Can Virtual Contrast Enhancement in Brain MRI Replace Gadolinium?: A Feasibility Study.

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.

[1]  Bolei Zhou,et al.  DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation , 2018, Issue 3.4, Fall 2021.

[2]  Martin Blaimer,et al.  Simultaneous T1 and T2 measurements using inversion recovery TrueFISP with principle component‐based reconstruction, off‐resonance correction, and multicomponent analysis , 2019, Magnetic resonance in medicine.

[3]  David Bonekamp,et al.  Automated brain extraction of multisequence MRI using artificial neural networks , 2019, Human brain mapping.

[4]  Yuval Elovici,et al.  CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning , 2019, USENIX Security Symposium.

[5]  Aykut Erdem,et al.  Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks , 2018, IEEE Transactions on Medical Imaging.

[6]  D. Cahill,et al.  Radiographic assessment of contrast enhancement and T2/FLAIR mismatch sign in lower grade gliomas: correlation with molecular groups , 2018, Journal of Neuro-Oncology.

[7]  Klaus H. Maier-Hein,et al.  No New-Net , 2018, 1809.10483.

[8]  Marcus A. Badgeley,et al.  Automated deep-neural-network surveillance of cranial images for acute neurologic events , 2018, Nature Medicine.

[9]  Doina Precup,et al.  Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation , 2018, MICCAI.

[10]  J. Pauly,et al.  Deep learning enables reduced gadolinium dose for contrast‐enhanced brain MRI , 2018, Journal of magnetic resonance imaging : JMRI.

[11]  Jeffrey L. Gunter,et al.  Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks , 2018, SASHIMI@MICCAI.

[12]  Mert R. Sabuncu,et al.  Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration , 2018, MICCAI.

[13]  Samuel J. Yang,et al.  In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images , 2018, Cell.

[14]  A. Enk,et al.  Sensitivity of different MRI sequences in the early detection of melanoma brain metastases , 2018, PloS one.

[15]  Sashank J. Reddi,et al.  On the Convergence of Adam and Beyond , 2018, ICLR.

[16]  Srikrishna Varadarajan,et al.  RADnet: Radiologist level accuracy using deep learning for hemorrhage detection in CT scans , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[17]  Mark Sandler,et al.  CycleGAN, a Master of Steganography , 2017, ArXiv.

[18]  Andrew Y. Ng,et al.  CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning , 2017, ArXiv.

[19]  Klaus H. Maier-Hein,et al.  Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge , 2017, BrainLes@MICCAI.

[20]  Jelmer M. Wolterink,et al.  Deep MR to CT Synthesis Using Unpaired Data , 2017, SASHIMI@MICCAI.

[21]  Sohil H. Patel,et al.  T2–FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project , 2017, Clinical Cancer Research.

[22]  B. Mädler,et al.  Value of quantitative magnetic resonance imaging T1-relaxometry in predicting contrast-enhancement in glioblastoma patients. , 2017, Oncotarget.

[23]  Sebastian Bickelhaupt,et al.  T1ρ-weighted Dynamic Glucose-enhanced MR Imaging in the Human Brain. , 2017, Radiology.

[24]  V. Runge.  Critical Questions Regarding Gadolinium Deposition in the Brain and Body After Injections of the Gadolinium-Based Contrast Agents, Safety, and Clinical Recommendations in Consideration of the EMA's Pharmacovigilance and Risk Assessment Committee Recommendation for Suspension of the Marketing Authori , 2017, Investigative radiology.

[25]  H. Schlemmer,et al.  Differentiation of pseudoprogression and real progression in glioblastoma using ADC parametric response maps , 2017, PloS one.

[26]  Alex Kendall,et al.  What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? , 2017, NIPS.

[27]  Su Ruan,et al.  Medical Image Synthesis with Context-Aware Generative Adversarial Networks , 2016, MICCAI.

[28]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  A. Radbruch.  Are some agents less likely to deposit gadolinium in the brain? , 2016, Magnetic resonance imaging.

[30]  Pascal J. Kieslich,et al.  Intraindividual Analysis of Signal Intensity Changes in the Dentate Nucleus After Consecutive Serial Applications of Linear and Macrocyclic Gadolinium-Based Contrast Agents , 2016, Investigative radiology.

[31]  Martin Bendszus,et al.  Virtual Raters for Reproducible and Objective Assessments in Radiology , 2016, Scientific Reports.

[32]  Klaus H. Maier-Hein,et al.  Deep MRI brain extraction: A 3D convolutional neural network for skull stripping , 2016, NeuroImage.

[33]  V. Runge.  Safety of the Gadolinium-Based Contrast Agents for Magnetic Resonance Imaging, Focusing in Part on Their Accumulation in the Brain and Especially the Dentate Nucleus , 2016, Investigative radiology.

[34]  Alexander Radbruch,et al.  High-Signal Intensity in the Dentate Nucleus and Globus Pallidus on Unenhanced T1-Weighted Images: Evaluation of the Macrocyclic Gadolinium-Based Contrast Agent Gadobutrol , 2015, Investigative radiology.

[35]  Pascal J. Kieslich,et al.  Increased Signal Intensity in the Dentate Nucleus on Unenhanced T1-Weighted Images After Gadobenate Dimeglumine Administration , 2015, Investigative radiology.

[36]  Pascal J. Kieslich,et al.  Gadolinium retention in the dentate nucleus and globus pallidus is dependent on the class of contrast agent. , 2015, Radiology.

[37]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[38]  P. Lundberg,et al.  Rapid magnetic resonance quantification on the brain: Optimization for clinical usage , 2008, Magnetic resonance in medicine.

[39]  D. Cicchetti.  Guidelines, Criteria, and Rules of Thumb for Evaluating Normed and Standardized Assessment Instruments in Psychology. , 1994 .