[Skip to Content]
[Skip to Content Landing]

The Potential of Radiomic-Based Phenotyping in Precision MedicineA Review

Educational Objective
To learn the potential of radiomic-based imaging in defining tumor phenotype.
1 Credit CME
Abstract

Importance  Advances in genomics have led to the recognition that tumors are populated by distinct genotypic subgroups that drive tumor development and progression. The spatial and temporal heterogeneity of solid tumors has been a critical barrier to the development of precision medicine approaches because the standard approach to tumor sampling, often invasive needle biopsy, is unable to fully capture the spatial state of the tumor. Image-based phenotyping, which represents quantification of the tumor phenotype through medical imaging, is a promising development for precision medicine.

Observations  Medical imaging can provide a comprehensive macroscopic picture of the tumor phenotype and its environment that is ideally suited to quantifying the development of the tumor phenotype before, during, and after treatment. As a noninvasive technique, medical imaging can be performed at low risk and inconvenience to the patient. The semantic features approach to tumor phenotyping, accomplished by visual assessment of radiologists, is compared with a computational radiomics approach that relies on automated processing of imaging assays. Together, these approaches capture important information for diagnostic, prognostic, and predictive purposes.

Conclusions and Relevance  Although imaging technology is already embedded in clinical practice for diagnosis, staging, treatment planning, and response assessment, the transition of these computational methods to the clinic has been surprisingly slow. This review outlines the promise of these novel technologies for precision medicine and the obstacles to clinical application.

Sign in to take quiz and track your certificates

Buy This Activity

JN Learning™ is the home for CME and MOC from the JAMA Network. Search by specialty or US state and earn AMA PRA Category 1 CME Credit™ from articles, audio, Clinical Challenges and more. Learn more about CME/MOC

Article Information

Corresponding Author: Hugo J. W. L. Aerts, PhD, Departments of Radiation Oncology and Radiology, Dana-Farber Cancer Institute, Harvard Institutes of Medicine, Ste HIM 343, 77 Avenue Louis Pasteur, Boston, MA 02115 (hugo_aerts@dfci.harvard.edu).

Accepted for Publication: May 19, 2016.

Correction: This article was corrected on March 23, 2017, for a typographical error in the abstract.

Published Online: August 18, 2016. doi:10.1001/jamaoncol.2016.2631

Conflict of Interest Disclosures: Dr Aerts reported owning shares in Genospace LLC and Sphera Inc, informatics companies directed at imaging and genomic data. No other disclosures were reported.

Funding/Support: This study was supported by awards U01CA190234 and U24CA194354 from the National Institutes of Health.

Role of the Funder/Sponsor: The funding source had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and the decision to submit the manuscript for publication.

Additional Contributions: Elizabeth Huynh, PhD, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, assisted with the figures. She received no compensation.

