分享:
分享到微信朋友圈
X
技术研究
人工智能辅助压缩感知与并行采集技术在肩关节MRI中的对比研究
杨泽铖 詹艺 施楠楠 商爱 单飞 沈杰

Cite this article as: YANG Z C, ZHAN Y, SHI N N, et al. Comparative use of artificial intelligence-assisted compressed sensing and parallel imaging for shoulder magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2024, 15(8): 166-171.本文引用格式:杨泽铖, 詹艺, 施楠楠, 等. 人工智能辅助压缩感知与并行采集技术在肩关节MRI中的对比研究[J]. 磁共振成像, 2024, 15(8): 166-171. DOI:10.12015/issn.1674-8034.2024.08.025.


[摘要] 目的 通过与并行采集(parallel imaging, PI)对比,探讨人工智能辅助压缩感知(artificial intelligence-assisted compressed sensing, ACS)技术对肩关节MRI扫描时间和图像质量的影响,并优化扫描方案。材料与方法 前瞻性纳入2023年11月至2024年2月在我院行肩关节MRI检查的70例患者,扫描序列采用快速自旋回波序列包括斜冠状位T1加权成像(oblique coronal T1-weighted, OCor T1WI)、斜冠状位T2加权频率选择脂肪抑制成像(oblique coronal T2-weighted with fat saturation, OCor T2WI-fs)、斜矢状位质子密度(proton density, PD)加权频率选择脂肪抑制成像(oblique sagittal PD-weighted with fat saturation, OSag PDWI-fs)、横断面PD加权频率选择脂肪抑制成像(transverse PD-weighted with fat saturation, Tra PDWI-fs),分别采用ACS和PI两种加速采集技术。比较两种技术的扫描时间。测量冈上肌肌腹和肱骨头的信号强度及背景标准差,并计算信噪比(signal-to-noise ratio, SNR)。采用李克特量表对图像质量进行评分。结果 相较于PI,采用ACS缩短了33.5%的扫描时间。采用ACS采集的图像伪影更少,骨骼肌肉的噪声更小,在图像质量主观评分上均高于采用PI的图像,差异均有统计学意义(P均<0.05)。OCor T1WI、OCor T2WI-fs和Tra PDWI-fs序列中采用ACS的图像在冈上肌和肱骨头的SNR均高于采用PI的图像,差异均有统计学意义(P均<0.001)。OSag PDWI-fs序列中图像冈上肌的SNR采用ACS与PI差异无统计学意义(P>0.05),图像肱骨头的SNR采用ACS采集的图像高于PI的图像,差异有统计学意义(P均<0.001)。结论 与传统的PI相比,采用ACS在肩关节MRI中可实现更高效且稳定的快速成像方案,提高图像质量,缩短扫描时间,提高患者耐受程度,具有较好的临床应用价值。
[Abstract] Objective By comparing with parallel imaging (PI), to explore the impact of artificial intelligence-assisted compressed sensing (ACS) technology on the scanning time and image quality of shoulder joint MRI, and optimizes the scanning scheme.Materials and Methods A total of 70 patients who underwent shoulder MRI in our hospital from November 2023 to February 2024 were prospectively enrolled. The scanning sequences used fast spin echo including oblique coronal T1-weighted (OCor T1WI), oblique coronal T2-weighted with fat saturation (OCor T2WI-fs), oblique sagittal proton density (PD)-weighted with fat saturation (OSag PDWI-fs), and transverse PD-weighted with fat saturation (Tra PDWI-fs), respectively, using two accelerated acquisition technologies: ACS and PI. Compare the scanning time of two technologies. Measure the signal intensity and background standard deviation of the supraspinatus muscle and humeral head, and calculate the signal-to-noise ratio (SNR). Use the Likert scale to rate image quality.Results Compared to PI, using ACS reduced scanning time by 33.5%. The images obtained using ACS have few artifacts and low noise. The subjective image quality scores are higher than those obtained using PI, and the differences are statistically significant (all P<0.05). The SNR of images using ACS in OCor T1WI, OCor T2WI-fs, and Tra PDWI-fs sequences were higher than those using PI in the supraspinatus muscle and humeral head, and the differences were statistically significant (all P<0.001). The SNR of the supraspinatus muscle in the OSag PDWI-fs sequence using ACS was not significantly different from that of PI (P>0.05), while the SNR of the humeral head in the images obtained using ACS was higher than that of PI, and the difference was statistically significant (all P<0.001).Conclusions Compared with PI, using ACS in shoulder MRI can achieve a more efficient and stable rapid imaging, improve image quality, shorten scanning time, and increase patient tolerance, which has clinical application value.
[关键词] 人工智能;压缩感知;并行成像;磁共振成像;肩关节
[Keywords] artificial intelligence;compressed sensing;parallel imaging;magnetic resonance imaging;shoulder

