEnglish (US)
JournalJournal of the American Statistical Association
DOIs
StatePublished - Jan 1 2019

Fingerprint

Multilayer
Tensor
Multimodality
Imaging
Breast Cancer
Higher-order Tensor
Tensor Decomposition
Population Structure
Dimension Reduction
Leverage
Convergence Properties
Prediction Model
Modality
Error Bounds
Tumor
Recovery
Regression
Learning
Decompose
Predict

Keywords

  • Cancer imaging
  • Dimension reduction
  • Heterogeneous modeling
  • High-order tensor decomposition
  • Multimodality integration
  • Spatial information

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Individualized Multilayer Tensor Learning With an Application in Imaging Analysis. / Tang, Xiwei; Bi, Xuan; Qu, Annie.

In: Journal of the American Statistical Association, 01.01.2019.

Research output: Contribution to journalArticle

@article{9613b1fb356b48c28fb100a613807818,
title = "Individualized Multilayer Tensor Learning With an Application in Imaging Analysis",
abstract = "This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles 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. Supplementary materials for this article are available online.",
keywords = "Cancer imaging, Dimension reduction, Heterogeneous modeling, High-order tensor decomposition, Multimodality integration, Spatial information",
author = "Xiwei Tang and Xuan Bi and Annie Qu",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/01621459.2019.1585254",
language = "English (US)",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor & Francis",

}

TY - JOUR

T1 - Individualized Multilayer Tensor Learning With an Application in Imaging Analysis

AU - Tang, Xiwei

AU - Bi, Xuan

AU - Qu, Annie

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles 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. Supplementary materials for this article are available online.

AB - This work is motivated by multimodality breast cancer imaging data, which is quite challenging in that the signals of discrete tumor-associated microvesicles 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. Supplementary materials for this article are available online.

KW - Cancer imaging

KW - Dimension reduction

KW - Heterogeneous modeling

KW - High-order tensor decomposition

KW - Multimodality integration

KW - Spatial information

UR - http://www.scopus.com/inward/record.url?scp=85066127272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066127272&partnerID=8YFLogxK

U2 - 10.1080/01621459.2019.1585254

DO - 10.1080/01621459.2019.1585254

M3 - Article

AN - SCOPUS:85066127272

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

ER -