References
1.
Kurland  BF, Gerstner  ER, Mountz  JM,  et al.  Promise and pitfalls of quantitative imaging in oncology clinical trials.  Magn Reson Imaging. 2012;30(9):1301-1312.PubMedGoogle ScholarCrossref
2.
Buckler  AJ, Bresolin  L, Dunnick  NR, Sullivan  DC.  A collaborative enterprise for multi-stakeholder participation in the advancement of quantitative imaging.  Radiology. 2011;258(3):906-914.PubMedGoogle ScholarCrossref
3.
Pirker  R, Pereira  JR, Szczesna  A,  et al; FLEX Study Team.  Cetuximab plus chemotherapy in patients with advanced non-small-cell lung cancer (FLEX): an open-label randomised phase III trial.  Lancet. 2009;373(9674):1525-1531.PubMedGoogle ScholarCrossref
4.
Lynch  TJ, Patel  T, Dreisbach  L,  et al.  Cetuximab and first-line taxane/carboplatin chemotherapy in advanced non-small-cell lung cancer: results of the randomized multicenter phase III trial BMS099.  J Clin Oncol. 2010;28(6):911-917.PubMedGoogle ScholarCrossref
5.
Khambata-Ford  S, Harbison  CT, Hart  LL,  et al.  Analysis of potential predictive markers of cetuximab benefit in BMS099, a phase III study of cetuximab and first-line taxane/carboplatin in advanced non-small-cell lung cancer.  J Clin Oncol. 2010;28(6):918-927.PubMedGoogle ScholarCrossref
6.
Hirsch  FR, Herbst  RS, Olsen  C,  et al.  Increased EGFR gene copy number detected by fluorescent in situ hybridization predicts outcome in non-small-cell lung cancer patients treated with cetuximab and chemotherapy.  J Clin Oncol. 2008;26(20):3351-3357.PubMedGoogle ScholarCrossref
7.
Gerlinger  M, Rowan  AJ, Horswell  S,  et al.  Intratumor heterogeneity and branched evolution revealed by multiregion sequencing.  N Engl J Med. 2012;366(10):883-892.PubMedGoogle Scholar
8.
Gerlinger  M, Swanton  C.  How Darwinian models inform therapeutic failure initiated by clonal heterogeneity in cancer medicine.  Br J Cancer. 2010;103(8):1139-1143.PubMedGoogle ScholarCrossref
9.
Gillies  RJ, Kinahan  PE, Hricak  H.  Radiomics: images are more than pictures, they are data.  Radiology. 2016;278(2):563-577.PubMedGoogle ScholarCrossref
10.
Therasse  P, Arbuck  SG, Eisenhauer  EA,  et al.  New guidelines to evaluate the response to treatment in solid tumors. European Organization for Research and Treatment of Cancer, National Cancer Institute of the United States, National Cancer Institute of Canada.  J Natl Cancer Inst. 2000;92(3):205-216.PubMedGoogle ScholarCrossref
11.
Jaffe  CC.  Measures of response: RECIST, WHO, and new alternatives.  J Clin Oncol. 2006;24(20):3245-3251.PubMedGoogle ScholarCrossref
12.
World Health Organization.  Handbook for Reporting Results of Cancer Treatment. Geneva, Switzerland: World Health Organization; 1979.
13.
Zhao  B, Oxnard  GR, Moskowitz  CS,  et al.  A pilot study of volume measurement as a method of tumor response evaluation to aid biomarker development.  Clin Cancer Res. 2010;16(18):4647-4653.PubMedGoogle ScholarCrossref
14.
Zhao  B, James  LP, Moskowitz  CS,  et al.  Evaluating variability in tumor measurements from same-day repeat CT scans of patients with non-small cell lung cancer.  Radiology. 2009;252(1):263-272.PubMedGoogle ScholarCrossref
15.
Lambin  P, Rios-Velazquez  E, Leijenaar  R,  et al.  Radiomics: extracting more information from medical images using advanced feature analysis.  Eur J Cancer. 2012;48(4):441-446.PubMedGoogle ScholarCrossref
16.
