Radiomics: Principles and radiotherapy applications

https://doi.org/10.1016/j.critrevonc.2019.03.015Get rights and content

Abstract

Radiomics is defined as the extraction of a large quantity of quantitative image features. The different radiomic indexes that have been proposed in the literature are described as well as the various factors that have an impact on the robustness of these indexes. We will see that several hundred quantitative features can be extracted per lesion and imaging modality. The ever-growing number of features studied raises the question of the statistical method of analysis used.

This review addresses the research supporting the clinical use of radiomics in oncology in the staging of disease, discrimination between healthy and pathological tissues, the identification of genetic features, the prediction of patient survival, the response to treatment, the recurrence after radiotherapy and chemoradiotherapy and the side effects.

Based on the existing literature, it remains difficult to identify features that should be used for current clinical practice.

Section snippets

Concept of radiomics

Medical imaging, such as computed tomography (CT), positron emission tomography (PET) using FDG radioactive glucose analogue, and magnetic resonance imaging (MRI) are used routinely in the clinical management of cancer patients. They tend to play a leading role in personalised treatment based on tumour imaging. Personalised medicine has been largely developed using invasive techniques based on genomics and proteomics. However, there is a spatial and temporal heterogeneity of tumour features (

Image features

Numerous image features have been proposed in the literature (Sollini et al., 2017). Features based on the shape and size of the lesion, histogram features based on first-order statistics, texture features, and filter- and model-based features are generally distinguished (see Fig. 1).

Medical applications

Various reviews of the literature (Marusyk et al., 2012; Kumar et al., 2012; Yip and Aerts, 2016; Sollini et al., 2017; Scalco and Rizzo, 2017) show that many studies support the clinical interest of radiomics in oncology, both in MR, CT, and FDG PET imaging, particularly for patients treated using radiotherapy for many localisations (NSCLC, H&N, oesophagus, breast, cervix, etc.). Before treatment, this concerns the staging of the disease and the identification of genetic features. For

Factors influencing radiomic features

The very encouraging results of radiomics, however, raise the issue of the robustness of features with respect to the experimental conditions and image processing performed before their extraction as well as the manner of extraction.

Methods of radiomic analysis

The ever-growing number of features studied raises the question of the statistical method of analysis used and its quality, especially as patient databases can be limited.

Conclusions and perspectives

Numerous articles support the clinical use of radiomic analysis in oncology, as well as on MRI, CT than on FDG PET images, in staging of the disease, significantly differentiating the early and advanced stages of the disease, tissue discrimination between healthy and pathological tissues, demonstrating genetic characteristics, predicting the response to treatment, patient survival, and side effects. These results from the literature mainly concern solid tumours for many localisations

Financial disclosure statement

This work was supported by grant from the Cancéropôle Nord-Ouest, France.

References (63)

  • R. Lopes et al.

    Fractal and multifractal analysis: a review

    Med. Image Anal.

    (2009)
  • S.A. Mattonen et al.

    Detection of local Cancer recurrence after stereotactic ablative radiation therapy for lung Cancer: physician performance versus radiomic assessment

    Int. J. Radiat. Oncol. Biol. Phys.

    (2016)
  • A. Moran et al.

    Radiomics-based Assessment of Radiation-induced Lung Injury After Stereotactic Body Radiotherapy

    Clin. Lung Cancer

    (2017)
  • F. Ng et al.

    Assessment of tumor heterogeneity by CT texture analysis: Can the largest cross-sectional area be used as an alternative to whole tumor analysis?

    Eur. J. Radiol.

    (2013)
  • M. Pota et al.

    Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification

    Artif. Intell. Med.

    (2017)
  • L.V. van Dijk et al.

    CT image biomarkers to improve patient-specific prediction of radiation-induced xerostomia and sticky saliva

    Radiother. Oncol.

    (2017)
  • H. Yu et al.

    Automated radiation targeting in head-and-Neck Cancer Using region-based texture analysis of PET and CT images

    Int. J. Radiat. Oncol. Biol. Phys.

    (2009)
  • H.J.W.L. Aerts et al.

    Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

    Nat. Commun.

    (2014)
  • L. Alic et al.

    Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

    PLoS One

    (2014)
  • M. Amadasun et al.

    Textural features corresponding to textural properties

    IEEE Trans. Syst. Man Cybern.

    (1989)
  • G.J. Anthony et al.

    Incorporation of pre-therapy 18F-FDG uptake data with CT texture features into a radiomics model for radiation pneumonitis diagnosis

    Med. Phys.

    (2017)
  • Y. Balagurunathan et al.

    Test-retest reproducibility analysis of lung CT image features

    J. Digit. Imaging

    (2014)
  • L. Breiman

    Random forests

    Mach. Learn.

    (2001)
  • F.J. Brooks et al.

    The Effect of Small Tumor Volumes on Studies of Intratumoral Heterogeneity of Tracer Uptake

    J. Nucl. Med.

    (2014)
  • K. Buch et al.

    Using texture analysis to determine human papillomavirus status of oropharyngeal squamous cell carcinomas on CT

    Am J Neuroradiol

    (2015)
  • R.A. Bundschuh et al.

    Textural parameters of tumor heterogeneity in 18F-FDG PET/CT for therapy response assessment and prognosis in patients with locally advanced rectal Cancer

    J. Nucl. Med.

    (2014)
  • I. Buvat et al.

    Tumor texture analysis in PET: where do we stand?

    J. Nucl. Med.

    (2015)
  • J. Calais et al.

    Areas of high 18F-FDG uptake on preradiotherapy PET/CT identify preferential sites of local relapse after chemoradiotherapy for non-small cell lung cancer

    J. Nucl. Med.

    (2015)
  • A. Chalkidou et al.

    False discovery rates in PET and CT studies with texture features: a systematic review

    PLoS One

    (2015)
  • C. Cortes et al.

    Support-vector networks

    Mach. Learn.

    (1995)
  • P. Desbordes et al.

    Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemo-radiation therapy using a random forest classifier

    PLoS One

    (2017)
  • Cited by (0)

    View full text