CoChat

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

Open access

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

Human 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/ncomms5006

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Extracting radiomics data from images. (a) Tumours are different. Example computed tomography (CT) images of lung cancer patients. CT images with tumour contours left, three-dimensional visualizations right. Please note strong phenotypic differences that can be captured with routine CT imaging, such as intratumour heterogeneity and tumour shape. (b) Strategy for extracting radiomics data from images. (I) Experienced physicians contour the tumour areas on all CT slices. (II) Features are extracted from within the defined tumour contours on the CT images, quantifying tumour intensity, shape, texture and wavelet texture. (III) For the analysis the radiomics features are compared with clinical data and gene-expression data.
Figure 1 Extracting radiomics data from images. (a) Tumours are different. Example computed tomography (CT) images of lung cancer patients. CT images with tumour contours left, three-dimensional visualizations right. Please note strong phenotypic differences that can be captured with routine CT imaging, such as intratumour heterogeneity and tumour shape. (b) Strategy for extracting radiomics data from images. (I) Experienced physicians contour the tumour areas on all CT slices. (II) Features are extracted from within the defined tumour contours on the CT images, quantifying tumour intensity, shape, texture and wavelet texture. (III) For the analysis the radiomics features are compared with clinical data and gene-expression data.CC BY-NC-ND · PubMed Central
Figure 2 Analysis workflow. The defined radiomic features algorithms were applied to seven different data sets. Two data sets were used to calculate the feature stability ranks, RIDER test/retest and multiple delineation respectively (both orange). The Lung1 data set, containing data of 422 non-small cell lung cancer (NSCLC) patients, was used as training data set. Lung2 (n=225), H&N1 (n=136) and H&N2 (n=95) were used as validation data sets. The Lung3 data set (n=89) was used for association of the radiomic signature with gene expression profiles. For the multivariate analysis, only one fixed four-feature radiomic signature was tested in the validation data sets.
Figure 2 Analysis workflow. The defined radiomic features algorithms were applied to seven different data sets. Two data sets were used to calculate the feature stability ranks, RIDER test/retest and multiple delineation respectively (both orange). The Lung1 data set, containing data of 422 non-small cell lung cancer (NSCLC) patients, was used as training data set. Lung2 (n=225), H&N1 (n=136) and H&N2 (n=95) were used as validation data sets. The Lung3 data set (n=89) was used for association of the radiomic signature with gene expression profiles. For the multivariate analysis, only one fixed four-feature radiomic signature was tested in the validation data sets.CC BY-NC-ND · PubMed Central
Figure 3 Radiomics heat map. (a) Unsupervised clustering of lung cancer patients (Lung1 set, n=422) on the y axis and radiomic feature expression (n=440) on the x axis, revealed clusters of patients with similar radiomic expression patterns. (b) Clinical patient parameters for showing significant association of the radiomic expression patterns with primary tumour stage (T-stage; P<1 × 10−20, χ2 test), overall stage (P=3.4 × 10−3, χ2 test) and histology (P=0.019, χ2 test). (c) Correspondence of radiomic feature groups with the clustered expression patterns.
Figure 3 Radiomics heat map. (a) Unsupervised clustering of lung cancer patients (Lung1 set, n=422) on the y axis and radiomic feature expression (n=440) on the x axis, revealed clusters of patients with similar radiomic expression patterns. (b) Clinical patient parameters for showing significant association of the radiomic expression patterns with primary tumour stage (T-stage; P<1 × 10−20, χ2 test), overall stage (P=3.4 × 10−3, χ2 test) and histology (P=0.019, χ2 test). (c) Correspondence of radiomic feature groups with the clustered expression patterns.CC BY-NC-ND · PubMed Central
Figure 4 Prognostic performance and gene-expression association of the radiomics signature. (a) Radiomic signature performance. Kaplan–Meier curves demonstrating performance of the radiomic signature on the lung cancer data sets (left) and the head-and-neck cancer data sets (right). The signature was built on the Lung1 data (n=422). The signature had a good performance in the Lung2 (CI=0.65, P=2.91 × 10−09, Wilcoxon test, n=225), and a high performance in H&N1 (CI=0.69, P=7.99 × 10−07, Wilcoxon test, n=136) and H&N2 (CI=0.69, P=3.53 × 10−06, Wilcoxon test, n=95) validation data sets. (b) Association of radiomic signature features and gene expression using gene-set enrichment analysis (GSEA) in the Lung3 data set (n=89). Gene sets that have been significantly enriched (FDR=20%) for at least one of the four radiomic features are indicated with an asterisk. The corresponding normalized enrichment scores (NES), GSEA’s primary statistic, for all radiomic signature features is displayed in a heat map, where light blue means low and dark blue means high NES.
Figure 4 Prognostic performance and gene-expression association of the radiomics signature. (a) Radiomic signature performance. Kaplan–Meier curves demonstrating performance of the radiomic signature on the lung cancer data sets (left) and the head-and-neck cancer data sets (right). The signature was built on the Lung1 data (n=422). The signature had a good performance in the Lung2 (CI=0.65, P=2.91 × 10−09, Wilcoxon test, n=225), and a high performance in H&N1 (CI=0.69, P=7.99 × 10−07, Wilcoxon test, n=136) and H&N2 (CI=0.69, P=3.53 × 10−06, Wilcoxon test, n=95) validation data sets. (b) Association of radiomic signature features and gene expression using gene-set enrichment analysis (GSEA) in the Lung3 data set (n=89). Gene sets that have been significantly enriched (FDR=20%) for at least one of the four radiomic features are indicated with an asterisk. The corresponding normalized enrichment scores (NES), GSEA’s primary statistic, for all radiomic signature features is displayed in a heat map, where light blue means low and dark blue means high NES.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