Aerts  HJWL, Velazquez  ER, Leijenaar  RTH,  et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.  Nat Commun. 2014;5:4006.PubMedGoogle Scholar
17.
Kumar  V, Gu  Y, Basu  S,  et al.  Radiomics: the process and the challenges.  Magn Reson Imaging. 2012;30(9):1234-1248.PubMedGoogle ScholarCrossref
18.
Clarke  LP, Nordstrom  RJ, Zhang  H,  et al.  The Quantitative Imaging Network: NCI’s historical perspective and planned goals.  Transl Oncol. 2014;7(1):1-4.PubMedGoogle ScholarCrossref
19.
Buckler  AJ, Bresolin  L, Dunnick  NR,  et al.  Quantitative imaging test approval and biomarker qualification: interrelated but distinct activities.  Radiology. 2011;259(3):875-884.PubMedGoogle ScholarCrossref
20.
Nishino  M, Guo  M, Jackman  DM,  et al.  CT tumor volume measurement in advanced non-small-cell lung cancer: performance characteristics of an emerging clinical tool.  Acad Radiol. 2011;18(1):54-62.PubMedGoogle ScholarCrossref
21.
Nishino  M, Dahlberg  SE, Fulton  LE,  et al.  Volumetric tumor response and progression in EGFR-mutant NSCLC patients treated with erlotinib or gefitinib.  Acad Radiol. 2016;23(3):329-336.PubMedGoogle ScholarCrossref
22.
Rios Velazquez  E, Aerts  HJWL, Gu  Y,  et al.  A semiautomatic CT-based ensemble segmentation of lung tumors: comparison with oncologists’ delineations and with the surgical specimen.  Radiother Oncol. 2012;105(2):167-173.PubMedGoogle ScholarCrossref
23.
Velazquez  ER, Parmar  C, Jermoumi  M,  et al.  Volumetric CT-based segmentation of NSCLC using 3D-Slicer.  Sci Rep. 2013;3:3529.PubMedGoogle ScholarCrossref
24.
Giger  ML.  Update on the potential of computer-aided diagnosis for breast cancer.  Future Oncol. 2010;6(1):1-4.PubMedGoogle ScholarCrossref
25.
Doi  K.  Computer-aided diagnosis in medical imaging: historical review, current status and future potential.  Comput Med Imaging Graph. 2007;31(4-5):198-211.PubMedGoogle ScholarCrossref
26.
Rios Velazquez  E, Meier  R, Dunn  WD  Jr,  et al.  Fully automatic GBM segmentation in the TCGA-GBM dataset: prognosis and correlation with VASARI features.  Sci Rep. 2015;5:16822.PubMedGoogle ScholarCrossref
27.
Porz  N, Bauer  S, Pica  A,  et al.  Multi-modal glioblastoma segmentation: man versus machine.  PLoS One. 2014;9(5):e96873.PubMedGoogle ScholarCrossref
28.
Lederlin  M, Puderbach  M, Muley  T,  et al.  Correlation of radio- and histomorphological pattern of pulmonary adenocarcinoma.  Eur Respir J. 2013;41(4):943-951.PubMedGoogle ScholarCrossref
29.
Honda  T, Kondo  T, Murakami  S,  et al.  Radiographic and pathological analysis of small lung adenocarcinoma using the new IASLC classification.  Clin Radiol. 2013;68(1):e21-e26.PubMedGoogle ScholarCrossref
30.
Hashizume  T, Yamada  K, Okamoto  N,  et al.  Prognostic significance of thin-section CT scan findings in small-sized lung adenocarcinoma.  Chest. 2008;133(2):441-447.PubMedGoogle ScholarCrossref
31.
Aoki  T, Tomoda  Y, Watanabe  H,  et al.  Peripheral lung adenocarcinoma: correlation of thin-section CT findings with histologic prognostic factors and survival.  Radiology. 2001;220(3):803-809.PubMedGoogle ScholarCrossref
32.
Lee  HY, Lee  KS.  Ground-glass opacity nodules: histopathology, imaging evaluation, and clinical implications.  J Thorac Imaging. 2011;26(2):106-118.PubMedGoogle ScholarCrossref
33.
Wang  H, Schabath  MB, Liu  Y,  et al.  Semiquantitative computed tomography characteristics for lung adenocarcinoma and their association with lung cancer survival.  Clin Lung Cancer. 2015;16(6):e141-e163.PubMedGoogle ScholarCrossref
