利用引导扩散增强改进基于深度学习的肩袖部分撕裂分级
该回顾性研究纳入1150例经关节镜证实肩袖撕裂患者,采用引导扩散模型增强MRI图像训练ResNet-34模型对Ellman分级进行预测,并与三名肌骨放射科医生比较。内部测试集AUC达0.97–0.99,外部测试集AUC达0.95–0.99,模型分级性能显著优于放射科医生(P<0.001),且评估时间缩短。结论认为该系统可提供可靠高效的肩袖部分撕裂分级方法。
要点
- 引导扩散增强可提升深度学习模型对肩袖部分撕裂Ellman分级的稳健性。
- 联合斜冠状面和斜矢状面序列的模型AUC在内部测试集为0.97–0.99,外部测试集为0.95–0.99。
- 模型分级性能显著优于三名经验丰富的肌骨放射科医生(P<0.001),并缩短评估时间。
核心结论
- 所提出的深度学习系统为肩袖部分撕裂分级提供可靠且高效的方法,达到放射科医生级准确度,且一致性更高、评估速度更快。
研究设计与样本
- 回顾性研究纳入1150例经关节镜证实肩袖撕裂患者,分为训练集741例、验证集185例、内部测试集185例,另设独立外部测试集224例;使用引导扩散模型增强MRI图像,采用ResNet-34模型对不同MRI序列(斜冠状面、斜矢状面及两者联合)进行Ellman分级,并与三名经验丰富的肌骨放射科医生比较。
诊断标准与关键数值
- 内部数据集滑囊侧部分撕裂:斜冠状面序列AUC 0.99、斜矢状面序列AUC 0.98、联合序列AUC 0.97;关节侧部分撕裂:斜冠状面序列AUC 0.99、斜矢状面序列AUC 0.99、联合序列AUC 0.99;序列组合间DeLong检验P=0.17、0.14、0.07,无显著差异。外部数据集联合序列模型:滑囊侧撕裂AUC 0.99、0.97、0.97,关节侧撕裂AUC 0.99、0.95、0.95。
临床应用与阅片要点
- 模型在内部和外部测试集均显示高AUC,且联合序列与单序列间无显著差异(P=0.17、0.14、0.07);放射科医生组内ICC为0.99,但分级性能显著低于ResNet-34模型(P<0.001);深度学习系统提高分级一致性并显著缩短评估时间。
局限性
- 原文未报告局限性。
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
RATIONALE AND OBJECTIVES: To develop and validate a deep learning system with guided diffusion-based data augmentation for grading partial-thickness supraspinatus tendon (SST) tears and to compare its performance with experienced radiologists, including external validation.
METHODS: This retrospective study included 1150 patients with arthroscopically confirmed SST tears, divided into a training set (741 patients), validation set (185 patients), and internal test set (185 patients). An independent external test set of 224 patients was used for generalizability assessment. To address data imbalance, MRI images were augmented using a guided diffusion model. A ResNet-34 model was employed for Ellman grading of bursal-sided and articular-sided partial-thickness tears across different MRI sequences (oblique coronal [OCOR], oblique sagittal [OSAG], and combined OCOR+OSAG). Performance was evaluated using AUC and precision-recall curves, and compared to three experienced musculoskeletal (MSK) radiologists. The DeLong test was used to compare performance across different sequence combinations.
RESULTS: A total of 26,020 OCOR images and 26,356 OSAG images were generated using the guided diffusion model. For bursal-sided partial-thickness tears in the internal dataset, the model achieved AUCs of 0.99, 0.98, and 0.97 for OCOR, OSAG, and combined sequences, respectively, while for articular-sided tears, AUCs were 0.99, 0.99, and 0.99. The DeLong test showed no significant differences among sequence combinations (P=0.17, 0.14, 0.07). In the external dataset, the combined-sequence model achieved AUCs of 0.99, 0.97, and 0.97 for bursal-sided tears and 0.99, 0.95, and 0.95 for articular-sided tears. Radiologists demonstrated an ICC of 0.99, but their grading performance was significantly lower than the ResNet-34 model (P<0.001). The deep learning system improved grading consistency and significantly reduced evaluation time, while guided diffusion augmentation enhanced model robustness.
CONCLUSION: The proposed deep learning system provides a reliable and efficient method for grading partial-thickness SST tears, achieving radiologist-level accuracy with greater consistency and faster evaluation speed.
引用
- Ni M, Jiesisibieke D, Zhao Y, et al. Improving Deep Learning-Based Grading of Partial-thickness Supraspinatus Tendon Tears with Guided Diffusion Augmentation. Acad Radiol. 2025. PMID: 40393829. doi:10.1016/j.acra.2025.04.072
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。