摘要
目的探讨深度学习重建(deep learning reconstruction,DLR)技术在提高颞下颌关节MRI快速自旋回波-质子密度加权成像(fast-spin echo proton density weighted imaging,FSE-PD)图像质量及缩短扫描时间中的应用价值。材料与方法招募40名健康志愿者,进行颞下颌关节MRI扫描,对每名健康志愿者行颞下颌关节MRI常规FSE-PD扫描和DLR加速FSE-PD扫描,并保存未施加DLR的加速FSE-PD原始图像。两名放射科医师分别对3组FSE-PD图像质量进行定性、定量评价。定性评价使用Likert量表(5分法)对图像解剖结构清晰度及整体图像质量进行主观评分。定量评价采用信噪比(signal-to-noise ratio,SNR)和对比噪声比(contrast-to-noise ratio,CNR)对图像质量进行客观评价。采用单因素方差分析和Kruskal-Wallis检验比较三组图像主观评分和客观指标的差异。采用组内相关系数(intra-class correlation coefficient,ICC)评估两名放射科医师主观评分的一致性。结果与常规FSE-PD组相比,DLR快速FSE-PD组扫描时间缩短了67%。两名放射科医师对图像解剖结构清晰度及整体图像质量主观评分的一致性较好(ICC分别为0.80、0.78),常规FSE-PD组、快速FSE-PD组和DLR快速FSE-PD组的图像解剖结构清晰度及整体图像质量评分差异均有统计学意义(P<0.05);三组FSE-PD图像间的SNR、CNR差异有统计学意义(P<0.05);DLR快速FSE-PD组的定性及定量评价结果均显著优于常规FSE-PD组。结论DLR技术可以缩短颞下颌关节MRI常规FSE-PD序列检查的扫描时间,提高图像质量,有助于患者更快地完成检查。
Objective:To explore the application value of deep learning reconstruction(DLR)technology in enhancing the image quality and reducing the scan time of fast-spin echo proton density weighted imaging(FSE-PD)in MRI of the temporomandibular joint(TMJ).Materials and Methods:Recruit 40 healthy volunteers and undergo MRI scans of the TMJ.Each healthy volunteer underwent conventional FSE-PD MRI scans and accelerated FSE-PD scans using DLR,the original accelerated FSE-PD images without DLR were simultaneously preserved.Two radiologists qualitatively and quantitatively evaluated the image quality of the three FSE-PD image sets,individually.Qualitative assessments utilized a Likert scale(5-point)for subjective scoring of anatomical structure clarity and overall image quality.Quantitative assessments utilized signal-to-noise ratio(SNR)and contrast-to-noise ratio(CNR)for objective evaluation of image quality.One-way ANOVA and Kruskal-Wallis test were used to compare the differences in subjective scores and objective indicators among the three groups.The intra-class correlation coefficient(ICC)was used to evaluate the consistency of the subjective scores of the two radiologists.Results:Compared to the conventional FSE-PD group,the DLR-accelerated FSE-PD group demonstrated a 67%reduction in scan time.The two radiologists exhibited good consistency in subjective scores for anatomical structure clarity and overall image quality(ICC of 0.80 and 0.78,respectively).There were significant differences in anatomical clarity and overall image quality scores among the conventional FSE-PD group,accelerated FSE-PD group,and DLR-accelerated FSE-PD group(P<0.05).The differences in SNR and CNR among the three FSE-PD groups were statistically significant(P<0.05).Qualitative and quantitative evaluation results for the DLR-accelerated FSE-PD group were both significantly superior to the conventional FSE-PD group.Conclusions:DLR technology could shorten the scanning time of conventional FSE-PD MRI of the TMJ,enhance image quality,and help patient
作者
王春杰
单艺
张越
武春雪
刘灿
王静娟
吴涛
葛献鹏
卢洁
WANG Chunjie;SHAN Yi;ZHANG Yue;WU Chunxue;LIU Can;WANG Jingjuan;WU Tao;GE Xianpeng;LU Jie(Department of Radiology and Nuclear Medicine,Xuanwu Hospital,Capital Medical University,Beijing 100053,China;Beijing Key Laboratory of MRI and Brain Informatics,Beijing 100053,China;Clinical Marking Department of MR,General Electric Medical(China)Co.,Ltd.,Beijing 100176,China;Department of Stomatology,Xuanwu Hospital,Capital Medical University,Beijing 100053,China)
出处
《磁共振成像》
CAS
CSCD
北大核心
2024年第10期3-7,21,共6页
Chinese Journal of Magnetic Resonance Imaging
基金
宣武医院汇智人才工程-支持计划-领军人才项目(编号:HZ2021ZCLJ005)。
关键词
颞下颌关节
深度学习
图像重建
磁共振成像
图像质量
temporomandibular joint
deep learning
image reconstruction
magnetic resonance imaging
image quality
