RT Journal Article
SR Electronic
T1 Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning
JF American Journal of Neuroradiology
JO Am. J. Neuroradiol.
FD American Society of Neuroradiology
SP 312
OP 319
DO 10.3174/ajnr.A8107
VO 45
IS 3
A1 Gowtham Murugesan
A1 Fang F. Yu
A1 Michael Achilleos
A1 John DeBevits
A1 Sahil Nalawade
A1 Chandan Ganesh
A1 Ben Wagner
A1 Ananth J Madhuranthakam
A1 Joseph A. Maldjian
YR 2024
UL http://www.ajnr.org/content/45/3/312.abstract
AB BACKGROUND AND PURPOSE: Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning.MATERIALS AND METHODS: We trained and validated a deep learning network by using MR images from 335 subjects in the Brain Tumor Segmentation Challenge 2019 training data set. A held out set of 125 subjects from the Brain Tumor Segmentation Challenge 2019 validation data set was used to test the generalization of the model. A residual inception DenseNet network, called T1c-ET, was developed and trained to simultaneously synthesize virtual contrast-enhanced T1-weighted (vT1c) images and segment the enhancing portions of the tumor. Three expert neuroradiologists independently scored the synthesized vT1c images by using a 3-point Likert scale, evaluating image quality and contrast enhancement against ground truth T1c images (1 = poor, 2 = good, 3 = excellent).RESULTS: The synthesized vT1c images achieved structural similarity index, peak signal-to-noise ratio, and normalized mean square error scores of 0.91, 64.35, and 0.03, respectively. There was moderate interobserver agreement between the 3 raters, regarding the algorithm’s performance in predicting contrast enhancement, with a Fleiss kappa value of 0.61. Our model was able to accurately predict contrast enhancement in 88.8% of the cases (scores of 2 to 3 on the 3-point scale).CONCLUSIONS: We developed a novel deep learning architecture to synthesize virtual postcontrast enhancement by using only conventional noncontrast brain MR images. Our results demonstrate the potential of deep learning methods to reduce the need for gadolinium contrast in the evaluation of primary brain tumors.BraTSBrain Tumor Segmentation BenchmarkETenhancing tumorGBCAgadolinium-based contrast agentMSEmean squared errorNMSEnormalized mean squared errorPSNRpeak signal-to-noise ratioRIDResidual Inception DenseNetSFLspatial frequency lossSPLstructural perception lossSSIMstructural similarity indexT2wT2-weightedvT1cvirtual contrast-enhanced T1-weightedWTwhole tumor