Heterogeneous Feature Integration for Regression in Multimodal Healthcare Applications

Search for this publication on Google Scholar
Tavakoli Hosseinabadi, M. (2020). Heterogeneous Feature Integration for Regression in Multimodal Healthcare Applications. Unc Charlotte Electronic Theses And Dissertations.
Download PDF

Analytics

55 views ◎
39 downloads ⇓


Abstract

The increasing performance of feature extraction and regression modeling in various domains raises the hope for machine and deep learning to assist clinicians in numerous healthcare applications. However, the complex and multimodal nature of the problems and the scarce resource of high-quality labeled data in this domain introduces several challenges and limitations. These challenges, along with lack of interpretability, undermines the generalizability and usability of many state-of-the-art machine learning models.This dissertation focuses on using multimodal sources of data for regression modeling in healthcare applications. The argument is that domain knowledge describes the nature of each modality's relationship with the target function. This relationship can characterize the appropriate level of representation and an efficient integration method. We define a framework with two heterogeneous modalities; one modality provides more local features, while another contains higher-level global information. We demonstrate the framework's applicability for multiple healthcare regression tasks. In this framework, we propose a pipeline for incorporating domain knowledge in designing an effective integration model. Particularly, we suggest two approaches for increasing the performance in the absence of large-scale data: leveraging the modality representations' abstraction based on domain knowledge and a tree-structure convolutional neural network for integrating the information from the heterogeneous modalities. This framework is discussed in more detail for two different cases of "radiation therapy treatment planning" and "Alzheimer's disease progression prediction." The former predicts a two-dimensional using the leveraged representation, the latter evaluates the whole pipeline for predicting a scalar target variable. The performance is compared with the previous submissions for the same dataset; it outperforms the best-reported results.

Details
Author

Tavakoli Hosseinabadi, Maryam

Title

Heterogeneous Feature Integration for Regression in Multimodal Healthcare Applications

Physical Description

1 online resource (130 pages) : PDF

Date

2020

Degree Granting Institution

University of North Carolina at Charlotte

Abstract

The increasing performance of feature extraction and regression modeling in various domains raises the hope for machine and deep learning to assist clinicians in numerous healthcare applications. However, the complex and multimodal nature of the problems and the scarce resource of high-quality labeled data in this domain introduces several challenges and limitations. These challenges, along with lack of interpretability, undermines the generalizability and usability of many state-of-the-art machine learning models.This dissertation focuses on using multimodal sources of data for regression modeling in healthcare applications. The argument is that domain knowledge describes the nature of each modality's relationship with the target function. This relationship can characterize the appropriate level of representation and an efficient integration method. We define a framework with two heterogeneous modalities; one modality provides more local features, while another contains higher-level global information. We demonstrate the framework's applicability for multiple healthcare regression tasks. In this framework, we propose a pipeline for incorporating domain knowledge in designing an effective integration model. Particularly, we suggest two approaches for increasing the performance in the absence of large-scale data: leveraging the modality representations' abstraction based on domain knowledge and a tree-structure convolutional neural network for integrating the information from the heterogeneous modalities. This framework is discussed in more detail for two different cases of "radiation therapy treatment planning" and "Alzheimer's disease progression prediction." The former predicts a two-dimensional using the leveraged representation, the latter evaluates the whole pipeline for predicting a scalar target variable. The performance is compared with the previous submissions for the same dataset; it outperforms the best-reported results.

Genre

doctoral dissertations

Subjects--Topics

Computer science
Information science
Diagnostic imaging

Degree

Ph.D.

Keywords

Alzheimer's Disease Progression
Domain Knowledge Incorporation
Heterogeneous Feature Integration
Multimodal Deep Learning
Radiation Treatment Planning
Regression

Subject Area

Information Technology

Advisor(s)

Ge, Yaorong
Hadzikadic, Mirsad

Committee Members

Mousavi, Reza
Dulin, Michael
Zadrozny, Wlodek

Degree Note

Thesis (Ph.D.)--University of North Carolina at Charlotte, 2020.

Rights Statement

This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). For additional information, see http://rightsstatements.org/page/InC/1.0/.

Rights Holder Information

Copyright is held by the author unless otherwise indicated.

Identifier

TavakoliHosseinabadi_uncc_0694D_12577

Permalink

http://hdl.handle.net/20.500.13093/etd:2235