EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accelerating Brain MR Imaging With Multisequence and Convolutional Neural Networks

Zhanhao Mo, He Sui, Zhongwen Lv, Xiaoqian Huang, Guobin Li, Dinggang Shen, Lin Liu, Shu Liao iD

Brain and Behavior · 2024

DOI: 10.1002/brb3.70163 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brain and Behavior, 2024. Verfasst von Zhanhao Mo und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Brain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Development Plan for Science and Technology in Jilin Province Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Magnetic resonance imaging (MRI) refers to one of the critical image modalities for diagnosis, whereas its long acquisition time limits its application. In this study, the aim was to investigate whether deep learning–based techniques are capable of using the common information in different MRI sequences to reduce the scan time of the most time‐consuming sequences while maintaining the image quality.

Method

Fully sampled T1‐FLAIR, T2‐FLAIR, and T2WI brain MRI raw data originated from 217 patients and 105 healthy subjects. The T1‐FLAIR and T2‐FLAIR sequences were subsampled using Cartesian masks based on four different acceleration factors. The fully sampled T1/T2‐FLAIR images were predicted from undersampled T1/T2‐FLAIR images and T2WI images through deep learning–based reconstruction. They were qualitatively assessed by two senior radiologists in accordance with the diagnosis decision and a four‐point scale image quality score. Furthermore, the images were quantitatively assessed based on regional signal‐to‐noise ratios (SNRs) and contrast‐to‐noise ratios (CNRs). The chi‐square test was performed, where p < 0.05 indicated a difference with statistical significance.

Results

The diagnosis decisions from two senior radiologists remained unchanged in accordance with the accelerated and fully sampled images. There were no significant differences in the regional SNRs and CNRs of most assessed regions ( p > 0.05) between the accelerated and fully sampled images. Moreover, no significant difference was identified in the image quality assessed by two senior radiologists ( p > 0.05).

Conclusion

Deep learning–based image reconstruction is capable of significantly expediting the brain MR imaging process and producing acceptable image quality without affecting diagnosis decisions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingDeep LearningBrainHumansAdultMaleFemaleMiddle AgedImage Processing, Computer-AssistedNeural Networks, ComputerAgedNeuroimagingYoung AdultSignal-To-Noise Ratio

Stichwörter der Autor:innen

accelerated imagingconvolutional neural networksdeep learningmagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, China.
  • Shanghai United Imaging Intelligence Co. Ltd., Shanghai, China.
  • Shanghai United Imaging Co. Ltd., Shanghai, China.

ORCID-Profile: Shu Liao

Förderung

  • The Development Plan for Science and Technology in Jilin Province Project

Zitieren

APA

Mo, Z., Sui, H., Lv, Z., Huang, X., Li, G., Shen, D., Liu, L., & Liao, S. (2024). Accelerating Brain MR Imaging With Multisequence and Convolutional Neural Networks. Brain and Behavior. https://doi.org/10.1002/brb3.70163

Vancouver

Mo Z, Sui H, Lv Z, Huang X, Li G, Shen D, et al. Accelerating Brain MR Imaging With Multisequence and Convolutional Neural Networks. Brain and Behavior. 2024. doi:10.1002/brb3.70163

BibTeX
@article{Mo2024,
  author = {Mo, Zhanhao and Sui, He and Lv, Zhongwen and Huang, Xiaoqian and Li, Guobin and Shen, Dinggang and Liu, Lin and Liao, Shu},
  title = {Accelerating Brain MR Imaging With Multisequence and Convolutional Neural Networks},
  journal = {Brain and Behavior},
  year = {2024},
  doi = {10.1002/brb3.70163}
}
Kostenlos starten →