中国医学装备2025，Vol.22Issue(10)：15-19,5.DOI:10.3969/j.issn.1672-8270.2025.10.003
人工智能辅助压缩感知技术在头颅3D-TOF-MRA中的序列优化
Sequent optimization of AI-assisted compressive sensing techniques in brain 3D-TOF-MRA
摘要
Abstract
Objective:To explore the influence of artificial intelligence(AI)-assisted compressive sensing(ACS)technique with different acceleration factors on the image quality and scan time of three dimensional time-of-flight magnetic resonance angiography(3D-TOF-MRA)for brain.Methods:Thirty participants who underwent brain magnetic resonance imaging(MRI)at Tongzhou Branch of Beijing Friendship Hospital were recruited.All subjects underwent imaging scans about four different parameters:a non-accelerated technique(control group),ACS technique integrated with acceleration factor of 4.03(ACS4 group),ACS technique integrated with acceleration factor of 5.02(ACS5 group),and ACS technique integrated with acceleration factor of 6.06(ACS6 group).The image clarity,ranking of imaging capabilities of distal branch blood vessels and the ratio of pseudo-stenosis were qualitatively analyzed.The signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR),edge sharpness,and scan time were quantitatively analyzed.Results:There was not difference in vessel clarity among three ACS groups at the proximal and middle intracranial segments.For distal segments of blood vessel,the ACS4 group[3.0(3.0,3.0)]and ACS5 group[3.0(3.0,3.0)]were better than ACS6[2.5(2.0,3.0)](q=29.800,27.500,P<0.05).The imaging capabilities of distal-branch vessel of ACS4 group and ACS5 group were better than ACS6 group.There was no stenosis in the proximal and middle segments of the images of the three ACS group,and there were no stenosis in the images of distal vessels of ACS4 group and ACS5 group.A total of 5 cases were pseudo-stenosis in the distal vessels of ACS6 group.Compared with the control group,the incidence of pseudo-stenosis in the distal vessels of ACS6 group was 16.7%.The SNR and CNR values of quantitative analysis for proximal vessels in ACS6 group were higher than them in ACS4 group(q=27.800,26.200,P<0.05),and there was not significant difference in them among ACS4 group,ACS6 group and ACS5 group(P>0.05).The differences of SNR and CNR values in the middle and distal segments of blood vessels among different groups were not significant(P>0.05).There was not significant difference in the edge sharpness of blood vessels among ACS4 group,ACS5 group,and ACS6 group(P>0.05),while all of them were higher than those of control group,and the differences were significant(q=48.150,53.367,44.883,P<0.001).Compared with control group,the scan-time of ACS4 group was reduced by 55.19%,and that of ACS5 group was reduced by 64.07%,and that of ACS6 group was reduced by 70%.Conclusion:ACS technique can accelerate the imaging speed of brain 3D-TOF-MRA and ensure image quality.It is clinically recommended to set the ACS acceleration factor as 5.02 to undergo brain 3D-TOF-MRA scans.关键词
磁共振血管成像/时间飞跃法/压缩感知/人工智能Key words
Magnetic resonance angiography(MRA)/Time of flight(TOF)/Compressive sensing/Artificial intelligence(AI)分类
医药卫生引用本文复制引用
宁凯,徐辉,李向明,张立新,王卫丰,袁颖..人工智能辅助压缩感知技术在头颅3D-TOF-MRA中的序列优化[J].中国医学装备,2025,22(10):15-19,5.基金项目
国家自然科学基金(82371904)National Natural Science Foundation of China(82371904) （82371904）
