Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Somatic Mutations Drive Distinct Imaging Phenotypes In Lung Cancer.

E. Rios Velazquez, Chintan Parmar, Ying Liu, T. L. Coroller, G. Cruz, O. Stringfield, Z. Ye, M. Makrigiorgos, F. Fennessy, Raymond H. Mak, R. Gillies, John Quackenbush, H. Aerts
Published 2017 · Biology, Medicine

Save to my Library
Download PDF
Analyze on Scholarcy
Share
Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR+ and EGFR- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR+ and KRAS+ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS+/KRAS- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost. Cancer Res; 77(14); 3922-30. ©2017 AACR.
This paper references
10.1007/s00261-017-1072-0
CT-based radiomics signature: a potential biomarker for preoperative prediction of early recurrence in hepatocellular carcinoma
Y. Zhou (2017)
10.1016/j.lungcan.2012.11.007
Radiographic assessment and therapeutic decisions at RECIST progression in EGFR-mutant NSCLC treated with EGFR tyrosine kinase inhibitors.
M. Nishino (2013)
10.1148/radiol.2015151169
Radiomics: Images Are More than Pictures, They Are Data
R. Gillies (2016)
10.1016/j.jtho.2016.07.002
Predicting Malignant Nodules from Screening CT Scans
Samuel H. Hawkins (2016)
10.1038/nm.2323
Cancer genomics: from discovery science to personalized medicine
L. Chin (2011)
10.1371/journal.pone.0161081
Imaging Characteristics of Driver Mutations in EGFR, KRAS, and ALK among Treatment-Naïve Patients with Advanced Lung Adenocarcinoma
Jangchul Park (2016)
10.1088/0031-9155/61/13/R150
Applications and limitations of radiomics.
S. Yip (2016)
Radiomics : images aremore thanpictures , they are data
KinahanPE Gillies RJ (2016)
10.1093/bioinformatics/btr511
survcomp: an R/Bioconductor package for performance assessment and comparison of survival models
Markus S. Schröder (2011)
10.1148/radiol.13130663
Radiogenomics of clear cell renal cell carcinoma: associations between CT imaging features and mutations.
C. Karlo (2014)
10.3389/fonc.2016.00071
Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology
Weimiao Wu (2016)
10.1148/radiol.14140789
ALK molecular phenotype in non-small cell lung cancer: CT radiogenomic characterization.
S. Yamamoto (2014)
10.1117/1.JMI.2.4.041007
Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data
Wentian Guo (2015)
10.1016/j.cllc.2015.11.002
Association Between Computed Tomographic Features and Kirsten Rat Sarcoma Viral Oncogene Mutations in Patients With Stage I Lung Adenocarcinoma and Their Prognostic Value.
H. Wang (2016)
10.1148/radiol.2522081593
Evaluating variability in tumor measurements from same-day repeat CT scans of patients with non-small cell lung cancer.
B. Zhao (2009)
10.1038/nature12627
Tumour heterogeneity in the clinic
P. Bedard (2013)
10.18637/JSS.V025.I01
FactoMineR: An R Package for Multivariate Analysis
S. Lê (2008)
10.1016/J.JTHO.2015.12.008
RADIOMICS ON LUNG CANCER
R. Gillies (2014)
10.1158/0008-5472.CAN-11-3943
Prognostic PET 18F-FDG uptake imaging features are associated with major oncogenomic alterations in patients with resected non-small cell lung cancer.
V. Nair (2012)
10.1016/j.ijrobp.2014.07.020
Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer.
D. Fried (2014)
10.1016/j.radonc.2016.05.024
CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer.
E. Huynh (2016)
Random forests. Mach Learn 2001;45:5–32
L. Breiman (2001)
10.1371/journal.pone.0100244
Noninvasive Image Texture Analysis Differentiates K-ras Mutation from Pan-Wildtype NSCLC and Is Prognostic
G. Weiss (2014)
10.1038/ng.2764
The Cancer Genome Atlas Pan-Cancer analysis project
J. Weinstein (2013)
KinahanPE,HricakH. Radiomics: images aremore thanpictures, they are data. Radiology 2016;278:563–77
RJ Gillies (2016)
Decoding tumor phenotypes for ALK, ROS1, andRET fusions in lung adenocarcinomausing a radiomics approach. Medicine 2015;94:e1753
YoonHJ (2015)
10.1016/J.YONC.2012.07.036
Intratumor Heterogeneity and Branched Evolution Revealed by Multiregion Sequencing
R. Arceci (2012)
10.1200/JCO.2012.45.3753
Genotyping and genomic profiling of non-small-cell lung cancer: implications for current and future therapies.
T. Li (2013)
10.1111/j.1349-7006.2008.00782.x
Intratumor heterogeneity of epidermal growth factor receptor mutations in lung cancer and its correlation to the response to gefitinib
K. Taniguchi (2008)
10.1016/j.ejca.2011.11.036
Radiomics: extracting more information from medical images using advanced feature analysis.
P. Lambin (2012)
10.1016/j.jmoldx.2014.06.004
Prospective enterprise-level molecular genotyping of a cohort of cancer patients.
