全自动多阶段深度学习系统用于Lenke分型:提高青少年特发性脊柱侧凸的诊断精度
本研究开发并验证了一个基于脊柱X线片的全自动深度学习系统,用于青少年特发性脊柱侧凸的Lenke分型。该系统在独立测试集上达到95.6%的总体准确率,腰椎和矢状面修饰符的F1分数分别为0.912和0.928,Cobb角测量与专家评估高度一致(ICC 0.969-0.976)。结论认为该系统可快速、客观、可解释且临床可靠地直接从X线片进行Lenke分型,性能与专家评估相当。
要点
- 全自动深度学习系统对Lenke分型的总体准确率达95.6%,宏平均F1分数为0.862。
- 椎体分割Dice系数正位0.917、侧位0.942,Cobb角测量与专家ICC为0.969至0.976。
- 腰椎修饰符(A/B/C)和矢状面修饰符(-/N/+)的F1分数分别为0.912和0.928,超过临床可接受阈值。
核心结论
- 全自动系统能够直接从X线片进行快速、客观、可解释且临床可靠的Lenke分型,性能与专家评估相当。
- 该系统在标准化青少年特发性脊柱侧凸手术规划、减少诊断差异和提高手术流程效率方面具有潜力。
研究设计与样本
- 回顾性研究纳入650人(平均年龄13.75±2.23岁;女433例,男217例;汉族618例,藏族32例),包括183名健康对照和467例青少年特发性脊柱侧凸患者(年龄10至18岁;25°≤Cobb角<90°),均具有全脊柱X线片。
- 多阶段深度学习系统包括:Swin-Unet分割椎体(C7-S1)以自动测量Cobb角;DeepLabv3+定位腰椎椎弓根(L1-L5),通过质心至中央骶椎线(CSVL)距离确定修饰符;融合模块整合特征以输出曲线类型及腰椎(A/B/C)和矢状面胸椎(-/N/+)修饰符,实现端到端自动Lenke分型。
- 使用独立测试集进行验证。
主要发现
- 系统在Lenke分型中达到95.6%的总体准确率,宏平均F1分数为0.862。
- 椎体分割的Dice系数为0.917(正位)和0.942(侧位)。
- Cobb角测量与专家评估高度一致,胸弯或胸腰弯/腰弯的组内相关系数为0.969至0.976。
- 修饰符分配的F1分数为0.912(腰椎A/B/C)和0.928(矢状面-/N/+),超过临床可接受阈值。
关键数值与推荐
- Lenke分型总体准确率95.6%,宏平均F1分数0.862。
- 椎体分割Dice系数:正位0.917,侧位0.942。
- Cobb角测量与专家ICC:胸弯或胸腰弯/腰弯0.969至0.976。
- 修饰符F1分数:腰椎A/B/C 0.912,矢状面-/N/+ 0.928。
临床怎么用
- 原文未据此给出推荐。
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)。
原文
BACKGROUND: The Lenke classification for adolescent idiopathic scoliosis (AIS) has interobserver variability due to subjective clinical assessment. We developed and validated a fully automated deep learning system for precise Lenke classification using spinal radiographs. METHODS: This retrospective study included 650 individuals (mean age, 13.75 ± 2.23 years; 433 female, 217 male; 618 Han Chinese, 32 Tibetan), comprising 183 healthy controls and 467 patients with AIS (aged 10 to 18 years; 25° ≤ Cobb angle < 90°) with full-spine radiographs. A multistage deep learning system consisting of (1) Swin-Unet segmentation of vertebrae (C7-S1) for automated Cobb angle measurement, (2) DeepLabv3+ localization of lumbar pedicles (L1-L5) to determine modifiers via the centroid-to-CSVL (central sacral vertebral line) distance, and (3) a fusion module integrating features to curve types and lumbar (A/B/C) and sagittal thoracic (-/N/+) modifiers was designed to perform end-to-end Lenke classification automatically. Validation used an independent test set. RESULTS: The system achieved 95.6% overall accuracy in Lenke classification and had a macro-averaged F1 score of 0.862. Vertebral segmentation attained Dice coefficients of 0.917 (anteroposterior) and 0.942 (lateral). Cobb angle measurements showed excellent agreement with those of experts (intraclass correlation coefficient, 0.969 to 0.976 for thoracic or thoracolumbar/lumbar curves). Modifier assignment achieved F1 scores of 0.912 (lumbar A/B/C) and 0.928 (sagittal -/N/+), exceeding clinical acceptability thresholds. CONCLUSIONS: The fully automated system was able to perform rapid, objective, interpretable, and clinically reliable classification of the Lenke type directly from radiographs, with performance comparable with that of expert assessment. It demonstrates potential for standardizing AIS surgical planning, reducing diagnostic variability, and improving surgical workflow efficiency. LEVEL OF EVIDENCE: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.
引用
- Xu L, Liu C, Zhong W, et al. A Fully Automated Multistage Deep Learning System for Lenke Classification: Enhanced Diagnostic Precision in Adolescent Idiopathic Scoliosis. J Bone Joint Surg Am. 2025. PMID: 41460944. doi:10.2106/JBJS.25.01015
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。