杨泽铖    詹艺    施楠楠    商爱    单飞    沈杰 *  

上海市(复旦大学附属)公共卫生临床中心放射科,上海 201508

通信作者:沈杰,E-mail:shenjie@shphc.org.cn

作者贡献声明:沈杰、单飞设计本研究的方案,对稿件重要内容进行了修改;杨泽铖起草和撰写稿件,解释本研究的数据;詹艺、施楠楠、商爱获取、分析本研究的数据,对稿件重要内容进行了修改;杨泽铖获得了上海市公共卫生临床中心院内课题基金项目资助。全体作者都同意发表最后的修改稿,同意对本研究的所有方面负责,确保本研究的准确性和诚信。


基金项目: 上海市公共卫生临床中心院内课题 KY-GW-2024-28
收稿日期:2024-04-26
接受日期:2024-08-12
中图分类号:R445.2  R681.7 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2024.08.025
本文引用格式:杨泽铖, 詹艺, 施楠楠, 等. 人工智能辅助压缩感知与并行采集技术在肩关节MRI中的对比研究[J]. 磁共振成像, 2024, 15(8): 166-171. DOI:10.12015/issn.1674-8034.2024.08.025.

0 引言

       随着人口老龄化进程加快、生活环境的改变以及手持智能设备的普及等因素,患有肩关节疼痛及功能障碍的人群日益增多[1, 2, 3]。MRI凭借无电离辐射、多参数成像、软组织分辨力高等优势在肩关节病变的影像学诊断中发挥着重要的临床价值[4, 5, 6]。MRI受限于扫描时间长,对于肩部不适的患者难以保持长时间的固定姿势,易产生运动伪影[7, 8, 9]。因此在保证图像质量的前提下,尽可能地缩短检查时间具有一定的临床意义。目前临床上广泛应用的加速采集技术主要有半傅里叶(half-fourier, HF)、并行采集(parallel imaging, PI)和压缩感知(compressed sensing, CS)三大类技术,但传统的加速采集技术在缩短扫描时间的同时,降低了图像质量,增加了重建伪影[10]。近年来,随着人工智能相关技术的不断发展,催生了一种新型的MRI加速采集技术——人工智能辅助压缩感知(artificial intelligence-assisted compressed sensing, ACS),该技术是在HF、PI和CS三种技术结合的基础上融入人工智能,提供了一种更高效且稳定的快速成像方案,能够在保证图像质量的基础上显著缩短扫描时间[11, 12, 13]。然而,目前国内外仅有ACS应用于肩关节MRI横断面的报道[14],尚缺乏ACS应用于肩关节MRI不同权重不同切面序列中的研究。因此,本研究将采用ACS和PI两种加速采集技术在肩关节MRI不同序列中进行对比,旨在探讨ACS技术在肩关节MRI中缩短检查时间和提高图像质量等方面的临床应用价值,希望为临床提供一种更快速且实用的肩关节MRI扫描方案,助力于提高患者耐受程度,减少运动伪影,促进工作效率。

1 材料与方法

1.1 研究对象

       前瞻性纳入2023年11月至2024年2月于上海市公共卫生临床中心行肩关节MRI检查的患者。纳入标准:(1)年龄18~80岁;(2)无肩部手术史。排除标准:(1)MRI检查禁忌证;(2)无法完成全部检查序列或图像质量不佳者。最终共纳入患者70例,男33例,女37例,年龄24~78(52.47±11.77)岁。本研究遵守《赫尔辛基宣言》,经上海市公共卫生临床中心伦理委员会批准,批准文号:2024-S027-02,全体受试者均签署了知情同意书。

1.2 仪器与方法

       本研究采用3.0 T超导磁共振(uMR 870,上海联影医疗科技有限公司,中国),使用12通道超柔线圈。取仰卧位,头先进,被检侧肩部尽可能靠近床中心,被检侧手臂自然伸直放于身旁且掌心向上,附加沙袋固定。扫描序列采用快速自旋回波序列包括斜冠状位T1加权成像(oblique coronal T1-weighted, OCor T1WI)、斜冠状位T2加权频率选择脂肪抑制成像(oblique coronal T2-weighted with fat saturation, OCor T2WI-fs)、斜矢状位质子密度(proton density, PD)加权频率选择脂肪抑制成像(oblique sagittal PD-weighted with fat saturation, OSag PDWI-fs)、横断面PD加权频率选择脂肪抑制成像(transverse PD-weighted with fat saturation, Tra PDWI-fs),分别采用ACS和PI两种加速采集技术,设置ACS的加速因子为3.0,PI的加速因子为2.0。具体扫描参数见表1

