Abstract
Radiomics is a novel image analysis technique, whereby voxel-level information is extracted from digital images and used to derive multiple numerical quantifiers of shape and tissue character. Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function. Conventional analysis of CMR scans is mostly reliant on qualitative image analysis and basic geometric quantifiers. Small proof-of-concept studies have demonstrated the feasibility and superior diagnostic accuracy of CMR radiomics analysis over conventional reporting. CMR radiomics has the potential to transform our approach to defining image phenotypes and, through this, improve diagnostic accuracy, treatment selection, and prognostication. The purpose of this article is to provide an overview of radiomics concepts for clinicians, with particular consideration of application to CMR. We will also review existing literature on CMR radiomics, discuss challenges, and consider directions for future work.
Highlights
Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function; its use in clinical practice is increasingly widespread
Through existing analysis approaches, it may not be possible to distinguish with certainty between disease entities that appear morphologically similar, such as hypertensive heart disease and hypertrophic cardiomyopathy (HCM) or athletic cardiac remodelling and dilated cardiomyopathy
Many patients with prophylactic intracardiac defibrillators based on low ejection fraction never require therapies from their device,[1] whilst only 30% of sudden cardiac death patients would qualify for a primary prevention device based on current guidelines.[2]
Summary
Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function; its use in clinical practice is increasingly widespread. Consider the pink cell (j = 1, i = 1); in the matrix of Panel A, we count two instances of voxels with SI of 1 (i = 1) occurring in an analysis is to recognize and quantitatively describe various SI patterns uninterrupted run of length 1 (j = 1), the cell is filled with the within the selected ROI This is achieved by numerically defining the SIs within the segmented volume and describing observed patterns using mathematical definitions. Descriptors of spatial distribution of signal intensities In order to consider the relationship of neighbouring voxel SIs, more complex mathematical approaches to analysis of the SI matrix are required These features are derived by considering the spatial distribution of SIs within the ROI and aim to quantify heterogeneity, repeatability, and complexity of the SI matrix.[26,27] They are computed through application of various mathematical processes to new matrices which are constructed according to specified rules from the original SI matrix. The main overarching motivator driving radiomics analysis is that certain radiomics features will correspond to particular disease states, and once identified, blueprints of radiomics features (radiomics signatures) may be used to accurately classify disease entities and clinical outcomes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
