Radiomics: Images Are More than Pictures, They Are Data
Licensed according to this deed.
Category
Published on
Abstract
Robert J. Gillies, PhD
Paul E. Kinahan, PhD
Hedvig Hricak, MD, PhD, Dr(hc)
In the past decade, the field of medical image analysis has grown exponentially, with an increased number of pattern recognition tools and an increase in data set sizes. These advances have facilitated the development of processes for high-throughput extraction of quantitative features that result in the conversion of images into mineable data and the subsequent analysis of these data for decision support; this practice is termed radiomics. This is in contrast to the traditional practice of treating medical images as pictures intended solely for visual interpretation. Radiomic data contain first-, second-, and higher-order statistics. These data are combined with other patient data and are mined with sophisticated bioinformatics tools to develop models that may potentially improve diagnostic, prognostic, and predictive accuracy. Because radiomics analyses are in- tended to be conducted with standard of care images, it is conceivable that conversion of digital images to mineable data will eventually become routine practice. This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision mak- ing, particularly in the care of patients with cancer.
R. J. Gillies, P. E. Kinahan, and H. Hricak, “Radiomics: Images Are More than Pictures, They Are Data,” Radiology, p. 151169, Nov. 2015.
Acknowledgments
This article was an out- growth of the 2014 Radiological Society of North America/American Association of Physicists in Medicine Plenary Session. The authors thank the following colleagues for their substantial in- put: Daniel Seeburg, MD (Johns Hopkins Uni- versity), for his timely review of an early draft of the manuscript; Olya String eld, PhD (Mof tt Cancer Center), for production of images; Rob- ert A. Gatenby, MD (Mof tt Cancer Center), for providing images, inspiration. and edits; Yoganand Balagurunathan, PhD (Mof tt Cancer Center), for his review of the manuscript; Sandy Napel, PhD (Stanford University), for providing a comprehensive list of relevant references; and Ada Muellner, MS (Memorial Sloan-Kettering Cancer Center), for her spectacular editing. We also acknowledge funding and support from RSNA’s sponsorship of QIBA and the NCI’s sponsorship of QIN.
References
1. Institute of Medicine I. Evolution of Transla- tional Omics. Lessons learned and the path forward. Washington, DC: National Acad- emies Press, 2012. 2. Giger ML. Update on the potential of com- puter-aided diagnosis for breast cancer. Fu- ture Oncol 2010;6(1):1–4. 3. Doi K. Computer-aided diagnosis in medi- cal imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007;31(4-5):198–211. 4. Guo Z, Shu Y, Zhou H, Zhang W, Wang H. Radiogenomics helps to achieve personalized therapy by evaluating patient responses to radiation treatment. Carcinogenesis 2015; 36(3):307–317. 5. West CM, Barnett GC. Genetics and geno- mics of radiotherapy toxicity: towards pre- diction. Genome Med 2011;3(8):52. 6. Wibmer A, Hricak H, Gondo T, et al. Ha- ralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differenti- ating prostate cancers with different Gleason scores. Eur Radiol 2015;25(10):2840–2850. 7. Coroller TP, Grossmann P, Hou Y, et al. CT- based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radio- ther Oncol 2015;114(3):345–350. 8. Committee on the Review of Omics-Based Tests for Predicting Patient Outcomes in Clinical Trials, Board on Health Care Ser- vices, Board on Health Sciences Policy, Insti- tute of Medicine. Evolution of Translational Omics: Lessons Learned and the Path For- ward. Micheel CM, Nass SJ, Omenn GS, eds. Washington, DC: National Academies Press. 9. Bates SE. It’s all about the test: the com- plexity of companion diagnostic co-develop- ment in personalized medicine. Clin Cancer Res 2014;20(6):1418. 