表1  肩关节MRI扫描参数
Tab. 1  Shoulder joint MRI scanning parameters

1.3 图像分析

1.3.1 图像质量主观评价

       由一名具有6年诊断经验的主治医师(观察者1)以及一名具有8年诊断经验的主治医师(观察者2)采用双盲法对各个序列的图像质量进行主观评分。采用李克特量表(Likert scale)评分:5分为图像质量优秀,组织结构显示清晰,噪声小,基本无伪影,完全能满足诊断;4分为图像质量良好,组织结构显示较清晰,噪声较小,无明显伪影,能满足诊断;3分为图像质量中等,组织结构显示稍差,噪声稍大,伪影较轻,能用于诊断;2分为图像质量较差,组织结构显示不清,噪声较大,伪影较重,不能满足诊断;1分为图像质量差,组织结构显示模糊,噪声大,伪影重,完全不能用于诊断。

1.3.2 图像质量客观评价

       所有图像均归档至联影工作站进行分析。由一名具有8年诊断经验的主治医师选取冈上肌肌腹、肱骨头和图像背景区域勾画感兴趣区,感兴趣区大小约为200 mm2,勾画时避开伪影和病变区,测量冈上肌肌腹和肱骨头信号强度(signal intensity, SI)及背景标准差(standard deviation, SD),且连续测量3次取平均值,见图1。计算信噪比(signal-to-noise ratio, SNR),见式(1)~(2[15]

图1  感兴趣区示意图。1A~1D分别为冈上肌肌腹在OCor T1WI、OCor T2WI-fs、OSag PDWI-fs、Tra PDWI-fs图像上的感兴趣区位置;1E~1H分别为肱骨头在OCor T1WI、OCor T2WI-fs、OSag PDWI-fs、Tra PDWI-fs图像上的感兴趣区位置;1I~1L分别为图像背景在OCor T1WI、OCor T2WI-fs、OSag PDWI-fs、Tra PDWI-fs图像上的感兴趣区位置。OCor T1WI:斜冠状位T1加权序列;OCor T2WI-fs:斜冠状位T2加权压脂序列;Osag PDWI-fs:斜矢状位PD加权压脂序列;Tra PDWI-fs:横断面PD加权压脂序列;PD:质子密度。
Fig. 1  The picture shows a schematic diagram of region of interest. 1A-1D represent the location of supraspinatus muscle on OCor T1WI, OCor T2WI-fs, OSag PDWI-fs, Tra PDWI-fs. 1E-1H represent the location of humeral head on OCor T1WI, OCor T2WI-fs, OSag PDWI-fs, Tra PDWI-fs. 1I-1L represent the location of background on OCor T1WI, OCor T2WI-fs, OSag PDWI-fs, Tra PDWI-fs. OCor T1WI: oblique coronal T1-weighted; OCor T2WI-fs: oblique coronal T2-weighted with fat saturation; Osag PDWI-fs: oblique sagittal PD-weighted with fat saturation; Tra PDWI-fs: transverse PD-weighted with fat saturation; PD: proton density.

1.4 统计学分析

       采用SPSS 22.0软件,图像质量客观评价数据以x¯±s表示,采用配对样本t检验。图像质量主观评分采用中位数(上下四分位数)表示,采用配对样本Wilcoxon检验。两位观察者对图像质量主观评分的一致性采用Kappa检验。Kappa值>0.80提示一致性极好;0.6<Kappa值≤0.8提示一致性较好;0.4<Kappa值≤0.6提示一致性一般;Kappa值≤0.40提示一致性较差。P<0.05为差异有统计学意义。

2 结果

2.1 一般资料

       本研究共纳入患者70例,男33例,女37例,年龄24~78(52.47±11.77)岁,左肩31例,右肩39例。其中临床诊断为肩关节疼痛者49例,肩周炎者12例,肩关节脱位者4例,健康查体者5例。MRI影像学诊断为肩关节退变者38例,肩袖损伤者49例,关节腔积液者53例,肱骨骨髓水肿者8例,肱骨骨折者1例。

