Evolving Role and Translation of Radiomics and Radiogenomics in Adult and Pediatric Neuro-Oncology

Abstract

Exponential technologic advancements in imaging, high-performance computing, and artificial intelligence, in addition to increasing access to vast amounts of diverse data, have revolutionized the role of imaging in medicine. Radiomics is defined as a high-throughput feature-extraction method that unlocks microscale quantitative data hidden within standard-of-care medical imaging. Radiogenomics is defined as the linkage between imaging and genomics information. Multiple radiomics and radiogenomics studies performed on conventional and advanced neuro-oncology image modalities show that they have the potential to differentiate pseudoprogression from true progression, classify tumor subgroups, and predict recurrence, survival, and mutation status with high accuracy. In this article, we outline the technical steps involved in radiomics and radiogenomics analyses with the use of artificial intelligence methods and review current applications in adult and pediatric neuro-oncology.

18F-FDG PET/CT-based radiomics nomogram could predict bone marrow involvement in pediatric neuroblastoma

“…Radiomics analysis converts medical images into mineable high-dimensional data by extracting innumerable quantitative features with high-throughput computing [ 12 ]. Once the high-dimension feature data describing quantitative attributes of volumes of interest is available, artificial intelligence, machine learning, or statistical approaches can be used to build classifier or regression modeling for disease detection, diagnosis, evaluation of prognosis and prediction of treatment response.…”

Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine

“…The potential of radiogenomics in tumor diagnosis, prognosis, and prediction is immense; however, translations into clinical settings are slow due to several associated challenges [ 175 ]. Adopting radiogenomics practices into clinical settings needs to overcome these significant challenges.…”

Editorial for “Investigation of the Inter‐ and Intra‐Scanner Reproducibility and Repeatability of Radiomics Features in Magnetic Resonance Imaging”

“…Features can also be extracted from images that are preprocessed by filters (eg, wavelet or Laplacian filters), as well as may stem from image fractal features 4 . They can also be, however, based on machine learning techniques 1 . One of such important tasks is a texture analysis—which is defined as a spatial distribution of an image that contains information on the local aspects of the tissue.…”

“…Furthermore, radiomics as a process can be divided into consecutive steps: acquisition of the medical images, identification of the volume of interest that relates to the pathology and its segmentation, extraction of relevant features describing the pathology, creating or sharing databases, and, finally, proposition with validation of predictive models. [1][2][3][4] This is the main reason why radiomics holds the promise of discovering hidden correlations and bringing transparency into radiologists' decisionmaking, respectively. One could summarize that radiomics is rather an approach than a specific method and that images are regarded as data rather than pictures.…”

“…4 They can also be, however, based on machine learning techniques. 1 One of such important tasks is a texture analysis-which is defined as a spatial distribution of an image that contains information on the local aspects of the tissue. To describe texture, we can use words in natural language such as coarseness, smoothness, or perhaps because it is difficult to grasp this concept in natural language a description by quantifiable features could be orthogonal and thus useful.…”