Contrast Agent Dose Reduction in MRI Utilizing a Generative Adversarial Network in an Exploratory Animal Study

Abstract

Objectives: The aim of this study is to use virtual contrast enhancement to reduce the amount of hepatobiliary gadolinium-based contrast agent in magnetic resonance imaging with generative adversarial networks (GANs) in a large animal model. Methods: With 20 healthy Göttingen minipigs, a total of 120 magnetic resonance imaging examinations were performed on 6 different occasions, 50% with reduced (low-dose; 0.005 mmol/kg, gadoxetate) and 50% standard dose (normaldose; 0.025 mmol/kg). These included arterial, portal venous, venous, and hepatobiliary contrast phases (20 minutes, 30 minutes). Because of incomplete examinations, one animal had to be excluded. Randomly, 3 of 19 animals were selected and withheld for validation (18 examinations). Subsequently, a GAN was trained for imageto-image conversion from low-dose to normal-dose (virtual normal-dose) with the remaining 16 animals (96 examinations). For validation, vascular and parenchymal contrast-to-noise ratio (CNR) was calculated using region of interest measurements of the abdominal aorta, inferior vena cava, portal vein, hepatic parenchyma, and autochthonous back muscles. In parallel, a visual Turing test was performed by presenting the normal-dose and virtual normal-dose data to 3 consultant radiologists, blinded for the type of examination. They had to decide whether they would consider both data sets as consistent in findings and which images were from the normal-dose study. Results: The pooled dynamic phase vascular and parenchymal CNR increased significantly from low-dose to virtual normal-dose (pooled vascular: P < 0.0001, pooled parenchymal: P = 0.0002) and was found to be not significantly different between virtual normal-dose and normal-dose examinations (vascular CNR [mean ± SD]: low-dose 17.6 ± 6.0, virtual normal-dose 41.8 ± 9.7, and normal-dose 48.4 ± 12.2; parenchymal CNR [mean ± SD]: low-dose 20.2 ± 5.9, virtual normaldose 28.3 ± 6.9, and normal-dose 29.5 ± 7.2). The pooled parenchymal CNR of the hepatobiliary contrast phases revealed a significant increase from the low-dose (22.8 ± 6.2) to the virtual normal-dose (33.2 ± 6.1; P < 0.0001) and normal-dose sequence (37.0 ± 9.1; P < 0.0001). In addition, there was no significant difference between the virtual normal-dose and normal-dose sequence. In the visual Turing test, on the median, the consultant radiologist reported that the sequences of the normal-dose and virtual normal-dose are consistent in findings in 100% of the examinations. Moreover, the consultants were able to identify the normal-dose series as such in a median 54.5% of the cases. Conclusions:In this feasibility study in healthy Göttingen minipigs, it could be shown that GAN-based virtual contrast enhancement can be used to recreate the image impression of normal-dose imaging in terms of CNR and subjective image similarity in both dynamic and hepatobiliary contrast phases from low-dose data with an 80% reduction in gadolinium-based contrast agent dose. Before clinical implementation, further studies with pathologies are needed to...

AI as a New Frontier in Contrast Media Research

“…The only approaches to reduce the amount of contrast agents with true low-dose and normal-dose datasets via AI-based image-to-image conversion in dynamic contrast agent phases have been acquired in animal experiments to date. 3,14 These were able to show that the technology works in this setting, but they have 2 major drawbacks. It is hardly possible to show the diversity of human pathologies in animal experiments and thus validate the algorithm with these pathologies, and on the other hand, these algorithms, because they also learn anatomical information, are only limited to transfer to humans.…”

“…The use of AI as a new frontier of contrast media research has shown promising results in recent studies, both in the context of MRI and CT imaging. 1,3,6,14,28 The potential of AI in reducing contrast agent doses, as well as the feasibility of eliminating contrast agent use entirely, has been explored in several studies, 1,3,4,6,7,14,38 and new application areas for AI in contrast agent management have been proposed. 2 Yet, as the reviewed studies have shown, the diagnostic accuracy of AI-based approaches for contrast agent reduction may be dose dependent 10 or pathology dependent, particularly for small lesions.…”

“…A rtificial intelligence (AI) techniques, particularly generative adversarial networks (GANs), have shown significant potential in processing medical image data. In recent studies, AI-based approaches have demonstrated the possibility of reducing the amount of gadolinium-based contrast agents (GBCAs) in magnetic resonance imaging (MRI) [1][2][3][4][5][6][7][8] and iodine-based contrast media (ICM) in computed tomography (CT). [9][10][11][12][13][14] For both modalities, the amount of contrast agent respectively can be technically optimized in completely different ways, for example, by means of applications for the optimization of the radiation spectrum such as CareKV 15 for CT or by means of sequence, 16 molecule relaxivity, 17,18 and acquisition time optimization for MRI.…”

fRegGAN with K-space Loss Regularization for Medical Image Translation

“…Generative adversarial networks (GANs) [8] have gained a lot of attention in the last years due to their ability to generate realistic images. In the medical imaging field, they are often used for image-to-image translation problems, such as mapping magnetic resonance imaging (MRI) to computed tomography images [17,24], T1-weighted to T2-weighted MRI [14,22], or low-to high dose contrast enhanced MRIs [9,19]. Such approaches could potentially reduce healthcare costs and patient burden while maintaining or even improving the diagnostic value of a modality.…”

A New Era in Magnetic Resonance Contrast Media

“…Introduction of this terminology added potentially to some confusion, as this entity and its associated symptoms (which include includes neurologic, cognitive, musculoskeletal, and other nonspecific complaints) were previously known by the terms gadolinium deposition disease and gadolinium storage condition. [26][27][28][29] Last in order but of great importance today (and potential impact upon the use of MR contrast media) is the use of artificial intelligence (AI) techniques in magnetic resonance and specifically their impact on contrast utilization-whether it be reduction of dose, [30][31][32][33] allowing new applications, 34 or the elimination of use in specific areas. [35][36][37] For the latter, it is still too early to come to any conclusions, and likely the answer is not straightforward.…”