Can Virtual Contrast Enhancement in Brain MRI Replace Gadolinium?

Abstract

Objectives Gadolinium-based contrast agents (GBCAs) have become an integral part in daily clinical decision making in the last 3 decades. However, there is a broad consensus that GBCAs should be exclusively used if no contrast-free magnetic resonance imaging (MRI) technique is available to reduce the amount of applied GBCAs in patients. In the current study, we investigate the possibility of predicting contrast enhancement from noncontrast multiparametric brain MRI scans using a deep-learning (DL) architecture. Materials and Methods A Bayesian DL architecture for the prediction of virtual contrast enhancement was developed using 10-channel multiparametric MRI data acquired before GBCA application. The model was quantitatively and qualitatively evaluated on 116 data sets from glioma patients and healthy subjects by comparing the virtual contrast enhancement maps to the ground truth contrast-enhanced T1-weighted imaging. Subjects were split in 3 different groups: enhancing tumors (n = 47), nonenhancing tumors (n = 39), and patients without pathologic changes (n = 30). The tumor regions were segmented for a detailed analysis of subregions. The influence of the different MRI sequences was determined. Results Quantitative results of the virtual contrast enhancement yielded a sensitivity of 91.8% and a specificity of 91.2%. T2-weighted imaging, followed by diffusion-weighted imaging, was the most influential sequence for the prediction of virtual contrast enhancement. Analysis of the whole brain showed a mean area under the curve of 0.969 ± 0.019, a peak signal-to-noise ratio of 22.967 ± 1.162 dB, and a structural similarity index of 0.872 ± 0.031. Enhancing and nonenhancing tumor subregions performed worse (except for the peak signal-to-noise ratio of the nonenhancing tumors). The qualitative evaluation by 2 raters using a 4-point Likert scale showed good to excellent (3–4) results for 91.5% of the enhancing and 92.3% of the nonenhancing gliomas. However, despite the good scores and ratings, there were visual deviations between the virtual contrast maps and the ground truth, including a more blurry, less nodular-like ring enhancement, few low-contrast false-positive enhancements of nonenhancing gliomas, and a tendency to omit smaller vessels. These “features” were also exploited by 2 trained radiologists when performing a Turing test, allowing them to discriminate between real and virtual contrast-enhanced images in 80% and 90% of the cases, respectively. Conclusions The introduced model for virtual gadolinium enhancement demonstrates a very good quantitative and qualitative performance. Future systematic studies in larger patient collectives with varying neurological disorders need to evaluate if the introduced virtual contrast enhancement might reduce GBCA exposure in clinical practice.

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

“…DL methods have been used for improving PET image quality, reducing noise [54], removing streak artifacts from CT [55], and developing novel techniques for tomographic image reconstruction based on a reduced amount of acquired data. Other promising applications are a generation of synthetic images, such as synthetic CT from MRI [56], virtual contrast-enhanced images [57], and rigid/deformable intramodal and multimodal image registration [58], and extraction of the respiratory signal [21] that could be used for breathing motion compensation of images [59].…”

Deep Learning Substitutes Gadolinium in Detecting Functional and Structural Brain Lesions with MRI

“…Next, we retrained the same network architecture after adding brain MRI scans from 6 mice with glioblastoma multiforme (GBM) into the training set. Similar to a previous study 14 , we compared the similarity between the predicted and ground truth maps by performing a receiver operating characteristic (ROC) analysis to measure the similarity of the high-enhancement regions (Fig. 2f) in addition to the quantitative similarity metrics above ( Fig.…”

“…A deep learning model should therefore be able to learn how to optimally extract this information, by training the model on previously-acquired MRI datasets where GBCAs were administered. Indeed, a growing number of recent studies have begun validating this assumption [13][14][15] . Nevertheless, among these, one study managed to use deep learning to reduce the GBCA dose 13 , but not to completely substitute it.…”

“…Nevertheless, among these, one study managed to use deep learning to reduce the GBCA dose 13 , but not to completely substitute it. Other studies succeeded in obviating the need for GBCA 14,15 , but the deep learning models require the acquisition of an array of either six or ten different MRI sequences, some that are not widely available.…”

AI in Radiology: Where are we today in Multiple Sclerosis Imaging?

“…In diesem Kontext erscheint es als ein besonders interessantes Ziel, eine T1-gewichtete Sequenz nach Kontrastmittelgabe basierend auf nativer Bildgebung zu synthetisieren. Eine derartige Studie wurde kürzlich von Kleesiek et al für Gliome vorgestellt [50].…”