2.2 成像时间比较

       采用PI加速采集技术的OCor T1WI、OCor T2WI-fs、OSag PDWI-fs、Tra PDWI-fs四组图像成像时间分别为80、142、142、120 s;采用ACS加速采集技术的四组图像成像时间分别为57、89、94、82 s。采用PI总扫描时间为484 s;采用ACS总扫描时间为322 s。采用ACS相较于PI缩短了33.5%的扫描时间。

2.3 各个序列图像质量主观评价一致性分析与比较

       两位观察者对图像质量的主观评分一致性较好,Kappa值范围为0.603~0.717,见表2。所有图像质量主观评分均≥4分,提示图像质量均能满足诊断,见图2。OCor T1WI、OCor T2WI-fs、OSag PDWI-fs和Tra PDWI-fs序列中采用ACS的图像在主观评分上均高于采用PI的图像,差异均有统计学意义(均P<0.05),见表3

图2  女,52岁,右肩关节退变,右侧冈上肌肌腱损伤。2A:OCor T1WI图像,采用PI;2B:OCor T2WI-fs图像,采用PI;2C:OSag PDWI-fs图像,采用PI;2D:Tra PDWI-fs图像,采用PI;2E:OCor T1WI图像,采用ACS;2F:OCor T2WI-fs图像,采用ACS;2G:OSag PDWI-fs图像,采用ACS;2H:Tra PDWI-fs图像,采用ACS。OCor T1WI:斜冠状位T1加权序列;OCor T2WI-fs:斜冠状位T2加权压脂序列;Osag PDWI-fs:斜矢状位PD加权压脂序列;Tra PDWI-fs:横断面PD加权压脂序列;PI:并行采集;ACS:人工智能辅助压缩感知;PD:质子密度。
Fig. 2  Female, 52 years old, right shoulder joint degeneration, right supraspinatus tendon injury. 2A: OCor T1WI image with PI; 2B: OCor T2WI-fs image with PI; 2C: OSag PDWI-fs image with PI; 2D: Tra PDWI-fs image with PI; 2E: OCor T1WI image with ACS; 2F: OCor T2WI-fs image with ACS; 2G: OSag PDWI-fs image with ACS; 2H: Tra PDWI-fs image with ACS. OCor T1WI: oblique coronal T1-weighted; OCor T2WI-fs: oblique coronal T2-weighted with fat saturation; Osag PDWI-fs: oblique sagittal PD-weighted with fat saturation; Tra PDWI-fs: transverse PD-weighted with fat saturation; PI: parallel imaging; ACS: artificial intelligence-assisted compressed sensing; PD: proton density.
表2  两位观察者对肩关节MRI各个序列图像质量主观评价一致性分析
Tab. 2  Consistency analysis of subjective evaluation of image quality in different sequences of shoulder joint MRI by two observers
表3  肩关节MRI各个序列图像质量主观评价的比较
Tab. 3  Comparison of subjective evaluation of image quality in various sequences of shoulder joint MRI

2.4 各个序列图像质量客观评价的比较

       OCor T1WI、OCor T2WI-fs和Tra PDWI-fs序列中采用ACS的图像在SNR冈上肌和SNR肱骨头均高于采用PI的图像,差异均有统计学意义(P均<0.001)。OSag PDWI-fs序列中图像的SNR冈上肌采用ACS与PI差异无统计学意义(P>0.05),图像的SNR肱骨头采用ACS采集的图像高于PI的图像,差异有统计学意义(P均<0.001),见表4

表4  肩关节MRI各个序列图像质量客观评价的比较
Tab. 4  Comparison of objective evaluation of image quality in various MRI sequences of shoulder joint

3 讨论

       本研究通过比较分别采用ACS和PI两种加速采集技术的四组肩关节MRI常规扫描序列,结果提示采用ACS加速的四组序列比采用PI总体缩短了约33.5%的扫描时间。研究结果显示在OCor T1WI、OCor T2WI-fs和Tra PDWI-fs序列中采用ACS可以提高冈上肌和肱骨头的SNR,提升图像密度分辨力,有助于提高诊断效能。目前尚未发现将ACS技术应用于四组肩关节MRI常规扫描序列的研究,故缩短肩关节MRI扫描时间能提高患者对检查的耐受性,减缓患者的不适感,促进设备的利用效率,具有较好的临床应用前景。

