Maryam Elikaei Moghadam - Department of Medical Imagin, Iran University of Medical science, Tehran, Iran

The term "Radiomics" denotes the process of extracting and analysing copious amounts of advanced quantitative imaging features from medical images obtained through computed tomography (CT), positron emission tomography (PET), or magnetic resonance imaging (MRI) techniques. It is critical to note that these data are meant to be extracted from standard-of-care images, thereby leading to a vast potential subject pool [۱]. Radiomic data can be mined effectively to construct both descriptive and predictive models that relate image features with phenotypes or gene-protein signatures. In medicine, various ways to generate big data exist, including the widely known fields of genomics, proteomics, or metabolomics. Similar to these “omics” clusters, imaging has been used increasingly to generate a dedicated omics cluster itself called “radiomics”. Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced, and sometimes nonintuitive mathematical analysis [۲,۳]. In essence, the fundamental hypothesis of radiomics is that these models, which may incorporate biological or medical data, can provide valuable diagnostic, prognostic, or predictive information. The radiomics endeavour can be split into different processes, each with its unique challenges that require overcoming, including (i) image acquisition and reconstruction, (ii) image segmentation and rendering, (iii) feature extraction and qualification, (iv) databases and data sharing for eventual (v) ad hoc informatic analyses. Each of these processes presents particular challenges that must be addressed [۱,۴,۵,۶]. In this research, by examining ۲۵ articles from various databases such as Scopus, Science Direct and etc in the field of radiomics and artificial intelligence, I came to the conclusion that despite all the challenges facing this field of science and its entry into the field of medical imaging, it can produce remarkable results. in the diagnosis and follow-up of various diseases, including cancer.

Radiomics, Image features, Quantitative imaging biomarkers, Artificial intelligent, Machine learning