Radiomics: Extracting more information from medical images using advanced feature analysis

Abstract

Solid cancers are spatially and temporally heterogeneous. This limits the use of invasive biopsy based molecular assays but gives huge potential for medical imaging, which has the ability to capture intra-tumoural heterogeneity in a non-invasive way. During the past decades, medical imaging innovations with new hardware, new imaging agents and standardised protocols, allows the field to move towards quantitative imaging. Therefore, also the development of automated and reproducible analysis methodologies to extract more information from image-based features is a requirement. Radiomics – the high-throughput extraction of large amounts of image features from radiographic images – addresses this problem and is one of the approaches that hold great promises but need further validation in multi-centric settings and in the laboratory.

Reproducibility of F18‐FDG PET radiomic features for different cervical tumor segmentation methods, gray‐level discretization, and reconstruction algorithms

“…These characteristics made textural features superior to SUV measurements regarding tumor heterogeneity characterization. Also, shape features (SF), which describe geometrical characteristics of tumors, have shown to provide a morphological characterization of PET uptake heterogeneity within a specified volume of interest 24, 25. Recent studies have emphasized on the higher discriminatory power of several radiomic features in comparison to SUV measurements regarding classification of tumor versus benign regions in lung, and head‐and‐neck patients,26 as well as for the prediction of cervical cancer treatment outcomes 27.…”

Robustness of intratumour 18F-FDG PET uptake heterogeneity quantification for therapy response prediction in oesophageal carcinoma

“…More recently, intra-tumour uptake heterogeneity has been identified as a potential source of treatment failure [11] and its characterization through 18 F-FDG PET imaging is currently generating a substantial amount of interest [12][13][14][15]. Such characterization provides additional and complementary PET image derived quantitative indices with potential value as already demonstrated in predicting therapy response or as prognostic factors in several cancers including lung [16], sarcoma [17], oesophageal [18,19] and rectal cancer [20].…”

Integrative methods for analyzing big data in precision medicine

“…Using novel high-throughput capturing technologies, we are now able to access the DNA of an individual (genetic data), the transcribed RNA over time (expression and co-expression data), proteins (protein profiles and protein interaction data), metabolism (metabolic profiles) and epigenome (DNA methylation data), among other data types [10]. The environment is also taken into account (e.g., nutrition and bacterial environment by nutriomics and metagenomics, respectively) [11,12], and also histopathological and medical imaging data are now subject to high throughput capturing and analysis methods [13][14][15][16].…”