3.1 加速采集技术在肩关节MRI中的优势及局限性

       肩关节是人体中最灵活的关节之一,也是容易发生肌肉骨骼疼痛的关节,肩关节疼痛通常会影响日常工作的进行,导致生活质量下降[16, 17]。MRI凭借其良好的软组织对比度和空间分辨力,被认为是诊断肩关节周围炎、肩峰下滑囊炎、肩袖损伤等病变最有效的非侵入性诊断方式之一[18, 19]。然而,肩关节MRI在肩部疼痛的患者中往往具有一定的挑战性,常规的MRI协议由于扫描时间较长,患者可能因肩部不适而引起运动伪影,从而导致图像质量下降,重复扫描增加时间成本[20, 21]

       MRI数据是在K空间(频率域)中采集的,可以通过快速傅里叶逆变换转换到空间域,从而生成能供临床诊断的MRI图像。快速MRI通过采样比奈奎斯特标准更少的K空间线来加速数据采集,但是会导致重建图像中的噪声和混叠伪影增加[22, 23]。传统的快速MRI技术PI利用相控阵线圈中单个接收线圈的空间敏感度差异来编码空间信息,降低成像所必需的梯度编码步数,从而缩短扫描时间,但可能会导致图像产生重建伪影及卷褶伪影等问题,同时受限于随着加速因子的增大,图像的SNR会逐步降低[24, 25]。OBAMA等[11]比较了PI和CS在肩关节MRI中的图像质量影响,结果提示传统的PI技术在肩关节MRI中会降低冈上肌和肱骨头的SNR,与本研究结果相似。DRATSCH等[19]研究结果提示CS技术随着加速因子的增大,图像SNR和对比噪声比逐步降低,导致组织结构与解剖细节显示不清,但是结合了人工智能的CS可以提供更优质且稳定的图像质量。

3.2 基于ACS技术的肩关节MRI的临床应用价值

       ACS是在HF、PI和CS三种技术结合的基础上融入人工智能,既能够有效缩短扫描时间,又可以保证不损失图像的SNR,是一种更为高效且稳定的快速成像方案[26, 27, 28]。ZHAO等[29]将ACS技术应用于踝关节MRI研究中发现,ACS与PI相比缩短了43%的扫描时间,同时保证了图像质量。本研究采用ACS这一创新性的快速成像技术,应用于肩关节MRI来优化扫描协议,结果提示相较于PI,ACS应用于肩关节MRI可缩短约33.5%的扫描时间。陈兴艳等[14]研究指出ACS应用于肩关节Tra PDWI-fs序列中,可缩短约39.5%的扫描时间,但该研究中两组间的重复时间,回波链长度,激励次数均不一致。本研究在仅改变加速采集技术,余参数保持一致的前提下,进一步探讨了ACS在四组不同权重不同切面肩关节MRI常规扫描序列中的临床应用价值。本研究结果显示ACS应用于OCor T1WI、OCor T2WI-fs和Tra PDWI-fs三组序列中均可提高冈上肌和肱骨头的SNR,且拥有更高的主观质量评分。ACS应用于OSag PDWI-fs序列中,可以提高肱骨头的SNR,但是对冈上肌的SNR不产生影响。ACS受采集和重建策略的影响,HF、PI和CS数学模型的约束以及正则化参数的选择,会对图像质量产生影响,但总体图像质量能满足临床诊断[30, 31]。本研究还发现采用ACS的序列相比于PI,其图像整体的伪影更少,骨骼肌肉的噪声更小,这一结论与既往研究相符[32]。这可能是由于ACS依靠人工智能模块重建能够抑制图像噪声和混叠伪影,并结合HF、PI和CS三种快速采集技术,从而提供更高的加速水平,ACS能够在成像速度和图像质量之间建立良好的平衡关系[33, 34, 35]

3.3 局限性

       本研究的局限性在于:(1)样本量较少,可能存在选择性偏倚;(2)未探讨ACS中不同加速因子可能对图像质量产生的影响;(3)未探讨ACS对肩关节病变诊断可能存在的潜在影响。在后续的研究中,将进一步扩大样本量,结合临床病症分级探讨,将不同加速因子下的ACS技术纳入对比研究,并探讨ACS技术在肩关节3D序列中的应用潜力。

4 结论

       综上所述,ACS技术应用于肩关节MRI不同方位、不同权重的序列中,相比于传统的PI均可实现更高效且稳定的快速成像方案,在提高或不降低图像SNR的条件下,进一步缩短扫描时间,有助于提高患者对MRI检查的耐受程度,有利于促进放射科的工作效率,ACS快速成像技术具有较好的临床应用价值。

