摘要
目的通过与常规T2加权黑血(T2-weighted dark blood,T2W-DB)序列比较,探讨应用人工智能辅助压缩感知技术的高空间分辨率T2加权黑血成像(high resolution T2 weighted dark blood based artificial intelligence assisted compressed sensing,ACS HR-T2W-DB)序列在心血管磁共振成像中评价心肌水肿的可行性。材料与方法前瞻性纳入2021年8月至12月来我院行心脏磁共振检查的患者38例。所有患者均行常规T2W-DB和ACS HR-T2W-DB心脏短轴面扫描。应用图像质量主观评分和客观定量指标分别评价常规T2W-DB和ACS HR-T2W-DB序列的图像质量。主观评分采用Likert评分量表评估总体图像质量、血池抑制效果、右心室游离壁、左心室游离壁和室间隔可视性。客观定量指标包括峰值信噪比(peak signal-to-noise ratio,pSNR)和心肌血池对比噪声比(心肌contrast-noise ratio,心肌-CNR),并对14例检出有局部心肌水肿的患者进行了心肌水肿区CNR(水肿-CNR)的评价。结果与常规T2W-DB序列相比,ACS HR-T2W-DB序列的空间分辨率提高了一倍(常规256×163 vs.ACS 336×269)。常规T2W-DB和ACS HR-T2W-DB序列图像质量主观评分中,ACS HR-T2W-DB序列右心室壁和左心室游离壁可视性的图像质量得分明显高于常规T2W-DB序列,差异有统计学意义(P均<0.05),总体图像质量、血池抑制效果和室间隔可视性在两个序列之间差异无统计学意义(P均>0.05)。图像质量客观定量评估中,基于ACS HR-T2W-DB序列pSNR和水肿-CNR均明显高于常规T2W-DB序列,差异有统计学意义(P均<0.05),心肌-CNR差异无统计学意义(P>0.05)。结论相较于常规T2W-DB序列,ACS HR-T2W-DB序列既不明显增加扫描时间,又提供了更高的空间分辨率、图像质量、水肿-CNR以及更佳的左室游离壁可视性,有望成为可疑心肌水肿患者的必备序列。
Objective:To explore the feasibility of high spatial resolution T2-weighted dark blood imaging sequence using artificial intelligence assisted compressed sensing(ACS HR-T2W-DB)technique in evaluating myocardial edema in cardiovascular magnetic resonance(CMR)imaging,compared with conventional T2W-DB sequence.Materials and Methods:A total of 38 patients who underwent cardiac magnetic resonance examination in our hospital from August to December 2021 were prospectively enrolled.All patients underwent short axial conventional T2W-DB and ACS HR-T2W-DB sequences.Subjective score and objective quantitative parameters were used to evaluate the image quality of conventional T2W-DB and ACS HR-T2W-DB sequences,respectively.Likert score scale was used to evaluate the overall image quality,blood pool inhibition effect,right ventricular free wall,left ventricular free wall and interventricular septum visibility.Objective quantitative parameters included peak signal-to-noise ratio(p SNR)and myocardial blood pool contrast-noise ratio(myocardial-CNR),and 14 patients with regional myocardial edema were evaluated by CNR(edema-CNR).Results:Compared with conventional T2W-DB sequence,the spatial resolution of ACS HR-T2W-DB sequence was doubled(conventional 256×163 vs.ACS 336×269).Compared to ACS HR-T2W-DB sequences,the image quality scores of right ventricular wall and left ventricular free wall in ACS HR-T2W-DB sequence were significantly higher than those in conventional T2W-DB sequence,and the difference was statistically significant(P<0.05),but there was no significant difference in overall image quality,blood pool suppression effect and interventricular septum visibility(P>0.05).In the objective quantitative parameters of image quality,pSNR and edema-CNR based on ACS HR-T2W-DB sequence were significantly higher than those of conventional T2W-DB sequence,and the difference was statistically significant(P<0.05),but there was no significant difference in myocardial-CNR(P>0.05).Conclusions:Compared with conventional T2W-DB sequence
作者
严祥虎
罗毅
冉玲平
张诗雨
夏黎明
黄璐
YAN Xianghu;LUO Yi;RAN Lingping;ZHANG Shiyu;XIA Liming;HUANG Lu(Department of Radiology,Tongji Hospital,Tongji Medical College,Huazhong University of Science and Technology,Wuhan 430030,China;United Imaging Healthcare,Shanghai 201800,China)
出处
《磁共振成像》
CAS
CSCD
北大核心
2022年第6期76-80,97,共6页
Chinese Journal of Magnetic Resonance Imaging
基金
国家自然科学基金面上项目(编号:81873889)
湖北省科技计划青年基金(编号:2021CFB060)。
关键词
心脏磁共振
人工智能
压缩感知
T2加权黑血
空间分辨率
水肿
cardiac magnetic resonance
artificial intelligence
compressed sensing
T2-weighted dark blood
spatial resolution
edema
