Impact of deep learning reconstruction in MRI on scan time and image quality of breast fat suppression sequence
Objective To investigate the impact of deep learning reconstruction(DLR)in magnetic resonance imaging(MRI)on scan time and image quality of breast T2-weighted(T2WI)fat suppression sequence.Methods Thirty female volunteers were recruited as research subjects.Breast MRI scan was performed using T2WI fat suppression sequence with an average number of acquisition(NAQ)of 1 and 2 as well as scan time of 217 s and 421 s,respectively.After scanning,Routine NAQ1 and Routine NAQ2 images were obtained.DLR was run on Routine NAQ1 image group to obtain DLR NAQ1 images.Signal-to-noise ratio(SNR)and contrast-to-noise ratio(CNR)of the images as well as the subjective and qualitative evaluation data from clinicians were analyzed and compared among three groups.Results SNR and CNR of DLR NAQ1 images of female volunteers were better than those of Routine NAQ1 and Routine NAQ2 images(P＜0.001),and the overall quality score of the images is better than that of both Route NAQ1 and Route NAQ2 images(P＜0.001).Conclusion DLR in MRI can shorten scan time of breast T2WI fat suppression sequence and improve image quality.
magnetic resonance imagingdeep learning reconstructionat suppressionaverage number of acquisitionsbreastscan efficiency
NETL
NSTL
万方数据
