深度学习重建7分钟3T膝关节MRI的关节镜验证诊断效能
本研究回顾性纳入117例接受深度学习重建7分钟五序列3T膝关节MRI并行关节镜手术的成人患者,以关节镜为参考标准。结果显示图像质量良好,对半月板撕裂、前交叉韧带撕裂及关节软骨缺损的诊断效能为良好至优秀,AUC≥0.81。
要点
- 深度学习重建可在7分钟内完成五序列3T膝关节MRI,图像质量与诊断效能均较好
- 前交叉韧带撕裂诊断效能最高,敏感度97%、特异度98%、AUC 0.97
- 外侧半月板撕裂及关节软骨缺损敏感度相对较低,报告时需警惕漏诊
核心结论
- 临床7分钟五序列3T膝关节MRI联合深度学习重建对关节镜证实的膝关节内部结构损伤具有良好至优秀的诊断效能
- 深度学习重建可在保持高诊断效能的同时实现快速高质量3T膝关节MRI
研究设计与样本
- 回顾性研究,纳入2021年6月至2024年5月间117例连续成人患者,平均年龄44±16岁,男65例、女52例
- 所有患者均接受深度学习重建3T膝关节MRI及关节镜手术,MRI与手术中位间隔35天,范围5-88天
- 采用AIR Recon DL深度学习图像重建流程,行2-3倍并行成像加速的7分钟五序列3T膝关节MRI
- 由7名肌骨放射科医师独立阅片,评估图像质量参数及半月板撕裂、交叉韧带与侧副韧带撕裂、关节软骨缺损
- 统计分析包括阅片者间一致性及诊断效能检验,以关节镜手术作为参考标准
关键影像表现/征象
- 总体图像质量良好,中位数4分,IQR 4-5,图像噪声极小,中位数4分,IQR 4-4
- 边缘锐利度良好,中位数4分,IQR 4-5,重建伪影基本无,中位数5分,IQR 4-5
- 所有图像质量指标的阅片者间一致性高,κ≥0.83
诊断标准与关键数值
- 内侧半月板撕裂:敏感度89%、特异度87%、准确性88%、AUC 0.87,关节镜患病率78/117即67%
- 外侧半月板撕裂:敏感度72%、特异度91%、准确性83%、AUC 0.82,关节镜患病率50/117即43%
- 前交叉韧带撕裂:敏感度97%、特异度98%、准确性97%、AUC 0.97,关节镜患病率30/117即26%
- 关节软骨缺损:敏感度73%、特异度89%、准确性86%、AUC 0.81,关节镜患病率182/702即26%
- 结构异常诊断的阅片者间一致性为良好至很好,κ≥0.62
临床应用与阅片要点
- 深度学习重建7分钟3T膝关节MRI可用于临床疑似膝关节内部结构损伤的快速评估
- 前交叉韧带撕裂可依据MRI作出高把握度诊断,敏感度与特异度均接近或超过97%
- 外侧半月板撕裂与关节软骨缺损敏感度仅72%-73%,阴性结果不应完全排除病变
- 图像质量指标一致性高,提示该快速流程采集的图像适合多阅片者重复判读
局限性
- 回顾性单中心设计,患者均因疼痛接受关节镜手术,存在选择偏倚
- MRI与关节镜手术间隔中位35天,期间病变可能进展或变化
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND. Deep learning reconstruction (DLR) methods can enhance image quality and reduce scan time of knee MRI compared with conventional approaches but require validation against independent reference standards to ensure robustness and accuracy. OBJECTIVE. The purpose of this study was to assess the diagnostic performance of a two- to threefold parallel imaging-accelerated 7-minute five-sequence 3-T knee MRI protocol using a deep learning-based image reconstruction pipeline (AIR Recon DL, GE HealthCare), with arthroscopic surgery as the reference standard. METHODS. A total of 117 consecutive adult patients (mean age: 44 ± 16 [SD] years; 65 men, 52 women) with painful knee conditions who underwent DLR 3-T knee MRI and arthroscopic knee surgery with a median MRI-to-surgery interval of 35 days (range: 5-88 days) between June 2021 and May 2024 were retrospectively identified and included. MRI studies were independently reviewed by seven musculoskeletal radiologists for image quality parameters using Likert scales (range: 1 [very bad] to 5 [very good]) and the presence of meniscus tears, cruciate and collateral ligament tears, and articular cartilage defects. Statistical analyses included interreader agreements and diagnostic performance testing. RESULTS. Overall image quality of DLR knee MRI scans was good (median: 4 [IQR, 4-5]), with minimal image noise (median: 4 [IQR, 4-4]), good edge sharpness (median: 4 [IQR, 4-5]), absence of reconstruction artifacts (median: 5 [IQR, 4-5]), and high interreader agreement for all quality metrics (κ ≥ 0.83). Diagnostic performance for detecting arthroscopy-validated structural abnormalities was good to excellent (AUC ≥ 0.81) with good to very good interreader agreement (κ ≥ 0.62). The sensitivity, specificity, accuracy, and AUC values were 89%, 87%, 88%, and 0.87 for medial meniscus tears (prevalence at arthroscopy: 78/117, 67%); 72%, 91%, 83%, and 0.82 for lateral meniscus tears (prevalence at arthroscopy: 50/117, 43%); 97%, 98%, 97%, and 0.97 for anterior cruciate ligament tears (prevalence at arthroscopy: 30/117, 26%); and 73%, 89%, 86%, and 0.81 for articular cartilage defects (prevalence at arthroscopy: 182/702, 26%). CONCLUSION. Clinical 7-minute five-sequence 3-T knee MRI with DLR provides good to excellent diagnostic performance for detecting arthroscopy-validated internal derangement of the knee. CLINICAL IMPACT. DLR enables rapid high-quality clinical 3-T knee MRI with high diagnostic performance for arthroscopy-validated abnormalities.
引用
- Leonhardt, Vosshenrich, Jardon, et al. Arthroscopy-Validated Diagnostic Performance of a Deep Learning Reconstruction Pipeline for Rapid 7-Minute Five-Sequence 3-T Knee MRI. AJR Am J Roentgenol. 2026. PMID: 42455029. doi:10.2214/AJR.26.35094
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。