Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology

Abstract

Medical image processing and analysis (also known as Radiomics) is a rapidly growing discipline that maps digital medical images into quantitative data, with the end goal of generating imaging biomarkers as decision support tools for clinical practice. The use of imaging data from routine clinical work-up has tremendous potential in improving cancer care by heightening understanding of tumor biology and aiding in the implementation of precision medicine. As a noninvasive method of assessing the tumor and its microenvironment in their entirety, radiomics allows the evaluation and monitoring of tumor characteristics such as temporal and spatial heterogeneity. One can observe a rapid increase in the number of computational medical imaging publications-milestones that have highlighted the utility of imaging biomarkers in oncology. Nevertheless, the use of radiomics as clinical biomarkers still necessitates amelioration and standardization in order to achieve routine clinical adoption. This Review addresses the critical issues to ensure the proper development of radiomics as a biomarker and facilitate its implementation in clinical practice.

Radiomic signature as a predictive factor for lymph node metastasis in early‐stage cervical cancer

“…Radiomics is a rapidly emerging discipline aiming to extract high‐throughput quantitative features from digital tomographic images (CT, MRI, or positron emission tomography) that can be converted into mineable high‐dimensional data. Radiomic features combined with patient/tumor characteristics can be leveraged via clinical decision support systems to improve medical decision‐making, in turn resulting in improved diagnostic, prognostic, and predictive accuracies, as well as facilitating therapeutic research . Thus, radiomic signature biomarkers may be helpful in identifying patients who may need LN biopsies.…”

Prediction of cervical cancer recurrence using textural features extracted from 18F-FDG PET images acquired with different scanners

“…Radiomics has great potential to influence patient care [14], from aiding diagnosis and classification of tumors by stage or histology [15–17], through the prediction of responses to radiotherapy [18] or to chemotherapy [19]. This technique can also be used to guide radiation therapy [20, 21].…”

Influence of temporal parameters of DCE‐MRI on the quantification of heterogeneity in tumor vascularization

“…A major challenge for radiomics approaches is to ensure a good quality of the quantitative data on which they rely. Besides reproducibility, repeatability, nonredundancy, and validity, quality here means controlling the bias due to slight variations in the imaging acquisition parameters . Standardizing the imaging protocols between radiological centers is unavoidable.…”

“…THE EXTENSIVE QUANTIFICATION of tumor heterogeneity on medical imaging is a growing field of research in oncology, referred to as radiomics. The underlying hypothesis of radiomics is that the imaging phenotype of a tumor could reflect its intrinsic molecular identities and aggressiveness . Texture analyses consist of the mathematical processing of images in order to extract numeric indices that objectively measure the heterogeneity, termed texture features.…”

“…The most commonly encountered ones in the medical literature are first‐order features, which are based on frequency histograms without spatial information, and second‐order features, which quantify the 2D and/or 3D rearrangements of voxels of different gray levels. Predictive radiomics approaches based on texture features, machine‐learning algorithms, and the potential combination with clinical characteristics and other ‐omics data (ie, genomics, transcriptomics, proteomics, and metabolomics) could help better stratify the therapeutic strategy for cancer patients and evaluate treatment responses …”