Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning
American Journal of Neuroradiology · 2024
DOI: 10.3174/ajnr.a8107 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Neuroradiology, 2024. Verfasst von Gowtham Murugesan und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas. Hauptthemen laut MEDLINE: Deep Learning, Brain Neoplasms. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, National Cancer Institute.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas.
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas frankf.yu@utsouthwestern.edu.
ORCID-Profile: Fang F Yu, Michael Achilleos, John DeBevits, Sahil Nalawade, Chandan Ganesh, Ben Wagner, Ananth J Madhuranthakam, Joseph A Maldjian
Förderung
- NCI NIH HHS
- National Cancer Institute
Zitieren
APA
Murugesan, G., Yu, F. F., Achilleos, M., DeBevits, J., Nalawade, S., Ganesh, C., Wagner, B., Madhuranthakam, A. J., & Maldjian, J. A. (2024). Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning. American Journal of Neuroradiology. https://doi.org/10.3174/ajnr.a8107
Vancouver
Murugesan G, Yu FF, Achilleos M, DeBevits J, Nalawade S, Ganesh C, et al. Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning. American Journal of Neuroradiology. 2024. doi:10.3174/ajnr.a8107
BibTeX
@article{Murugesan2024,
author = {Murugesan, Gowtham and Yu, Fang F and Achilleos, Michael and DeBevits, John and Nalawade, Sahil and Ganesh, Chandan and Wagner, Ben and Madhuranthakam, Ananth J and Maldjian, Joseph A},
title = {Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning},
journal = {American Journal of Neuroradiology},
year = {2024},
doi = {10.3174/ajnr.a8107}
}
EUVIMED