[1]
世界中医药学会联合会骨质疏松专业委员会, 上海中医药大学附属龙华医院, 中日友好医院, 等. 肩周炎中西医结合诊疗专家共识[J]. 世界中医药, 2023, 18(7): 911-917. DOI: 10.3969/j.issn.1673-7202.2023.07.004.
Osteoporosis Committee of World Federation of Chinese Medicine Societies, Longhua Hospital Affiliated to Shanghai University of Chinese Medicine, China-Japan Friendship Hospital, et al. Expert consensus on the diagnosis and treatment of periarthritis of the shoulder with integrated traditional Chinese and western medicine[J]. World Chin Med, 2023, 18(7): 911-917. DOI: 10.3969/j.issn.1673-7202.2023.07.004.
[2]
HERRMANN J, FENG Y S, GASSENMAIER S, et al. Fast 5-minute shoulder MRI protocol with accelerated TSE-sequences and deep learning image reconstruction for the assessment of shoulder pain at 1.5 and 3 Tesla[J/OL]. Eur J Radiol Open, 2024, 12: 100557 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/38495213/. DOI: 10.1016/j.ejro.2024.100557.
[3]
GOWDA C S, MIRZA K, GALAGALI D A. Rotator cuff tears: correlation between clinical examination, magnetic resonance imaging and arthroscopy[J/OL]. Cureus, 2024, 16(3): e56065 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/38618461/. DOI: 10.7759/cureus.56065.
[4]
WU H X, ZUO Z J, LI Y C, et al. Anatomic characteristics of shoulder based on MRI accurately predict incomplete rotator cuff injuries in patients: relevance for predictive, preventive, and personalized healthcare strategies[J]. EPMA J, 2023, 14(3): 553-570. DOI: 10.1007/s13167-023-00333-5.
[5]
FEUERRIEGEL G C, WEISS K, VAN A T, et al. Deep-learning-based image quality enhancement of CT-like MR imaging in patients with suspected traumatic shoulder injury[J/OL]. Eur J Radiol, 2024, 170: 111246 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/38056345/. DOI: 10.1016/j.ejrad.2023.111246.
[6]
SNEAG D B, ABEL F, POTTER H G, et al. MRI advancements in musculoskeletal clinical and research practice[J/OL]. Radiology, 2023, 308(2): e230531 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37581501/. DOI: 10.1148/radiol.230531.
[7]
李智慧, 陆勇. 肩袖损伤的磁共振表现与诊断[J]. 中国临床医生杂志, 2023, 51(5): 522-524. DOI: 10.3969/j.issn.2095-8552.2023.05.004.
LI Z H, LU Y. Magnetic resonance imaging and diagnosis of rotator cuff injury[J]. Chin J Clin, 2023, 51(5): 522-524. DOI: 10.3969/j.issn.2095-8552.2023.05.004.
[8]
ALAIA E F, SUBHAS N. Shoulder MR imaging and MR arthrography techniques: new advances[J]. Magn Reson Imaging Clin N Am, 2020, 28(2): 153-163. DOI: 10.1016/j.mric.2019.12.001.
[9]
曹家骏, 刘娜, 钟美梦, 等. 人工智能-压缩感知技术在颅脑3D T2-FLAIR序列采集及脑白质高信号评价中的应用[J]. 磁共振成像, 2024, 15(2): 135-139, 146. DOI: 10.12015/issn.1674-8034.2024.02.020.
CAO J J, LIU N, ZHONG M M, et al. Application of artificial intelligence-assisted compressed sensing technology in brain 3D T2-FLAIR sequence acquisition and evaluation of white matter hyperintensity[J]. Chin J Magn Reson Imag, 2024, 15(2): 135-139, 146. DOI: 10.12015/issn.1674-8034.2024.02.020.
[10]
KANIEWSKA M, DEININGER-CZERMAK E, GETZMANN J M, et al. Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time[J]. Eur Radiol, 2023, 33(3): 1513-1525. DOI: 10.1007/s00330-022-09151-1.
[11]
OBAMA Y, OHNO Y, YAMAMOTO K, et al. MR imaging for shoulder diseases: effect of compressed sensing and deep learning reconstruction on examination time and imaging quality compared with that of parallel imaging[J/OL]. Magn Reson Imaging, 2022, 94: 56-63 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/35934207/. DOI: 10.1016/j.mri.2022.08.004.
