Introduction to Radiomics

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics—the so-called radiomic features—within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

[1]  Olivier Gevaert,et al.  Prognostic PET 18F-FDG uptake imaging features are associated with major oncogenomic alterations in patients with resected non-small cell lung cancer. , 2012, Cancer research.

[2]  Qianjin Feng,et al.  Radiomics Analysis of PET and CT Components of PET/CT Imaging Integrated with Clinical Parameters: Application to Prognosis for Nasopharyngeal Carcinoma , 2019, Molecular Imaging and Biology.

[3]  M. Soussan,et al.  A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET , 2018, The Journal of Nuclear Medicine.

[4]  Pedro Rosa-Neto,et al.  Machine Learning in Nuclear Medicine: Part 1—Introduction , 2019, The Journal of Nuclear Medicine.

[5]  P. Lambin,et al.  Radiomics: the bridge between medical imaging and personalized medicine , 2017, Nature Reviews Clinical Oncology.

[6]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[7]  P. Gibbs,et al.  Radiomic features of glucose metabolism enable prediction of outcome in mantle cell lymphoma , 2019, European Journal of Nuclear Medicine and Molecular Imaging.

[8]  V Goh,et al.  Texture analysis of 125I-A5B7 anti-CEA antibody SPECT differentiates metastatic colorectal cancer model phenotypes and anti-vascular therapy response , 2015, British Journal of Cancer.

[9]  R. Jeraj,et al.  Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters , 2010, Acta oncologica.

[10]  Alex Zwanenburg,et al.  Radiomics in nuclear medicine: robustness, reproducibility, standardization, and how to avoid data analysis traps and replication crisis , 2019, European Journal of Nuclear Medicine and Molecular Imaging.

[11]  Steffen Löck,et al.  A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling , 2017, Scientific Reports.

[12]  S. Röhrich,et al.  Machine learning: from radiomics to discovery and routine , 2018, Der Radiologe.

[13]  Ronald Boellaard,et al.  Repeatability of Radiomic Features in Non-Small-Cell Lung Cancer [18F]FDG-PET/CT Studies: Impact of Reconstruction and Delineation , 2016, Molecular Imaging and Biology.

[14]  J. Gustafsson,et al.  Intratumor heterogeneity predicts metastasis of triple-negative breast cancer , 2017, Carcinogenesis.

[15]  Emiliano Spezi,et al.  Assessing radiomic feature robustness to interpolation in 18F-FDG PET imaging , 2019, Scientific Reports.

[16]  Jesús Angulo,et al.  Advanced Statistical Matrices for Texture Characterization: Application to Cell Classification , 2014, IEEE Transactions on Biomedical Engineering.

[17]  Andre Dekker,et al.  Radiomics: the process and the challenges. , 2012, Magnetic resonance imaging.

[18]  Chintan Parmar,et al.  Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non–Small Cell Lung Cancer , 2017, The Journal of Nuclear Medicine.

[19]  D. Townsend,et al.  Impact of Image Reconstruction Settings on Texture Features in 18F-FDG PET , 2015, The Journal of Nuclear Medicine.

[20]  Hien Dang,et al.  The significance of intertumor and intratumor heterogeneity in liver cancer , 2018, Experimental & Molecular Medicine.

[21]  Chia-Chi Lin,et al.  Abstract 3725: Combined cytotoxic effects of volasertib and cisplatin in urothelial carcinoma cells , 2012 .

[22]  Vicky Goh,et al.  What can artificial intelligence teach us about the molecular mechanisms underlying disease? , 2019, European Journal of Nuclear Medicine and Molecular Imaging.

[23]  Stefan Förster,et al.  Textural analysis of pre-therapeutic [18F]-FET-PET and its correlation with tumor grade and patient survival in high-grade gliomas , 2015, European Journal of Nuclear Medicine and Molecular Imaging.

[24]  Jianhua Ma,et al.  Radiomic signature of 18F fluorodeoxyglucose PET/CT for prediction of gastric cancer survival and chemotherapeutic benefits , 2018, Theranostics.

[25]  N Hosten,et al.  Population Imaging as Valuable Tool for Personalized Medicine , 2012, Clinical pharmacology and therapeutics.