3 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 29 references

Cited by

Items 201–300 of 1,023

Metadata

Authors
Aerts, H. J. W. L., Velazquez, E. R., Leijenaar, R. T. H., Parmar, C., Grossmann, P., Carvalho, 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.
Affiliations
  • Brigham and Women's Hospital (US)
  • Maastricht University (NL)
  • Radboud University Medical Center (NL)
  • Amsterdam UMC Location Vrije Universiteit Amsterdam (NL)
  • Dana-Farber Cancer Institute (US)
  • Moffitt Cancer Center (US)
Corresponding author
Aerts, Hugo J. W. L.
Venue
Nature Communications
Published
2014-06-03
Volume
5
Issue
1
Pages
4006-4006
ISSN
2041-1723 (ISSN-L)
OpenAlex
W2103004421
Cited by
5,132
References
29
Citations by year
2026: 415 · 2025: 460 · 2024: 458 · 2023: 510 · 2022: 567 · 2021: 638 · 2020: 587 · 2019: 552 · 2018: 388 · 2017: 283 · 2016: 175 · 2015: 82 · 2014: 11
FWCI
142.84
Type
journal article
Language
en
Open access
Locations
  • Nature Communications (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • Pure Amsterdam UMC (publishedVersion)
  • Amsterdam UMC (VU Amsterdam) - Institutional Repository (publishedVersion)
  • Radboud Repository (Radboud University) (submittedVersion)
  • Digital Access to Scholarship at Harvard (DASH) (Harvard University) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • Research Publications (Maastricht University) (submittedVersion, cc-by-nc-nd)
  • Radboud Repository (Radboud University) (submittedVersion, other-oa)
  • Research Publications (Maastricht University) (submittedVersion, other-oa)
  • Data Archiving and Networked Services (DANS) (submittedVersion)
Funders
  • European Federation of Pharmaceutical Industries and Associations
  • KWF Kankerbestrijding (UM 2009-4454, 2011-5020, KWF UM 2009-4454, KWF UM 2011-5020, 2009-4454)
  • Center for Translational Molecular Medicine (grant 030-103, 030-103)
  • Innovative Medicines Initiative (115151)
  • National Institutes of Health (U01 CA)
  • National Cancer Institute (NIH-USA U01CA 143062-01, U01CA143062)
  • Interreg
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Medical Imaging Techniques and Applications
Keywords
radiomics, tumor phenotype, lung cancer, head and neck cancer, radiogenomics, intratumoral heterogeneity, computed tomography, image texture features, gene expression, non-invasive imaging, treatment decision support
MeSH terms
Adenocarcinoma, Carcinoma, Non-Small-Cell Lung, Carcinoma, Squamous Cell, Female, Head and Neck Neoplasms, Humans, Lung Neoplasms, Male, Phenotype, Prognosis, Tomography, X-Ray Computed, Tumor Burden, Positron-Emission Tomography, Multimodal Imaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.