10. Collins FS, Varmus H. A new initiative on pre- cision medicine. N Engl J Med 2015;372(9): 793–795. 11. Of ce of the Press Secretary. Fact sheet: President Obama’s precision medicine initiative. The White House Web site. http://www.whitehouse.gov/the-press- office/2015/01/30/fact-sheet-president- obama-s-precision-medicine-initiative. Up- dated January 30, 2015. Accessed April 4, 2015. 12. Siegel R, Ma J, Zou Z, Jemal A. Cancer statistics, 2014. CA Cancer J Clin 2014; 64(1):9–29. 13. Yachida S, Jones S, Bozic I, et al. Distant metastasis occurs late during the genetic evolution of pancreatic cancer. Nature 2010; 467(7319):1114–1117. 14. Gerlinger M, Rowan AJ, Horswell S, et al. Intratumor heterogeneity and branched evo- lution revealed by multiregion sequencing. N Engl J Med 2012;366(10):883–892. 15. Sottoriva A, Spiteri I, Piccirillo SG, et al. Intratumor heterogeneity in human glioblas- toma re ects cancer evolutionary dynamics. Proc Natl Acad Sci U S A 2013;110(10): 4009–4014. 16. Sequist LV, Martins RG, Spigel D, et al. First-line ge tinib in patients with advanced non-small-cell lung cancer harboring so- Radiology: Volume 000: Number 0— 2016 n radiology.rsna.org 17. Burstein HJ, Harris LN, Marcom PK, et al. Trastuzumab and vinorelbine as rst-line therapy for HER2-overexpressing metastatic breast cancer: multicenter phase II trial with clinical outcomes, analysis of serum tumor markers as predictive factors, and cardiac surveillance algorithm. J Clin Oncol 2003;21(15):2889–2895. 18. Wagle N, Emery C, Berger MF, et al. Dis- secting therapeutic resistance to RAF inhi- bition in melanoma by tumor genomic pro- ling. J Clin Oncol 2011;29(22):3085–3096. 19. Sequist LV, Waltman BA, Dias-Santagata D, et al. Genotypic and histological evolu- tion of lung cancers acquiring resistance to EGFR inhibitors. Sci Transl Med 2011;3(75): 75ra26. 20. Clauson J, Hsieh YC, Acharya S, Rademak- er AW, Morrow M. Results of the Lynn Sage Second-Opinion Program for local therapy in patients with breast carcinoma: changes in management and determinants of where care is delivered. Cancer 2002;94(4):889– 894. 21. Nguyen PL, Schultz D, Renshaw AA, et al. The impact of pathology review on treat- ment recommendations for patients with adenocarcinoma of the prostate. Urol Oncol 2004;22(4):295–299. 22. Staradub VL, Messenger KA, Hao N, Wiley EL, Morrow M. Changes in breast cancer therapy because of pathology second opin- ions. Ann Surg Oncol 2002;9(10):982–987. 23. Kronz JD, Westra WH, Epstein JI. Mandatory second opinion surgical pathology at a large referral hospital. Cancer 1999;86(11): 2426–2435. 24. Kumar V, Gu Y, Basu S, et al. Radiomics: the process and the challenges. Magn Reson Imaging 2012;30(9):1234–1248. 25. 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. 26. Clarke LP, Sriram RD, Schilling LB. Imaging as a Biomarker: Standards for Change Mea- surements in Therapy workshop summary. Acad Radiol 2008;15(4):501–530. 27. Shankar LK, Hoffman JM, Bacharach S, et al. Consensus recommendations for the use of 18F-FDG PET as an indicator of therapeu- tic response in patients in National Cancer Institute Trials. J Nucl Med 2006;47(6):1059– 1066. 28. 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. Buckler AJ, Bresolin L, Dunnick NR, Sul- livan DC; for the Group. A collaborative en- terprise for multi-stakeholder participation in the advancement of quantitative imaging. Radiology 2011;258(3):906–914. Kinahan P, Wahl R, Shao L, Frank R, Perl- man E. The QIBA pro le for quantitative FDG-PET/CT oncology imaging [abstr]. J Nucl Med 2014;55(Suppl 1):1520. FDG-PET/CT Technical Committee. FDG- PET/CT as an Imaging Biomarker Measuring Response to Cancer Therapy, Quantitative Imaging Biomarkers Alliance, Version 1.05, Publicly Reviewed Version. RSNA Web site. http://www.rsna.org/qiba/. Published De- cember 11, 2013. Accessed May 20, 2015. van Persijn van