Advanced atherosclerosis imaging by CT: Radiomics, machine learning and deep learning

In the last decade, technical advances in the field of medical imaging significantly improved and broadened the application of coronary CT angiography (CCTA) for the non-invasive assessment of coronary artery disease. Recently, similar breakthroughs are happening in the post-processing, analysis and interpretation of radiological images. Technologies such as radiomics allow to extract significantly more information from scans than what human visual assessment is capable of. This allows the precision phenotyping of diseases based on medical images. The increased amount of information can then be analyzed using novel data analytic techniques such as machine learning (ML) and deep learning (DL), which utilize the power of big data to build predictive models, which seek to mimic human intelligence, artificially. Thanks to big data availability and increased computational power, these novel analytic methods are outperforming conventional statistical techniques. In this current overview we describe the basics of radiomics, ML and DL, highlighting similarities, differences, limitations and potential pitfalls of these techniques. In addition, we provide a brief overview of recently published results on the applications of the aforementioned techniques for the non-invasive assessment of coronary atherosclerosis using CCTA.