Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media?

Abstract

In recent years, cardiovascular imaging examinations have experienced exponential growth due to technological innovation, and this trend is consistent with the most recent chest pain guidelines. Contrast media have a crucial role in cardiovascular magnetic resonance (CMR) imaging, allowing for more precise characterization of different cardiovascular diseases. However, contrast media have contraindications and side effects that limit their clinical application in determinant patients. The application of artificial intelligence (AI)-based techniques to CMR imaging has led to the development of non-contrast models. These AI models utilize non-contrast imaging data, either independently or in combination with clinical and demographic data, as input to generate diagnostic or prognostic algorithms. In this review, we provide an overview of the main concepts pertaining to AI, review the existing literature on non-contrast AI models in CMR, and finally, discuss the strengths and limitations of these AI models and their possible future development.

Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes

“…ML refers to the ability of AI systems to extract patterns in raw data without being explicitly programmed to do so. It involves training a model through the utilization of data with known ground-truths to subsequently generate predictions for new, unseen inputs [ 12 , 14 ]. ML models can be broadly classified into different classes according to the type of experience which they are authorized to undergo throughout their training processes, including supervised, unsupervised, and hybrid paradigms such as semi-supervised learning, weakly supervised learning, and self-supervised learning [ 7 , 15 ].…”

“…With regards to CMR, non-contrast CMR examinations combined with AI have shown promising results, enabling faster, more accessible, and cost-effective CMR images that unquestionably offer advantages in the clinical assessment of cardiomyopathy [ 14 ]. This becomes particularly relevant in light of the anticipated exponential rise in CMR examinations in accordance with the recent ESC guidelines [ 1 ].…”

Atrial and Ventricular Strain Imaging Using CMR in the Prediction of Ventricular Arrhythmia in Patients with Myocarditis

“…This makes it a viable option for patients with concomitant renal disease, allergies to gadolinium, or limited tolerance due to cardiac symptoms such as orthopnea [26][27][28][29]. Promising diagnostic possibilities are emerging with abbreviated CMR protocols that omit the use of contrast media [30][31][32][33]. Identifying predictive CMR parameters derived from an abbreviated CMR protocol is expected to unquestionably yield significant advantages in real-life clinical practice.…”