Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer

Hong Jun Yoon; Arvind Ramanathan; Folami Alamudun; Georgia Tourassi

doi:10.1117/12.2318508

Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer

Hong Jun Yoon
, Arvind Ramanathan
, Folami Alamudun
, Georgia Tourassi

Biostatistics and Biomedical Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

9 Scopus citations

Abstract

Integration of heterogeneous data from different modalities such as genomics and radiomics is a growing area of research expected to generate better prediction of clinical outcomes in comparison with single modality approaches. To date radiogenomics studies have focused primarily on investigating correlations between genomic and radiomic features, or selection of salient features to determine clinical tumor phenotype. In this study, we designed deep neural networks (DNN), which combine both radiomic and genomic features to predict pathological stage and molecular receptor status of invasive breast cancer patients. Utilizing imaging data from The Cancer Imaging Archive (TCIA) and gene expression data from The Cancer Genome Atlas (TCGA), we evaluated the predictive power of Convolutional Neural Networks (CNN). Overall, results suggest superior performance on CNNs leveraging radiogenomics in comparison with CNNs trained on single modality data sources.

Original language	English
Title of host publication	14th International Workshop on Breast Imaging (IWBI 2018)
Editors	Elizabeth A. Krupinski
Publisher	SPIE
ISBN (Electronic)	9781510620070
DOIs	https://doi.org/10.1117/12.2318508
State	Published - 2018
Event	14th International Workshop on Breast Imaging (IWBI 2018) - Atlanta, United States Duration: Jul 8 2018 → Jul 11 2018

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10718
ISSN (Print)	1605-7422

Conference

Conference	14th International Workshop on Breast Imaging (IWBI 2018)
Country/Territory	United States
City	Atlanta
Period	07/8/18 → 07/11/18

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Keywords

convolutional neural networks
deep learning
gene expression
genomics
phenotypes
radiogenomics
radiomics

Access to Document

10.1117/12.2318508

Cite this

@inproceedings{49771fe4e7d8475bac15413ee4a654f5,

title = "Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer",

abstract = "Integration of heterogeneous data from different modalities such as genomics and radiomics is a growing area of research expected to generate better prediction of clinical outcomes in comparison with single modality approaches. To date radiogenomics studies have focused primarily on investigating correlations between genomic and radiomic features, or selection of salient features to determine clinical tumor phenotype. In this study, we designed deep neural networks (DNN), which combine both radiomic and genomic features to predict pathological stage and molecular receptor status of invasive breast cancer patients. Utilizing imaging data from The Cancer Imaging Archive (TCIA) and gene expression data from The Cancer Genome Atlas (TCGA), we evaluated the predictive power of Convolutional Neural Networks (CNN). Overall, results suggest superior performance on CNNs leveraging radiogenomics in comparison with CNNs trained on single modality data sources.",

keywords = "convolutional neural networks, deep learning, gene expression, genomics, phenotypes, radiogenomics, radiomics",

author = "Yoon, \{Hong Jun\} and Arvind Ramanathan and Folami Alamudun and Georgia Tourassi",

note = "Publisher Copyright: {\textcopyright} 2018 SPIE.; 14th International Workshop on Breast Imaging (IWBI 2018) ; Conference date: 08-07-2018 Through 11-07-2018",

year = "2018",

doi = "10.1117/12.2318508",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Krupinski, \{Elizabeth A.\}",

booktitle = "14th International Workshop on Breast Imaging (IWBI 2018)",

}

Yoon, HJ, Ramanathan, A, Alamudun, F & Tourassi, G 2018, Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer. in EA Krupinski (ed.), 14th International Workshop on Breast Imaging (IWBI 2018)., 107181H, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10718, SPIE, 14th International Workshop on Breast Imaging (IWBI 2018), Atlanta, United States, 07/8/18. https://doi.org/10.1117/12.2318508

Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer. / Yoon, Hong Jun; Ramanathan, Arvind; Alamudun, Folami et al.
14th International Workshop on Breast Imaging (IWBI 2018). ed. / Elizabeth A. Krupinski. SPIE, 2018. 107181H (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10718).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer

AU - Yoon, Hong Jun

AU - Ramanathan, Arvind

AU - Alamudun, Folami

AU - Tourassi, Georgia

PY - 2018

Y1 - 2018

N2 - Integration of heterogeneous data from different modalities such as genomics and radiomics is a growing area of research expected to generate better prediction of clinical outcomes in comparison with single modality approaches. To date radiogenomics studies have focused primarily on investigating correlations between genomic and radiomic features, or selection of salient features to determine clinical tumor phenotype. In this study, we designed deep neural networks (DNN), which combine both radiomic and genomic features to predict pathological stage and molecular receptor status of invasive breast cancer patients. Utilizing imaging data from The Cancer Imaging Archive (TCIA) and gene expression data from The Cancer Genome Atlas (TCGA), we evaluated the predictive power of Convolutional Neural Networks (CNN). Overall, results suggest superior performance on CNNs leveraging radiogenomics in comparison with CNNs trained on single modality data sources.

AB - Integration of heterogeneous data from different modalities such as genomics and radiomics is a growing area of research expected to generate better prediction of clinical outcomes in comparison with single modality approaches. To date radiogenomics studies have focused primarily on investigating correlations between genomic and radiomic features, or selection of salient features to determine clinical tumor phenotype. In this study, we designed deep neural networks (DNN), which combine both radiomic and genomic features to predict pathological stage and molecular receptor status of invasive breast cancer patients. Utilizing imaging data from The Cancer Imaging Archive (TCIA) and gene expression data from The Cancer Genome Atlas (TCGA), we evaluated the predictive power of Convolutional Neural Networks (CNN). Overall, results suggest superior performance on CNNs leveraging radiogenomics in comparison with CNNs trained on single modality data sources.

KW - convolutional neural networks

KW - deep learning

KW - gene expression

KW - genomics

KW - phenotypes

KW - radiogenomics

KW - radiomics

UR - https://www.scopus.com/pages/publications/85050246994

U2 - 10.1117/12.2318508

DO - 10.1117/12.2318508

M3 - Conference contribution

AN - SCOPUS:85050246994

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - 14th International Workshop on Breast Imaging (IWBI 2018)

A2 - Krupinski, Elizabeth A.

PB - SPIE

T2 - 14th International Workshop on Breast Imaging (IWBI 2018)

Y2 - 8 July 2018 through 11 July 2018

ER -

Deep radiogenomics for predicting clinical phenotypes in invasive breast cancer

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this