Meerten EL, Gelderblom H, Bloem JL. RECIST revised: implications for the radiologist: a review article on the modi ed RECIST guideline. Eur Radiol 2010;20(6):1456–1467. Burnside ES, Sickles EA, Bassett LW, et al. The ACR BI-RADS experience: learning from history. J Am Coll Radiol 2009;6(12): 851–860. Bomers JG, Barentsz JO. Standardization of multiparametric prostate MR imaging using PI-RADS. BioMed Res Int 2014;2014: 431680. Kazerooni EA, Armstrong MR, Amorosa JK, et al. ACR CT accreditation program and the lung cancer screening program designation. J Am Coll Radiol 2015;12(1):38–42. Gatenby RA, Grove O, Gillies RJ. Quantita- tive imaging in cancer evolution and ecology. Radiology 2013;269(1):8–15. Zhou M, Hall L, Goldgof D, et al. Radiolog- ically de ned ecological dynamics and clin- ical outcomes in glioblastoma multiforme: preliminary results. Transl Oncol 2014;7(1): 5–13. Rios Velazquez E, Aerts HJ, Gu Y, et al. A semiautomatic CT-based ensemble segmenta- tion of lung tumors: comparison with oncolo- gists’ delineations and with the surgical speci- men. Radiother Oncol 2012;105(2):167–173. van Dam IE, van Sörnsen de Koste JR, Hanna GG, Muirhead R, Slotman BJ, Senan S. Improving target delineation on 4-dimen- sional CT scans in stage I NSCLC using a de- formable registration tool. Radiother Oncol 2010;96(1):67–72. Segal E, Sirlin CB, Ooi C, et al. Decoding global gene expression programs in liver cancer by noninvasive imaging. Nat Biotech- nol 2007;25(6):675–680. 41. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classi cation. IEEE Trans Syst Man Cybern 1973;SMC- 3(6):610–621. 42. Davnall F, Yip CS, Ljungqvist G, et al. As- sessment of tumor heterogeneity: an emerg- ing imaging tool for clinical practice? Insights Imaging 2012;3(6):573–589. 43. O’Connor JP, Rose CJ, Waterton JC, Cara- no RA, Parker GJ, Jackson A. Imaging in- tratumor heterogeneity: role in therapy response, resistance, and clinical outcome. Clin Cancer Res 2015;21(2):249–257. 44. Rose CJ, Mills SJ, O’Connor JP, et al. Quan- tifying spatial heterogeneity in dynamic con- trast-enhanced MRI parameter maps. Magn Reson Med 2009;62(2):488–499. 45. Larkin TJ, Canuto HC, Kettunen MI, et al. Analysis of image heterogeneity using 2D Minkowski functionals detects tumor re- sponses to treatment. Magn Reson Med 2014; 71(1):402–410. 46. Grossmann P, Grove O, El-Hachem N, et al. Identi cation of molecular phenotypes in lung cancer by integrating radiomics and genomics. Sci Transl Med (in press). 47. Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics ap- proach. Nat Commun 2014;5:4006. 48. Pickup L, Talwar A, Stalin S, et al. Lung nodule classi cation using learnt texture features on a single patient population [ab- str]. In: Radiological Society of North Amer- ica Scienti c Assembly and Annual Meeting Program. Oak Brook, Ill: Radiological Soci- ety of North America, 2015; SSM06. 49. Schabath MB, Massion PP, Thompson ZJ, et al. Behavior of incidence lung cancers in the CT arm of the National Lung Screening Trial. JAMA (in press). 50. Balagurunathan Y, Kumar V, Gu Y, et al. Test- retest reproducibility analysis of lung CT image features. J Digit Imaging 2014;27(6): 805–823. 51. Lin LI. A concordance correlation coef cient to evaluate reproducibility. Biometrics 1989; 45(1):255–268. 52. Carrasco JL, King TS, Chinchilli VM. The concordance correlation coef cient for re- peated measures estimated by variance components. J Biopharm Stat 2009;19(1): 90–105. 53. Fehr D, Veeraraghavan H, Wibmer A, et al. Automatic classi cation of prostate cancer Gleason scores from multi-parametric mag- netic resonance images. Proc Natl Acad Sci USA (in press). 54. Diehn M, Nardini C, Wang DS, et al. Identi - cation of noninvasive imaging surrogates for brain tumor gene-expression modules. Proc Natl Acad Sci U S A 2008;105(13):5213– 5218. 