Carretero-Gómez Laura, Fung Maggie, Wiesinger Florian, Carl Michael, McKinnon Graeme, de Arcos José, Mandava Sagar, Arauz Santiago, Sánchez-Lacalle Eugenia, Nagrani Satish, López-Alcorocho Juan Manuel, Rodríguez-Íñigo Elena, Malpica Norberto, Padrón Mario
GE HealthCare, Munich, Germany.
Medical Image Analysis and Biometry Lab, Rey Juan Carlos University, Madrid, Spain.
Skeletal Radiol. 2025 Jun;54(6):1263-1273. doi: 10.1007/s00256-024-04830-0. Epub 2024 Nov 22.
To evaluate image quality and lesion conspicuity of zero echo time (ZTE) MRI reconstructed with deep learning (DL)-based algorithm versus conventional reconstruction and to assess DL ZTE performance against CT for bone loss measurements in shoulder instability.
Forty-four patients (9 females; 33.5 ± 15.65 years) with symptomatic anterior glenohumeral instability and no previous shoulder surgery underwent ZTE MRI and CT on the same day. ZTE images were reconstructed with conventional and DL methods and post-processed for CT-like contrast. Two musculoskeletal radiologists, blinded to the reconstruction method, independently evaluated 20 randomized MR ZTE datasets with and without DL-enhancement for perceived signal-to-noise ratio, resolution, and lesion conspicuity at humerus and glenoid using a 4-point Likert scale. Inter-reader reliability was assessed using weighted Cohen's kappa (K). An ordinal logistic regression model analyzed Likert scores, with the reconstruction method (DL-enhanced vs. conventional) as the predictor. Glenoid track (GT) and Hill-Sachs interval (HSI) measurements were performed by another radiologist on both DL ZTE and CT datasets. Intermodal agreement was assessed through intraclass correlation coefficients (ICCs) and Bland-Altman analysis.
DL ZTE MR bone images scored higher than conventional ZTE across all items, with significantly improved perceived resolution (odds ratio (OR) = 7.67, p = 0.01) and glenoid lesion conspicuity (OR = 25.12, p = 0.01), with substantial inter-rater agreement (K = 0.61 (0.38-0.83) to 0.77 (0.58-0.95)). Inter-modality assessment showed almost perfect agreement between DL ZTE MR and CT for all bone measurements (overall ICC = 0.99 (0.97-0.99)), with mean differences of 0.08 (- 0.80 to 0.96) mm for GT and - 0.07 (- 1.24 to 1.10) mm for HSI.
DL-based reconstruction enhances ZTE MRI quality for glenohumeral assessment, offering osseous evaluation and quantification equivalent to gold-standard CT, potentially simplifying preoperative workflow, and reducing CT radiation exposure.
评估采用基于深度学习（DL）的算法重建的零回波时间（ZTE）磁共振成像（MRI）与传统重建方法相比的图像质量和病变显示能力，并评估基于DL的ZTE在测量肩关节不稳骨质流失方面相对于CT的性能。
44例有症状的前盂肱关节不稳且既往无肩部手术史的患者（9例女性；年龄33.5±15.65岁）于同一天接受了ZTE MRI和CT检查。ZTE图像采用传统方法和DL方法重建，并进行后处理以获得类似CT的对比度。两名肌肉骨骼放射科医生在不知道重建方法的情况下，使用4分李克特量表独立评估20个随机的MR ZTE数据集，包括有无DL增强的情况，评估肱骨和肩胛盂的感知信噪比、分辨率和病变显示能力。使用加权科恩kappa（K）评估阅片者间的可靠性。采用有序逻辑回归模型分析李克特评分，以重建方法（DL增强与传统）作为预测因素。另一名放射科医生对DL ZTE和CT数据集进行肩胛盂轨迹（GT）和希尔-萨克斯间隙（HSI）测量。通过组内相关系数（ICC）和布兰德-奥特曼分析评估不同模态间的一致性。
在所有项目中，基于DL的ZTE MR骨图像评分均高于传统ZTE，感知分辨率（优势比（OR）=7.67，p=0.01）和肩胛盂病变显示能力（OR=25.12，p=0.01）显著提高，阅片者间一致性良好（K=0.61（0.38 - 0.83）至0.77（0.58 - 0.95））。不同模态评估显示，在所有骨测量方面，基于DL的ZTE MR与CT之间几乎完全一致（总体ICC=0.99（0.97 - 0.99）），GT的平均差异为0.08（-0.80至0.96）mm，HSI的平均差异为-0.07（-1.24至1.10）mm。
基于DL的重建提高了用于盂肱关节评估的ZTE MRI质量，提供了与金标准CT相当的骨质评估和量化，可能简化术前工作流程并减少CT辐射暴露。
