深度学习用于自动髋部骨折检测与分类:实现更高准确率
以骨科医生诊断为参考标准,比较人工智能辅助前后的诊断表现。模型在内部数据集四类骨折中准确率0.99–1.0,外部验证集敏感度0.83–0.89、特异度0.90–0.99。结论认为该模型较单纯人工诊断显著提高髋部骨折检测与分类准确率。
要点
- 模型在内部数据集四类骨折中准确率0.99–1.0,外部验证集敏感度0.83–0.89、特异度0.90–0.99。
- 内部数据集不稳定型骨折敏感度0.98、特异度0.99,稳定型敏感度0.95、特异度0.99。
- 外部验证集Micro AVG敏感度0.83(SD 0.05)、特异度0.96(SD 0.01),Macro AVG敏感度0.69(SD 0.02)、特异度0.95(SD 0.02)。
核心结论
- 与单纯人工诊断相比,所开发模型显著提高髋部骨折检测与分类的准确率。
- 该模型在辅助临床医生准确诊断和分类髋部骨折方面显示出较大潜力。
研究设计与样本
- 回顾性研究使用5168张髋关节正位X线片,其中两家机构的4493张(内部数据集)用于训练,另一家机构的675张用于验证。
- 基于卷积神经网络(CNN)的分类模型在四种髋部骨折类型(移位型、外翻嵌插型、稳定型、不稳定型)上训练,使用DAMO-YOLO进行数据处理与增强。
- 以骨科医生诊断为参考标准,比较人工智能辅助前后的诊断表现。
主要发现
- 内部数据集四类骨折的准确率、敏感度、特异度、IoU、Dice系数分别为:移位型(1.0、0.79、1.0、0.70、0.82),外翻嵌插型(1.0、0.80、1.0、0.70、0.82),稳定型(0.99、0.95、0.99、0.83、0.89),不稳定型(1.0、0.98、0.99、0.86、0.92)。
- 外部验证数据集四类骨折的敏感度与特异度分别为:移位型(0.83、0.94),外翻嵌插型(0.89、0.90),稳定型(0.88、0.95),不稳定型(0.85、0.99)。
- 外部数据集的总体均值:Micro AVG敏感度0.83(SD 0.05)、特异度0.96(SD 0.01);Macro AVG敏感度0.69(SD 0.02)、特异度0.95(SD 0.02)。
临床怎么用
- 作者认为该模型在辅助临床医生准确诊断和分类髋部骨折方面显示出较大潜力。
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
AIMS: The aim of this study was to develop and evaluate a deep learning-based model for classification of hip fractures to enhance diagnostic accuracy. METHODS: A retrospective study used 5,168 hip anteroposterior radiographs, with 4,493 radiographs from two institutes (internal dataset) for training and 675 radiographs from another institute for validation. A convolutional neural network (CNN)-based classification model was trained on four types of hip fractures (Displaced, Valgus-impacted, Stable, and Unstable), using DAMO-YOLO for data processing and augmentation. The model's accuracy, sensitivity, specificity, Intersection over Union (IoU), and Dice coefficient were evaluated. Orthopaedic surgeons' diagnoses served as the reference standard, with comparisons made before and after artificial intelligence assistance. RESULTS: The accuracy, sensitivity, specificity, IoU, and Dice coefficients of the model for the four fracture categories in the internal dataset were as follows: Displaced (1.0, 0.79, 1.0, 0.70, 0.82), Valgus-impacted (1.0, 0.80, 1.0, 0.70, 0.82), Stable (0.99, 0.95, 0.99, 0.83, 0.89), and Unstable (1.0, 0.98, 0.99, 0.86, 0.92), respectively. For the external validation dataset, the sensitivity and specificity were as follows: Displaced (0.83, 0.94), Valgus-impacted (0.89, 0.90), Stable (0.88, 0.95), and Unstable (0.85, 0.99), respectively. The overall means (Micro AVG and Macro AVG) for the external dataset were Micro AVG (0.83 (SD 0.05), 0.96 (SD 0.01)) and Macro AVG (0.69 (SD 0.02), 0.95 (SD 0.02)), respectively. CONCLUSION: Compared to human diagnosis alone, our study demonstrates that the developed model significantly improves the accuracy of detecting and classifying hip fractures. Our model has shown great potential in assisting clinicians with the accurate diagnosis and classification of hip fractures.
引用
- Zheng Z, Ryu BY, Kim SE, et al. Deep learning for automated hip fracture detection and classification : achieving superior accuracy. Bone Joint J. 2025. PMID: 39889758. doi:10.1302/0301-620X.107B2.BJJ-2024-0791.R1
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。