Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Hugo J. W. L. Aerts; Emmanuel Rios Velazquez; Ralph T. H. Leijenaar; Chintan Parmar; Patrick Grossmann; Sara Cavalho; Johan Bussink; Rene Monshouwer; Benjamin Haibe-Kains; Derek Rietveld; Frank Hoebers; Michelle M. Rietbergen; C. Rene Leemans; Andre Dekker; John Quackenbush; Robert J. Gillies; Philippe Lambin

doi:10.1038/ncomms5006

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Hugo J. W. L. Aerts^*
, Emmanuel Rios Velazquez
, Ralph T. H. Leijenaar
, Chintan Parmar
, Patrick Grossmann
, Sara Cavalho
, Johan Bussink
, Rene Monshouwer
, Benjamin Haibe-Kains
, Derek Rietveld
, Frank Hoebers
, Michelle M. Rietbergen
, C. Rene Leemans
, Andre Dekker
, John Quackenbush
, Robert J. Gillies
, Philippe Lambin

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

uman cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.

Original language	English
Article number	4006
Journal	Nature Communications
Volume	5
DOIs	https://doi.org/10.1038/ncomms5006
Publication status	Published - Jun 2014

Access to Document

10.1038/ncomms5006Licence: CC BY-NC-ND

NSCLC-Radiomics-Genomics
Aerts, H. J. W. L. (Contributor), Rios Velazquez, E. (Contributor), Leijenaar, R. (Contributor), Parmar, C. (Contributor), Grossmann, P. (Contributor), Botelho de Carvalho, S. (Contributor), Bussink, J. (Contributor), Monshouwer, R. (Contributor), Haibe-Kains, B. (Contributor), Rietveld, D. (Contributor), Hoebers, F. (Contributor), Rietbergen, M. M. (Contributor), Leemans, C. R. (Contributor), Dekker, A. (Contributor), Quackenbush, J. (Contributor), Gillies, R. J. (Contributor) & Lambin, P. (Contributor), The Cancer Imaging Archive, 2014
DOI: 10.7937/k9/tcia.2015.l4fret6z
Dataset/Software: Dataset
NSCLC-Radiomics
Rios Velazquez, E. (Contributor), Lambin, P. (Contributor), Rietbergen, M. M. (Contributor), Botelho de Carvalho, S. (Contributor), Monshouwer, R. (Contributor), Grossmann, P. (Contributor), Haibe-Kains, B. (Contributor), Bussink, J. (Contributor), Quackenbush, J. (Contributor), Rietveld, D. (Contributor), Parmar, C. (Contributor), Leijenaar, R. (Contributor), Dekker, A. (Contributor), Leemans, C. R. (Contributor), Hoebers, F. (Contributor), Gillies, R. J. (Contributor) & Aerts, H. J. W. L. (Contributor), The Cancer Imaging Archive, 2014
DOI: 10.7937/k9/tcia.2015.pf0m9rei
Dataset/Software: Dataset

Cite this

Aerts, H. J. W. L., Velazquez, E. R., Leijenaar, R. T. H., Parmar, C., Grossmann, P., Cavalho, S., Bussink, J., Monshouwer, R., Haibe-Kains, B., Rietveld, D., Hoebers, F., Rietbergen, M. M., Leemans, C. R., Dekker, A., Quackenbush, J., Gillies, R. J., & Lambin, P. (2014). Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications, 5, Article 4006. https://doi.org/10.1038/ncomms5006

@article{e0d5efc960924712a82df4620340546c,

title = "Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach",

abstract = "uman cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.",

author = "Aerts, \{Hugo J. W. L.\} and Velazquez, \{Emmanuel Rios\} and Leijenaar, \{Ralph T. H.\} and Chintan Parmar and Patrick Grossmann and Sara Cavalho and Johan Bussink and Rene Monshouwer and Benjamin Haibe-Kains and Derek Rietveld and Frank Hoebers and Rietbergen, \{Michelle M.\} and Leemans, \{C. Rene\} and Andre Dekker and John Quackenbush and Gillies, \{Robert J.\} and Philippe Lambin",

year = "2014",

month = jun,

doi = "10.1038/ncomms5006",

language = "English",

volume = "5",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Research",

}

Aerts, HJWL, Velazquez, ER, Leijenaar, RTH, Parmar, C, Grossmann, P, Cavalho, S, Bussink, J, Monshouwer, R, Haibe-Kains, B, Rietveld, D, Hoebers, F, Rietbergen, MM, Leemans, CR, Dekker, A, Quackenbush, J, Gillies, RJ & Lambin, P 2014, 'Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach', Nature Communications, vol. 5, 4006. https://doi.org/10.1038/ncomms5006

TY - JOUR

T1 - Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

AU - Aerts, Hugo J. W. L.

AU - Velazquez, Emmanuel Rios

AU - Leijenaar, Ralph T. H.

AU - Parmar, Chintan

AU - Grossmann, Patrick

AU - Cavalho, Sara

AU - Bussink, Johan

AU - Monshouwer, Rene

AU - Haibe-Kains, Benjamin

AU - Rietveld, Derek

AU - Hoebers, Frank

AU - Rietbergen, Michelle M.

AU - Leemans, C. Rene

AU - Dekker, Andre

AU - Quackenbush, John

AU - Gillies, Robert J.

AU - Lambin, Philippe

PY - 2014/6

Y1 - 2014/6

N2 - uman cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.

AB - uman cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost.

U2 - 10.1038/ncomms5006

DO - 10.1038/ncomms5006

M3 - Article

SN - 2041-1723

VL - 5

JO - Nature Communications

JF - Nature Communications

M1 - 4006

ER -

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Abstract

Access to Document

Fingerprint

Datasets

NSCLC-Radiomics-Genomics

NSCLC-Radiomics

Cite this