55. Kuo MD, Gollub J, Sirlin CB, Ooi C, Chen X. Radiogenomic analysis to identify im- aging phenotypes associated with drug re- sponse gene expression programs in hepa- tocellular carcinoma. J Vasc Interv Radiol 2007;18(7):821–831. 56. Grove O, Berglund AE, Schabath MB, et al. Quantitative computed tomographic de- scriptors associate tumor shape complexity and intratumor heterogeneity with prog- nosis in lung adenocarcinoma. PLoS One 2015;10(3):e0118261. 57. Gevaert O, Mitchell LA, Achrol AS, et al. Glioblastoma multiforme: exploratory ra- diogenomic analysis by using quantitative image features. Radiology 2014;273(1):168– 174. 58. Vignati A, Mazzetti S, Giannini V, et al. Tex- ture features on T2-weighted magnetic res- onance imaging: new potential biomarkers for prostate cancer aggressiveness. Phys Med Biol 2015;60(7):2685–2701. 59. Teruel JRHM, Heldahl MG, Goa PE, et al. Dynamic contrast-enhanced MRI texture analysis for pretreatment prediction of clin- ical and pathological response to neoadju- vant chemotherapy in patients with locally advanced breast cancer. NMR Biomed 2014; 27(8):887–896. 60. Klaeser B, Wiskirchen J, Wartenberg J, et al. PET/CT-guided biopsies of metabolically active bone lesions: applications and clin- ical impact. Eur J Nucl Med Mol Imaging 2010;37(11):2027–2036. 61. Tatli S, Gerbaudo VH, Mamede M, Tun- cali K, Shyn PB, Silverman SG. Abdominal masses sampled at PET/CT-guided percuta- neous biopsy: initial experience with regis- tration of prior PET/CT images. Radiology 2010;256(1):305–311. 62. Simon RM, Paik S, Hayes DF. Use of ar- chived specimens in evaluation of prognos- tic and predictive biomarkers. J Natl Cancer Inst 2009;101(21):1446–1452. 63. Hayes DF, Bast RC, Desch CE, et al. Tumor marker utility grading system: a framework to evaluate clinical utility of tumor markers. J Natl Cancer Inst 1996;88(20):1456–1466. 64. Chalmers I, Glasziou P. Avoidable waste in the production and reporting of research evidence. Lancet 2009;374(9683):86–89. 65. Simera I, Moher D, Hirst A, Hoey J, Schulz KF, Altman DG. Transparent and accurate reporting increases reliability, utility, and impact of your research: reporting guide- lines and the EQUATOR Network. BMC Med 2010;8:24. 66. Prinz F, Schlange T, Asadullah K. Believe it or not: how much can we rely on published data on potential drug targets? Nat Rev Drug Discov 2011;10(9):712. 67. Begley CG, Ellis LM. Drug development: Raise standards for preclinical cancer re- search. Nature 2012;483(7391):531–533. 68. Journals unite for reproducibility. Nature 2014;515(7525):7. 69. McNutt M. Journals unite for reproducibil- ity. Science 2014;346(6210):679. 70. Landis SC, Amara SG, Asadullah K, et al. A call for transparent reporting to optimize the predictive value of preclinical research. Nature 2012;490(7419):187–191. 71. Drawing Causal Inference from Big Data. Arthur M. Sackler Colloquia of the National Academy of Sciences. https://www.youtube. com/playlist?list=PLGJm1x3XQeK0NgFO X2Z7Wt-P5RU5Zv0Hv. Published April 2, 2015. Accessed May 5, 2015. 72. Nelson B. Data sharing: empty archives. Na- ture 2009;461(7261):160–163. 73. Devidas M, London WB, Anderson JR. The use of central laboratories and remote elec- tronic data capture to risk-adjust therapy for pediatric acute lymphoblastic leukemia and neuroblastoma. Semin Oncol 2010;37(1):53– 59. 74. Heilbrun ME. Evaluating RadLex and real world radiology reporting: are we there yet? Acad Radiol 2013;20(11):1327–1328. 75. Kahn CE Jr. Annotation of gures from the biomedical imaging literature: a comparative analysis of RadLex and other standardized vocabularies. Acad Radiol 2014;21(3):384– 392. 76. Mabotuwana T, Lee MC, Cohen-Solal EV, Chang P. Mapping institution-speci c study descriptions to RadLex Playbook entries. J Digit Imaging 2014;27(3):321–330. 77. Clark K, Vendt B, Smith K, et al. The Can- cer Imaging Archive (TCIA): maintaining and operating a public information reposi- tory. J Digit Imaging 2013;26(6):1045–1057.