Synthetic Post-Contrast Imaging through Artificial Intelligence: Clinical Applications of Virtual and Augmented Contrast Media

Abstract

Contrast media are widely diffused in biomedical imaging, due to their relevance in the diagnosis of numerous disorders. However, the risk of adverse reactions, the concern of potential damage to sensitive organs, and the recently described brain deposition of gadolinium salts, limit the use of contrast media in clinical practice. In recent years, the application of artificial intelligence (AI) techniques to biomedical imaging has led to the development of 'virtual' and 'augmented' contrasts. The idea behind these applications is to generate synthetic post-contrast images through AI computational modeling starting from the information available on other images acquired during the same scan. In these AI models, non-contrast images (virtual contrast) or low-dose post-contrast images (augmented contrast) are used as input data to generate synthetic post-contrast images, which are often undistinguishable from the native ones. In this review, we discuss the most recent advances of AI applications to biomedical imaging relative to synthetic contrast media.

Keywords: CT; MRI; artificial intelligence; augmented contrast; cardiac imaging; gadolinium-based contrast agents; iodinated contrast agents; neuroimaging; synthetic imaging; virtual contrast.

Figure 1

The CycleGAN model consists of a forward cycle and a backward cycle. (a) In the forward cycle, a synthesis network $Synt{h}_c$ is trained to translate an input non-contrast image into a contrast one. Network $Synt{h}_{nc}$ is trained to translate the resulting contrast image back into a non-contrast image that approximates the original non-contrast one. $Dis{c}_c$ discriminates between real and synthesized contrast images. (b) In the backward cycle, $Synt{h}_{nc}$ synthesizes non-contrast images from input contrast images, $Synt{h}_c$ reconstructs the input contrast image from the synthesized non- contrast one, and $Dis{c}_{nc}$ discriminates between real and synthesized non-contrast images. $I_{nc}$ = original non-contrast image; $I_c$ = original contrast image.