34.
Takashima  S, Maruyama  Y, Hasegawa  M, Saito  A, Haniuda  M, Kadoya  M.  High-resolution CT features: prognostic significance in peripheral lung adenocarcinoma with bronchioloalveolar carcinoma components.  Respiration. 2003;70(1):36-42.PubMedGoogle ScholarCrossref
35.
Takashima  S, Maruyama  Y, Hasegawa  M,  et al.  Prognostic significance of high-resolution CT findings in small peripheral adenocarcinoma of the lung: a retrospective study on 64 patients.  Lung Cancer. 2002;36(3):289-295.PubMedGoogle ScholarCrossref
36.
VASARI feature set. https://wiki.nci.nih.gov/display/CIP/VASARI. Accessed January 10, 2016.
37.
Zinn  PO, Mahajan  B, Sathyan  P,  et al.  Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme.  PLoS One. 2011;6(10):e25451.PubMedGoogle ScholarCrossref
38.
Opulencia  P, Channin  DS, Raicu  DS, Furst  JD.  Mapping LIDC, RadLex™, and lung nodule image features.  J Digit Imaging. 2011;24(2):256-270.PubMedGoogle ScholarCrossref
39.
Gutman  DA, Cooper  LAD, Hwang  SN,  et al.  MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set.  Radiology. 2013;267(2):560-569.PubMedGoogle ScholarCrossref
40.
Diehn  M, Nardini  C, Wang  DS,  et al.  Identification of noninvasive imaging surrogates for brain tumor gene-expression modules.  Proc Natl Acad Sci U S A. 2008;105(13):5213-5218.PubMedGoogle ScholarCrossref
41.
Naeini  KM, Pope  WB, Cloughesy  TF,  et al.  Identifying the mesenchymal molecular subtype of glioblastoma using quantitative volumetric analysis of anatomic magnetic resonance images.  Neuro Oncol. 2013;15(5):626-634.PubMedGoogle ScholarCrossref
42.
Pope  WB, Chen  JH, Dong  J,  et al.  Relationship between gene expression and enhancement in glioblastoma multiforme: exploratory DNA microarray analysis.  Radiology. 2008;249(1):268-277.PubMedGoogle ScholarCrossref
43.
Gutman  DA, Dunn  WD  Jr, Grossmann  P,  et al.  Somatic mutations associated with MRI-derived volumetric features in glioblastoma.  Neuroradiology. 2015;57(12):1227-1237.PubMedGoogle ScholarCrossref
44.
Tixier  F, Hatt  M, Valla  C,  et al.  Visual versus quantitative assessment of intratumor 18F-FDG PET uptake heterogeneity: prognostic value in non-small cell lung cancer.  J Nucl Med. 2014;55(8):1235-1241.PubMedGoogle ScholarCrossref
45.
Wetzel  SG, Cha  S, Johnson  G,  et al.  Relative cerebral blood volume measurements in intracranial mass lesions: interobserver and intraobserver reproducibility study.  Radiology. 2002;224(3):797-803.PubMedGoogle ScholarCrossref
46.
Haralick  RM, Shanmugam  K, Its’Hak  D.  Textural features for image classification.  IEEE Trans Syst Man Cybern. 1973;3(6):610-621.Google ScholarCrossref
47.
Galloway  MM.  Texture analysis using gray level run lengths.  Comput Graph Image Process. 1975;4(2):172-179.Google ScholarCrossref
48.
Thibault  G, Guillaume  T, Bernard  F,  et al.  Shape and texture indexes application to cell nuclei classification.  Int J Pattern Recognit Artif Intell. 2013;27(1):1357002.Google ScholarCrossref
49.
Coroller  TP, Grossmann  P, Hou  Y,  et al.  CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma.  Radiother Oncol. 2015;114(3):345-350.PubMedGoogle ScholarCrossref
50.
Cunliffe  A, Armato  SG  III, Castillo  R, Pham  N, Guerrero  T, Al-Hallaq  HA.  Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development.  Int J Radiat Oncol Biol Phys. 2015;91(5):1048-1056.PubMedGoogle ScholarCrossref