[12]
LIU H B, DENG D L, ZENG W L, et al. AI-assisted compressed sensing and parallel imaging sequences for MRI of patients with nasopharyngeal carcinoma: comparison of their capabilities in terms of examination time and image quality[J]. Eur Radiol, 2023, 33(11): 7686-7696. DOI: 10.1007/s00330-023-09742-6.
[13]
SUI H, GONG Y, LIU L, et al. Comparison of artificial intelligence-assisted compressed sensing (ACS) and routine two-dimensional sequences on lumbar spine imaging[J/OL]. J Pain Res, 2023, 16: 257-267 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/36744117/. DOI: 10.2147/JPR.S388219.
[14]
陈兴艳, 查福祥, 秦秀凤, 等. ACS技术在肩关节磁共振轴位上的可行性研究[J]. 放射学实践, 2023, 38(11): 1458-1461. DOI: 10.13609/j.cnki.1000-0313.2023.11.016.
CHEN X Y, ZHA F X, QIN X F, et al. Feasibility study of ACS technique in axial magnetic resonance imaging of shoulder joint[J]. Radiol Pract, 2023, 38(11): 1458-1461. DOI: 10.13609/j.cnki.1000-0313.2023.11.016.
[15]
LIU J, LI W, LI Z Y, et al. Magnetic resonance shoulder imaging using deep learning-based algorithm[J]. Eur Radiol, 2023, 33(7): 4864-4874. DOI: 10.1007/s00330-023-09470-x.
[16]
LUIME J J, KOES B W, HENDRIKSEN I J, et al. Prevalence and incidence of shoulder pain in the general population; a systematic review[J]. Scand J Rheumatol, 2004, 33(2): 73-81. DOI: 10.1080/03009740310004667.
[17]
FEUERRIEGEL G C, WEISS K, KRONTHALER S, et al. Evaluation of a deep learning-based reconstruction method for denoising and image enhancement of shoulder MRI in patients with shoulder pain[J]. Eur Radiol, 2023, 33(7): 4875-4884. DOI: 10.1007/s00330-023-09472-9.
[18]
GOES P C K, PATHRIA M N. Radiographic/MR imaging correlation of the shoulder[J]. Magn Reson Imaging Clin N Am, 2019, 27(4): 575-585. DOI: 10.1016/j.mric.2019.07.005.
[19]
DRATSCH T, SIEDEK F, ZÄSKE C, et al. Reconstruction of shoulder MRI using deep learning and compressed sensing: a validation study on healthy volunteers[J/OL]. Eur Radiol Exp, 2023, 7(1): 66 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37880546/. DOI: 10.1186/s41747-023-00377-2.
[20]
KOHLI A, PILKINTON D T, XI Y, et al. Image quality improvement and motion degradation reduction in shoulder MR imaging: comparison of BLADE and rectilinear techniques at 3-Tesla scanning[J]. Skeletal Radiol, 2022, 51(12): 2291-2297. DOI: 10.1007/s00256-022-04085-7.
[21]
SHIRAISHI K, NAKAURA T, UETANI H, et al. Combination use of compressed sensing and deep learning for shoulder magnetic resonance imaging with various sequences[J]. J Comput Assist Tomogr, 2023, 47(2): 277-283. DOI: 10.1097/RCT.0000000000001418.
[22]
LIAO S, MO Z H, ZENG M S, et al. Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction[J/OL]. Cell Rep Med, 2023, 4(7): 101119 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37467726/. DOI: 10.1016/j.xcrm.2023.101119.
[23]
YOON M A, GOLD G E, CHAUDHARI A S. Accelerated musculoskeletal magnetic resonance imaging[J/OL]. J Magn Reson Imaging, 2023 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/38156716/. DOI: 10.1002/jmri.29205.
[24]
袁畅, 张煜堃, 曹家骏, 等. 头颈联合3D-TOF-MRA人工智能辅助压缩感知序列的优化[J]. 磁共振成像, 2024, 15(4): 139-144, 152. DOI: 10.12015/issn.1674-8034.2024.04.022.
YUAN C, ZHANG Y K, CAO J J, et al. Optimization of artificial intelligence-assisted compressed sensing sequences for cerebral and carotid 3D-TOF-MRA[J]. Chin J Magn Reson Imag, 2024, 15(4): 139-144, 152. DOI: 10.12015/issn.1674-8034.2024.04.022.
[25]