L. Macconaill (2014)
10.1001/jamaoncol.2016.2631
The Potential of Radiomic-Based Phenotyping in Precision Medicine: A Review.
H. Aerts (2016)
10.1158/0008-5472.CAN-12-2217
Intratumor heterogeneity: evolution through space and time.
C. Swanton (2012)
BallmanKV. Precisiononcology: anoverview
LA Garraway (2013)
Precisiononcology : anoverview
LA Garraway (2013)
10.1038/nm.3388
The quest to overcome resistance to EGFR-targeted therapies in cancer
C. R. Chong (2013)
10.1016/j.cllc.2016.02.001
Radiomic Features Are Associated With EGFR Mutation Status in Lung Adenocarcinomas.
Y. Liu (2016)
10.1371/journal.pone.0007887
Profiling Critical Cancer Gene Mutations in Clinical Tumor Samples
L. Macconaill (2009)
10.1023/A:1010933404324
Random Forests
L. Breiman (2004)
10.2967/jnumed.113.120485
Multifunctional Imaging Signature for V-KI-RAS2 Kirsten Rat Sarcoma Viral Oncogene Homolog (KRAS) Mutations in Colorectal Cancer
K. Miles (2014)
10.1371/journal.pone.0169172
Associations of Radiomic Data Extracted from Static and Respiratory-Gated CT Scans with Disease Recurrence in Lung Cancer Patients Treated with SBRT
E. Huynh (2017)
KungHJ,Mack PC, GandaraDR.Genotyping and genomic profiling of non-small-cell lung cancer: implications for current and future therapies
T Li (2013)
10.2967/jnumed.116.181826
Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non–Small Cell Lung Cancer
S. Yip (2017)
10.1038/ncomms5006
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
H. Aerts (2014)
10.1111/J.2517-6161.1995.TB02031.X
Controlling the false discovery rate: a practical and powerful approach to multiple testing
Y. Benjamini (1995)
10.1016/j.jtho.2016.11.2226
Radiomic‐Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC
T. Coroller (2017)
10.1038/srep13087
Machine Learning methods for Quantitative Radiomic Biomarkers
Chintan Parmar (2015)
10.1038/srep11044
Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer
Chintan Parmar (2015)
10.1007/s00330-014-3516-z
Comparative analysis of clinicoradiologic characteristics of lung adenocarcinomas with ALK rearrangements or EGFR mutations
J. Y. Zhou (2014)
10.1148/radiol.2016151455
CT Features Associated with Epidermal Growth Factor Receptor Mutation Status in Patients with Lung Adenocarcinoma.
Y. Liu (2016)
10.1093/bioinformatics/btu651
Quantifying tumor heterogeneity in whole-genome and whole-exome sequencing data
Layla Oesper (2014)
10.1158/1538-7445.AM2012-3725
Abstract 3725: Combined cytotoxic effects of volasertib and cisplatin in urothelial carcinoma cells
C. Lin (2012)
10.18637/JSS.V025.I14
GEEQBOX: A MATLAB Toolbox for Generalized Estimating Equations and Quasi-Least Squares
S. Ratcliffe (2008)
Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection
Gavin Brown (2012)
10.1097/MD.0000000000001753
Decoding Tumor Phenotypes for ALK, ROS1, and RET Fusions in Lung Adenocarcinoma Using a Radiomics Approach
Hyun Jung Yoon (2015)
10.1371/journal.pone.0019601
Benchmarking of Mutation Diagnostics in Clinical Lung Cancer Specimens
S. Querings (2011)
10.1200/JCO.2005.09.985
Epidermal growth factor receptor mutations in non-small-cell lung cancer: implications for treatment and tumor biology.
P. Jänne (2005)
10.1007/s00330-015-3814-0
CT Radiogenomic Characterization of EGFR, K-RAS, and ALK Mutations in Non-Small Cell Lung Cancer
S. Rizzo (2015)
10.1016/j.radonc.2015.02.015
CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma.
T. Coroller (2015)
10.1093/nar/gkw650
Elimination of unaltered DNA in mixed clinical samples via nuclease-assisted minor-allele enrichment
Chen Song (2016)
10.1038/ng.2526
Genomic sequencing of meningiomas identifies oncogenic SMO and AKT1 mutations
P. Brastianos (2013)
10.1016/j.radonc.2016.04.004
Radiomic phenotype features predict pathological response in non-small cell lung cancer.
T. Coroller (2016)
10.1200/JCO.2013.49.4799
Precision oncology: an overview.
L. Garraway (2013)



This paper is referenced by
10.1016/j.crad.2019.07.026
A radiomics model for determining the invasiveness of solitary pulmonary nodules that manifest as part-solid nodules.
Q. Weng (2019)
10.21037/tlcr-20-122
3D radiomics predicts EGFR mutation, exon-19 deletion and exon-21 L858R mutation in lung adenocarcinoma.