51.
Parmar  C, Leijenaar  RTH, Grossmann  P,  et al.  Radiomic feature clusters and prognostic signatures specific for lung and head & neck cancer.  Sci Rep. 2015;5:11044.PubMedGoogle ScholarCrossref
52.
Hatt  M, Majdoub  M, Vallières  M,  et al.  18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort.  J Nucl Med. 2015;56(1):38-44.PubMedGoogle ScholarCrossref
53.
Yang  F, Thomas  MA, Dehdashti  F, Grigsby  PW.  Temporal analysis of intratumoral metabolic heterogeneity characterized by textural features in cervical cancer.  Eur J Nucl Med Mol Imaging. 2013;40(5):716-727.PubMedGoogle ScholarCrossref
54.
El Naqa  I, Grigsby  P, Apte  A,  et al.  Exploring feature-based approaches in PET images for predicting cancer treatment outcomes.  Pattern Recognit. 2009;42(6):1162-1171.PubMedGoogle ScholarCrossref
55.
Gevaert  O, Mitchell  LA, Achrol  AS,  et al.  Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features.  Radiology. 2015;276(1):313.PubMedGoogle ScholarCrossref
56.
Upadhaya  T, Taman  U, Yannick  M, Eric  S, Le Reste  P-J, Mathieu  E. Prognostic value of multimodal MRI tumor features in glioblastoma multiforme using textural features analysis. In:  Proceedings of the 2015 IEEE 12th International Symposium on Biomedical Imaging. New York, NY: IEEE; 2015:50-54.
57.
Chang  P, Schwartz  L. Fully automated quantitative scoring of vasari glioma imaging features. Paper presented at: SIIM 2015; May 30, 2015; Washington, DC.
58.
Yanagawa  M, Tanaka  Y, Kusumoto  M,  et al.  Automated assessment of malignant degree of small peripheral adenocarcinomas using volumetric CT data: correlation with pathologic prognostic factors.  Lung Cancer. 2010;70(3):286-294.PubMedGoogle ScholarCrossref
59.
Gimenez  F, Xu  J, Liu  Y,  et al.  Automatic annotation of radiological observations in liver CT images.  AMIA Annu Symp Proc. 2012;2012:257-263.PubMedGoogle Scholar
60.
Parmar  C, Grossmann  P, Bussink  J, Lambin  P, Aerts  HJWL.  Machine learning methods for quantitative radiomic biomarkers.  Sci Rep. 2015;5:13087.PubMedGoogle ScholarCrossref
61.
Parmar  C, Grossmann  P, Rietveld  D, Rietbergen  MM, Lambin  P, Aerts  HJW.  Radiomic machine-learning classifiers for prognostic biomarkers of head and neck cancer.  Front Oncol. 2015;5:272.PubMedGoogle ScholarCrossref
62.
Hong  SJ, Kim  TJ, Choi  YW, Park  J-S, Chung  J-H, Lee  KW.  Radiogenomic correlation in lung adenocarcinoma with epidermal growth factor receptor mutations: Imaging features and histological subtypes [published online January 19, 2016].  Eur Radiol. doi:10.1007/s00330-015-4196-z.PubMedGoogle Scholar
63.
Hsu  J-S, Huang  MS, Chen  CY,  et al.  Correlation between EGFR mutation status and computed tomography features in patients with advanced pulmonary adenocarcinoma.  J Thorac Imaging. 2014;29(6):357-363.PubMedGoogle ScholarCrossref
64.
Liu  Y, Kim  J, Balagurunathan  Y,  et al.  Radiomic features are associated with EGFR mutation status in lung adenocarcinomas [published online February 16, 2016].  Clin Lung Cancer. doi:10.1016/j.cllc.2016.02.001.PubMedGoogle Scholar
65.
Freer  TW, Ulissey  MJ.  Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center.  Radiology. 2001;220(3):781-786.PubMedGoogle ScholarCrossref
66.
Feig  SA, Sickles  EA, Evans  WP, Linver  MN.  Re: Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system.  J Natl Cancer Inst. 2004;96(16):1260-1261.PubMedGoogle ScholarCrossref
67.