SINGH D, MONGA A, DE MOURA H L, et al. Emerging trends in fast MRI using deep-learning reconstruction on undersampled k-space data: a systematic review[J/OL]. Bioengineering, 2023, 10(9): 1012 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37760114/. DOI: 10.3390/bioengineering10091012.
[26]
WANG S S, CAO G H, WANG Y, et al. Review and prospect: artificial intelligence in advanced medical imaging[J/OL]. Front Radiol, 2021, 1: 781868 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37492170/. DOI: 10.3389/fradi.2021.781868.
[27]
潘珂, 刘倩倩, 唐玲玲, 等. 人工智能-压缩感知与压缩感知在膝关节MRI中的加速效率及图像质量评价研究[J]. 磁共振成像, 2022, 13(5): 94-98. DOI: 10.12015/issn.1674-8034.2022.05.017.
PAN K, LIU Q Q, TANG L L, et al. Study on acceleration efficiency and image quality of artificial intelligence compressed sensing and compressed sensing in knee MRI[J]. Chin J Magn Reson Imag, 2022, 13(5): 94-98. DOI: 10.12015/issn.1674-8034.2022.05.017.
[28]
NI M, HE M, YANG Y X, et al. Application research of AI-assisted compressed sensing technology in MRI scanning of the knee joint: 3D-MRI perspective[J]. Eur Radiol, 2024, 34(5): 3046-3058. DOI: 10.1007/s00330-023-10368-x.
[29]
ZHAO Q, XU J J, YANG Y X, et al. AI-assisted accelerated MRI of the ankle: clinical practice assessment[J/OL]. Eur Radiol Exp, 2023, 7(1): 62 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/37857868/. DOI: 10.1186/s41747-023-00374-5.
[30]
钟美梦, 曹家骏, 安琪, 等. 人工智能辅助压缩感知技术对颅脑磁敏感加权成像图像质量及核团相位值的影响[J]. 磁共振成像, 2023, 14(12): 91-97. DOI: 10.12015/issn.1674-8034.2023.12.015.
ZHONG M M, CAO J J, AN Q, et al. Impact of AI-assisted compressed sensing on quality and phase value of nuclei of brain susceptibility weighted imaging[J]. Chin J Magn Reson Imag, 2023, 14(12): 91-97. DOI: 10.12015/issn.1674-8034.2023.12.015.
[31]
李烁, 王效春. 压缩感知磁共振成像技术的临床应用进展[J]. 磁共振成像, 2023, 14(12): 198-202. DOI: 10.12015/issn.1674-8034.2023.12.036.
LI S, WANG X C. Clinical advancements in the application of compressed sensing techniques in magnetic resonance imaging[J]. Chin J Magn Reson Imag, 2023, 14(12): 198-202. DOI: 10.12015/issn.1674-8034.2023.12.036.
[32]
WANG Q Z, ZHAO W L, XING X Y, et al. Feasibility of AI-assisted compressed sensing protocols in knee MR imaging: a prospective multi-reader study[J]. Eur Radiol, 2023, 33(12): 8585-8596. DOI: 10.1007/s00330-023-09823-6.
[33]
LIU K, XI B, SUN H T, et al. The clinical feasibility of artificial intelligence-assisted compressed sensing single-shot fluid-attenuated inversion recovery (ACS-SS-FLAIR) for evaluation of uncooperative patients with brain diseases: comparison with the conventional T2-FLAIR with parallel imaging[J]. Acta Radiol, 2023, 64(5): 1943-1949. DOI: 10.1177/02841851221139125.
[34]
ZHAO Y J, PENG C D, WANG S F, et al. The feasibility investigation of AI-assisted compressed sensing in kidney MR imaging: an ultra-fast T2WI imaging technology[J/OL]. BMC Med Imaging, 2022, 22(1): 119 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/35787673/. DOI: 10.1186/s12880-022-00842-1.
[35]
TANG H, PENG C D, ZHAO Y J, et al. An applicability study of rapid artificial intelligence-assisted compressed sensing (ACS) in anal fistula magnetic resonance imaging[J/OL]. Heliyon, 2024, 10(1): e22817 [2024-04-25]. https://pubmed.ncbi.nlm.nih.gov/38169794/. DOI: 10.1016/j.heliyon.2023.e22817.

上一篇 磁共振集合序列与T2mapping序列在慢性冈上肌腱炎定量评估中的价值研究
下一篇 MR弹性成像与钆塞酸二钠增强T1 mapping定量评估兔肝纤维化的对比研究
  
诚聘英才 | 广告合作 | 免责声明 | 版权声明
联系电话:010-67113815
京ICP备19028836号-2