Guixue Liu (2020)
10.3389/fonc.2019.01062
Predictive Power of a Radiomic Signature Based on 18F-FDG PET/CT Images for EGFR Mutational Status in NSCLC
X. Li (2019)
10.1186/s12880-019-0355-z
Computed tomography-based predictive nomogram for differentiating primary progressive pulmonary tuberculosis from community-acquired pneumonia in children
B. Wang (2019)
10.21037/ATM.2019.12.149
Attitudes towards medical artificial intelligence talent cultivation: an online survey study.
Dongyuan Yun (2020)
10.1038/s41598-019-45766-z
Repeatability of Multiparametric Prostate MRI Radiomics Features
Michael Schwier (2019)
10.1109/CBMS.2018.00051
Exploratory Radiomics for Predicting Adaptive Radiotherapy in Non-Small Cell Lung Cancer
R. Sicilia (2018)
10.1007/s00259-020-04986-6
The deep learning model combining CT image and clinicopathological information for predicting ALK fusion status and response to ALK-TKI therapy in non-small cell lung cancer patients
Zheng-bo Song (2020)
10.21037/atm-19-4690
A CT-derived deep neural network predicts for programmed death ligand-1 expression status in advanced lung adenocarcinomas.
Y. Zhu (2020)
10.1007/s00259-019-04372-x
Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics
M. Sollini (2019)
10.31557/apjcb.2020.5.4.189-199
Reviewing the Role of Artificial Intelligence in Cancer
Shankargouda Patil (2020)
10.1245/s10434-020-08255-6
Development and External Validation of Radiomics Approach for Nuclear Grading in Clear Cell Renal Cell Carcinoma
H. Zhou (2020)
10.1148/radiol.2017171183
When Machines Think: Radiology's Next Frontier.
K. Dreyer (2017)
10.7150/thno.30309
The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges
Z. Liu (2019)
10.1007/s00432-018-2787-1
Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas
Shuang Wu (2018)
10.1007/s10462-019-09764-x
A systematic review and meta-analysis on performance of intelligent systems in lung cancer: Where are we?
M. Sokouti (2019)
10.1016/j.radonc.2019.01.004
CT-based radiomic features predict tumor grading and have prognostic value in patients with soft tissue sarcomas treated with neoadjuvant radiation therapy.
J. Peeken (2019)
10.1007/s00330-018-5912-2
Development and validation of a prognostic index for efficacy evaluation and prognosis of first-line chemotherapy in stage III–IV lung squamous cell carcinoma
J. Song (2018)
10.1016/j.ejrad.2018.11.032
Genomics of non-small cell lung cancer (NSCLC): Association between CT-based imaging features and EGFR and K-RAS mutations in 122 patients-An external validation.
S. Rizzo (2019)
10.1007/s11307-018-1225-8
Metabolic Imaging Phenotype Using Radiomics of [18F]FDG PET/CT Associated with Genetic Alterations of Colorectal Cancer
S. Chen (2018)
10.1007/s00292-019-00704-8
[Radiomics-AI-based image analysis].
A. Demircioğlu (2019)
10.3389/fonc.2020.00369
Clinical, Conventional CT and Radiomic Feature-Based Machine Learning Models for Predicting ALK Rearrangement Status in Lung Adenocarcinoma Patients
Lan Song (2020)
10.1016/j.ejrad.2019.01.005
Prediction of EGFR mutations by conventional CT-features in advanced pulmonary adenocarcinoma.
Y. Chen (2019)
10.1016/j.lungcan.2018.05.001
Prognostic impact of the integration of volumetric quantification of the solid part of the tumor on 3DCT and FDG-PET imaging in clinical stage IA adenocarcinoma of the lung.
H. Furumoto (2018)
10.1186/s13073-019-0689-8
Artificial intelligence in clinical and genomic diagnostics
R. Dias (2019)
10.1183/13993003.00986-2018
Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning
S. Wang (2019)
10.3389/fonc.2020.568857
Performance of 18F-FDG PET/CT Radiomics for Predicting EGFR Mutation Status in Patients With Non-Small Cell Lung Cancer
Min Zhang (2020)
10.1016/j.acra.2018.02.019
A Radiomics Signature in Preoperative Predicting Degree of Tumor Differentiation in Patients with Non-small Cell Lung Cancer.
X. Chen (2018)
10.21037/atm-19-4630
Dual-mode ultrasound radiomics and intrinsic imaging phenotypes for diagnosis of lymph node lesions.
Y. Chen (2020)
10.1002/jmri.26531
MR‐Based Radiomics Nomogram of Cervical Cancer in Prediction of the Lymph‐Vascular Space Invasion preoperatively
Z. Li (2019)
10.1007/S13369-018-3468-8
Lung Cancer Classification Models Using Discriminant Information of Mutated Genes in Protein Amino Acids Sequences
Mohsin Sattar (2019)
10.1002/jmri.27138
Radiomics Based on MRI as a Biomarker to Guide Therapy by Predicting Upgrading of Prostate Cancer From Biopsy to Radical Prostatectomy
G. Zhang (2020)
See more
Semantic Scholar Logo Some data provided by SemanticScholar