Birdwell  RL, Bandodkar  P, Ikeda  DM.  Computer-aided detection with screening mammography in a university hospital setting.  Radiology. 2005;236(2):451-457.PubMedGoogle ScholarCrossref
68.
Cupples  TE, Cunningham  JE, Reynolds  JC.  Impact of computer-aided detection in a regional screening mammography program.  AJR Am J Roentgenol. 2005;185(4):944-950.PubMedGoogle ScholarCrossref
69.
Morton  MJ, Whaley  DH, Brandt  KR, Amrami  KK.  Screening mammograms: interpretation with computer-aided detection–prospective evaluation.  Radiology. 2006;239(2):375-383.PubMedGoogle ScholarCrossref
70.
Xu  XW, Doi  K, Kobayashi  T, MacMahon  H, Giger  ML.  Development of an improved CAD scheme for automated detection of lung nodules in digital chest images.  Med Phys. 1997;24(9):1395-1403.PubMedGoogle ScholarCrossref
71.
Shiraishi  J, Li  Q, Suzuki  K, Engelmann  R, Doi  K.  Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification.  Med Phys. 2006;33(7):2642-2653.PubMedGoogle ScholarCrossref
72.
Chan  HP, Doi  K, Vyborny  CJ,  et al.  Improvement in radiologists’ detection of clustered microcalcifications on mammograms: the potential of computer-aided diagnosis.  Invest Radiol. 1990;25(10):1102-1110.PubMedGoogle ScholarCrossref
73.
Yin  FF, Giger  ML, Vyborny  CJ, Doi  K, Schmidt  RA.  Comparison of bilateral-subtraction and single-image processing techniques in the computerized detection of mammographic masses.  Invest Radiol. 1993;28(6):473-481.PubMedGoogle ScholarCrossref
74.
Arimura  H, Katsuragawa  S, Suzuki  K,  et al.  Computerized scheme for automated detection of lung nodules in low-dose computed tomography images for lung cancer screening.  Acad Radiol. 2004;11(6):617-629.PubMedGoogle ScholarCrossref
75.
Beyer  F, Zierott  L, Fallenberg  EM,  et al.  Comparison of sensitivity and reading time for the use of computer-aided detection (CAD) of pulmonary nodules at MDCT as concurrent or second reader.  Eur Radiol. 2007;17(11):2941-2947.PubMedGoogle ScholarCrossref
76.
Perry  N, Puthaar  E.  European Guidelines for Quality Assurance in Breast Cancer Screening and Diagnosis. Luxembourg City, Luxembourg: Office for Official Publications of the European Union; 2013.
77.
Wood  DE, Kazerooni  E, Baum  SL,  et al; National Comprehension Cancer Network.  Lung cancer screening, version 1.2015: featured updates to the NCCN guidelines.  J Natl Compr Canc Netw. 2015;13(1):23-34.PubMedGoogle Scholar
If you are not a JN Learning subscriber, you can either:
Subscribe to JN Learning for one year
Buy this activity
jn-learning_Modal_LoginSubscribe_Purchase
If you are not a JN Learning subscriber, you can either:
Subscribe to JN Learning for one year
Buy this activity
jn-learning_Modal_LoginSubscribe_Purchase
With a personal account, you can:
  • Access free activities and track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
Education Center Collection Sign In Modal Right

Name Your Search

Save Search
With a personal account, you can:
  • Track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
jn-learning_Modal_SaveSearch_NoAccess_Purchase

Lookup An Activity

or

My Saved Searches

You currently have no searches saved.

With a personal account, you can:
  • Access free activities and track your credits
  • Personalize content alerts
  • Customize your interests
  • Fully personalize your learning experience
Education Center Collection Sign In Modal Right
Topics
State Requirements