深度学习赋能超声用于进展性距腓前韧带损伤分类:多中心模型开发与验证研究
本研究在10家医院回顾性纳入健康对照和急性距腓前韧带损伤患者,开发基于超声的深度学习模型ATFLNet并进行内外部验证,另在3家医院前瞻性验证。模型在五分类中宏观平均AUC≥0.970,外部验证中持续优于高年资放射科医生(均p<.05);AI辅助策略将放射科医生平均准确率从0.707提升至0.811(p<.001),模拟场景中准确率从0.794提升至0.864(p=.003)并降低诊断变异性。
要点
- ATFLNet在全部五个分类中宏观平均AUC≥0.970,外部验证中持续优于高年资放射科医生(均p<.05)。
- AI辅助策略将放射科医生阅片平均准确率从0.707提升至0.811(p<.001)。
- 模拟场景中AI辅助使准确率从0.794提升至0.864(p=.003),并降低诊断变异性,初级放射科医生尤为明显。
核心结论
- 基于超声的ATFLNet模型在ATFL损伤评估中优于人类专家,AI辅助策略在真实临床场景中有提升诊断表现的潜力。
研究设计与样本
- 回顾性纳入10家医院连续健康对照和急性ATFL损伤患者(轻度扭伤、部分撕裂、完全撕裂和撕脱骨折),ATFLNet训练集n=2566、内部验证集n=642、外部验证集n=717和493;参考标准为三名专家多数共识的手术或影像学发现;另在3家医院进行前瞻性验证(n=472)。
诊断标准与关键数值
- ATFLNet在各数据集的全部五个分类中宏观平均AUC≥0.970。
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: Ultrasound (US) is the preferred modality for assessing anterior talofibular ligament (ATFL) injuries. We aimed to advance ATFL injuries classification by developing a US-based deep learning (DL) model, and explore how artificial intelligence (AI) could help radiologists improve diagnostic performance.
MATERIALS AND METHODS: Consecutive healthy controls and patients with acute ATFL injuries (mild strain, partial tear, complete tear, and avulsion fracture) at 10 hospitals were retrospectively included. A US-based DL model (ATFLNet) was trained (n=2566), internally validated (n=642), and externally validated (n=717 and 493). Surgical or radiological findings based on the majority consensus of three experts served as the reference standard. Prospective validation was conducted at three additional hospitals (n=472). The performance was compared to that of 12 radiologists at different levels (external validation sets 1 and 2); an ATFLNet-aided strategy was developed, comparing with the radiologists when reviewing B-mode images (external validation set 2); the strategy was then tested in a simulated scenario (reviewing images alongside dynamic clips; prospective validation set). Statistical comparisons were performed using the McNemar's test, while inter-reader agreement was evaluated with the Multireader Fleiss κ statistic.
RESULTS: ATFLNet obtained macro-average area under the curve ≥0.970 across all five classes in each dataset, indicating robust overall performance. Additionally, it consistently outperformed senior radiologists in external validation sets (all p<.05). ATFLNet-aided strategy improved radiologists' average accuracy (0.707 vs. 0.811, p<.001) for image review. In the simulated scenario, it led to enhanced accuracy (0.794 to 0.864, p=.003), and a reduction in diagnostic variability, particularly for junior radiologists.
CONCLUSIONS: Our US-based model outperformed human experts for ATFL injury evaluation. AI-aided strategies hold the potential to enhance diagnostic performance in real-world clinical scenarios.
引用
- Shi X, Zhang H, Yuan Y, et al. Deep Learning-Enabled Ultrasound for Advancing Anterior Talofibular Ligament Injuries Classification: A Multicenter Model Development and Validation Study. Acad Radiol. 2025. PMID: 40764200. doi:10.1016/j.acra.2025.07.013
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。