Radiomics – the value of the numbers in present and future radiology

Abstract

Radiomics is a new concept that has been functioning in medicine for only a few years. This idea, created recently, relies on processing innumerable quantities of metadata acquired from every examination, followed by extraction thereof from relevant imaging examinations, such as computer tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET) images, by means of appropriate created algorithms. The extracted results have great potential and broad possibilities of application. Thanks to these we can verify efficiency of treatment, predict locations of metastases of tumours, correlate results with histopathological examinations, or define the type of cancer more precisely. In effect, we obtain more personalised treatment for each patient, which is extremely important and highly recommendable in the tests and applicable treatment therapies conducted nowadays. Radiomics is a non-invasive and high efficiency post-processing method. This article is intended to explain the idea of radiomics, the mechanisms of data acquisition, existing possibilities, and the challenges incurred by radiologists and physicians at the stage of making diagnosis or conducting treatment.

Longitudinal CT Imaging to Explore the Predictive Power of 3D Radiomic Tumour Heterogeneity in Precise Imaging of Mantle Cell Lymphoma (MCL)

“…Studies prove the quantification of tumour heterogeneity as a promising tool for monitoring treatment response and clinical outcome [ 21 , 28 , 46 ]. Radiomics is an innovative field of computer-based research that reveals disease characteristics from medical images that are not visually seen to non-invasively quantify tumour heterogeneity for precision medicine [ 18 , 19 , 20 ]. Studies have shown that radiomics may improve the accuracy of diagnosis and prediction to support clinical decision-making using different imaging techniques in various malignancies, however, there is still limited evidence in Lymphoma, especially MCL [ 30 , 33 , 34 , 35 , 47 , 48 , 49 , 50 , 51 , 52 , 53 ].…”

“…The emergence of technological innovation and the urge to fulfil personalized medicine has given rise to the constantly evolving field of research called “radiomics”—a computer-assisted technique for extracting and quantifying patterns, so-called radiomic features within diagnostic medical images to reflect the radiographic phenotype using data characterization algorithms. By capturing signal intensity distribution, i.e., grey-level patterns, radiomics quantifies a large panel of phenotypic characteristics, such as shape and texture, potentially reflecting intra- and intertumour heterogeneities [ 18 , 19 , 20 , 21 , 22 , 23 ].…”

Color Doppler Ultrasound Improves Machine Learning Diagnosis of Breast Cancer

“…Radiomics, the diagnosis of medical images through the automated extraction and analysis of predictive quantitative features, has been increasingly used in medical imaging, especially X-ray tomography and tomosynthesis, computer tomography (CT), positron emission tomography (PET), and magnetic resonance imaging (MRI) [ 32 ]. Most breast cancer radiomics studies are on MRI or mammography, and relatively few use ultrasound features [ 33 , 34 , 35 , 36 ].…”

Detection of Microstructural Medial Prefrontal Cortex Changes Using Magnetic Resonance Imaging Texture Analysis in a Post-Traumatic Stress Disorder Rat Model

“…The term radiomics, which was first introduced by Lambin et al ( 19 ), refers to the high-throughput processing and analysis of quantitative data extracted from medical images with a view to discovering meaningful associations between these data and particular disease features. Radiomics has been widely applied in the management of a wide range of cancers, and it can improve the accuracy of diagnosis, evaluate therapeutic effects, and assess overall prognosis ( 20 – 25 ). Furthermore, emerging clinical and experimental studies have shown that MR texture analysis (MRTA) can be used to as neuroimaging markers for many neurological diseases ( 26 – 31 ); it can provide an early, non-invasive, and accurate method to detect many neurodegenerative diseases because it can detect unseen or subtle signal changes and thus obtain latent image information ( 32 – 35 ).…”