Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach

By Hugo J. W. L. Aerts, E. R. Velazquez, R. Leijenaar, Chintan Parmar, Patrick Grossmann, Sara Cavalho, J. Bussink, R. Monshouwer, Benjamin Haibe-Kains, D. Rietveld and 7 more. Nature Communications, 2014

4,696 citations recorded by the source corpus.

Human cancers exhibit strong phenotypic differences that can be visualized noninvasively by medical imaging. Radiomics refers to the comprehensive quantification of tumour phenotypes by applying a large number of quantitative image features. Here we present a radiomic analysis of 440 features quantifying tumour image intensity, shape and texture, which are extracted from computed tomography data of 1,019 patients with lung or head-and-neck cancer. We find that a large number of radiomic features have prognostic power in independent data sets of lung and head-and-neck cancer patients, many of which were not identified as significant before. Radiogenomics analysis reveals that a prognostic radiomic signature, capturing intratumour heterogeneity, is associated with underlying gene-expression patterns. These data suggest that radiomics identifies a general prognostic phenotype existing in both lung and head-and-neck cancer. This may have a clinical impact as imaging is routinely used in clinical practice, providing an unprecedented opportunity to improve decision-support in cancer treatment at low cost. An individual tumour is often heterogeneous and its various features can be visualised noninvasively using medical imaging. Here, the authors analyse large computed tomography data sets using radiomic algorithms to identify heterogeneity, and find that some of these tumour features have prognostic value across cancer types.

Subfields: Oncology, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/3b002068646831a6f59fabb6daeb0209ed54049d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Oncology

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Data Analysis Strategies in Medical Imaging (2018, background): “Similarly, it has been demonstrated that different radiomic features based on the shape, texture, and regional heterogeneity of the diseased tissues are associated with several clinical endpoints in oncology (4, 10, 11, 13, 25 – 32) and in other domains such as cardiology (14).”
Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images (2015, positive): “Our work demonstrates that PCa diagnosis can be improved by combining data-augmented classification together with more of the latent information in standard MRIs (the so-called “radiomics hypothesis”) (27, 28) compared with using ADC mean or T2 signal intensities alone, thereby reducing the potentia”
Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors and Machine-learning Approaches (2017, background): “14,31 Examples of texture features include gray-level co-occurrence matrices 32 and gray-level size zone matrices, 33 which examine the spatial relationships of pixels through a series of statistical measures.”
Machine Learning in Radiation Oncology: Opportunities, Requirements, and Needs (2018, background): “The limited reproducibility of imaging systems both within and across institutions remains a significant challenge for radiomics (65, 66).”
Innovative approaches for cancer treatment: current perspectives and new challenges (2019, background): “Radiomics is intended as the high throughput quantification of tumour properties obtained from the analysis of medical images [14, 15, 231].”
Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer (2015, methodology): “Some studies have investigated the reproducibility/variability of radiomic features across different clinical settings (2, 12–14).”
Repeatability and Reproducibility of Radiomic Features: A Systematic Review (2018, neutral): “Three studies evaluated the reproducibility of radiomic features with respect to multiple manual segmentations in the same patient (interobserver sensitivity) by use of PET (4, 39, 43).”
The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. (2016, neutral): “(2) Subsequently, the ROI is re-segmented to only contain values in the range [1, 6].”
Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation (2017, methodology): “Treatment therapy monitoring and lung nodule analysis (Aerts et al., 2014) using computed tomography (CT) images are important strategies for early lung cancer diagnosis and survival time improvement.”
A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change. (2018, methodology): “Specific quantitative imaging modeling studies were performed on a comprehensive list of tumor sites, including head and neck, (4, 8-13) lung, (3, 4, 14-18) breast, (19-29) liver, (30, 31) cervix, (32-36) prostate, (37, 38) extremities (sarcoma), (39, 40) and brain.”
The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges (2019, methodology): “Aerts et al. found the clusters of radiomic features were associated with the prognosis of lung cancer [4].”
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem (2020, methodology): “ity areas that are at risk of being excluded by threshold- or registrationbased methods, when they are close to the lung border. We utilized the publicly available, previously published Lung1 dataset [38] to quantify the model’s ability to cover tumor areas within the lung. The collection contains s”
Convolutional neural networks: an overview and application in radiology (2018, methodology): “Most recent radiomics studies use hand-crafted feature extraction techniques, such as texture analysis, followed by conventional machine learning classifiers, such as random forests and support vector machines [15, 16].”