[26]  J. Brenton,et al.  Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging. , 2017, Clinical radiology.

[27]  Steffen Löck,et al.  Image biomarker standardisation initiative , 2016 .

[28]  Quanzheng Li,et al.  Iterative PET Image Reconstruction Using Convolutional Neural Network Representation , 2017, IEEE Transactions on Medical Imaging.

[29]  Andrzej Materka,et al.  Texture analysis for magnetic resonance imaging , 2006 .

[30]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[31]  Kyung-Han Lee,et al.  Correlations between metabolic texture features, genetic heterogeneity, and mutation burden in patients with lung cancer , 2018, European Journal of Nuclear Medicine and Molecular Imaging.

[32]  Dinggang Shen,et al.  3D conditional generative adversarial networks for high-quality PET image estimation at low dose , 2018, NeuroImage.

[33]  N. McGranahan,et al.  The causes and consequences of genetic heterogeneity in cancer evolution , 2013, Nature.

[34]  G. Fink,et al.  Predicting IDH genotype in gliomas using FET PET radiomics , 2018, Scientific Reports.

[35]  Thierry Denoeux,et al.  Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction , 2016, Medical Image Anal..

[36]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[37]  W. B. Marks,et al.  Fractal methods and results in cellular morphology — dimensions, lacunarity and multifractals , 1996, Journal of Neuroscience Methods.

[38]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[39]  Kyung Soo Lee,et al.  Quantitative image variables reflect the intratumoral pathologic heterogeneity of lung adenocarcinoma , 2016, Oncotarget.

[40]  M. Reiser,et al.  Population-Based Imaging and Radiomics: Rationale and Perspective of the German National Cohort MRI Study , 2016, Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren.

[41]  M. Hatt,et al.  Reproducibility of Tumor Uptake Heterogeneity Characterization Through Textural Feature Analysis in 18F-FDG PET , 2012, The Journal of Nuclear Medicine.

[42]  Robert King,et al.  Textural features corresponding to textural properties , 1989, IEEE Trans. Syst. Man Cybern..

[43]  Dimitris Visvikis,et al.  18F-FDG PET/CT heterogeneity quantification through textural features in the era of harmonisation programs: a focus on lung cancer , 2016, European Journal of Nuclear Medicine and Molecular Imaging.

[44]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[45]  Eric O. Aboagye,et al.  Discovery of pre-therapy 2-deoxy-2-18F-fluoro-D-glucose positron emission tomography-based radiomics classifiers of survival outcome in non-small-cell lung cancer patients , 2018, European Journal of Nuclear Medicine and Molecular Imaging.

[46]  M. Hatt,et al.  External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy , 2018, European Journal of Nuclear Medicine and Molecular Imaging.

[47]  H. Aerts,et al.  Applications and limitations of radiomics , 2016, Physics in medicine and biology.

[48]  William G. Wee,et al.  Neighboring gray level dependence matrix for texture classification , 1982, Comput. Graph. Image Process..

[49]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[50]  Jian Fan,et al.  Texture Classification by Wavelet Packet Signatures , 1993, MVA.

[51]  J. Reis-Filho,et al.  Pan-cancer analysis of intratumor heterogeneity as a prognostic determinant of survival , 2016, Oncotarget.

[52]  Robert J. Gillies,et al.  The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis , 2015, Scientific Reports.

[53]  Cornelis H. Slump,et al.  Repeatability of 18F‐FDG PET radiomic features: A phantom study to explore sensitivity to image reconstruction settings, noise, and delineation method , 2018, Medical physics.

[54]  Thomas Beyer,et al.  Optimized Feature Extraction for Radiomics Analysis of 18F-FDG PET Imaging , 2018, The Journal of Nuclear Medicine.

[55]  Ying Sun,et al.  Prognostic Value of Deep Learning PET/CT-Based Radiomics: Potential Role for Future Individual Induction Chemotherapy in Advanced Nasopharyngeal Carcinoma , 2019, Clinical Cancer Research.

[56]  Thomas J. Fuchs,et al.  DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problem , 2018, Medical Image Anal..

[57]  Polina Golland,et al.  Detecting stable distributed patterns of brain activation using Gini contrast , 2011, NeuroImage.