THA-AID:用于全髋关节置换术植入物自动检测并量化不确定性与离群值的深度学习工具
本研究开发了基于241,419张X线片训练的深度学习工具THA-AID,可从正位、侧位或斜位片识别20种股骨和8种髋臼假体,并报告预测不确定性和检测离群数据。内部测试集股骨与髋臼准确率均为98.9%,外部测试集股骨准确率97.0%,超过99%的域外和超过89%的域内离群数据被正确识别。
要点
- THA-AID可从正位、侧位或斜位X线片识别20种股骨和8种髋臼假体。
- 内部测试集股骨与髋臼准确率均为98.9%,不同投照体位间无显著差异。
- 外部测试集股骨分类器准确率97.0%,超过99%域外离群数据被正确识别。
核心结论
- THA-AID是用于从X线片自动识别植入物的工具,在内部和外部测试集上表现优异,且性能不因投照体位而下降。
- 据作者所知,这是骨科首个包含深度学习模型不确定性量化和离群检测的研究。
研究设计与样本
- 研究基于241,419张X线片训练THA-AID深度学习工具,用于识别20种股骨和8种髋臼假体。
- 使用内部、外部和域外测试集评估THA-AID,并与人类专家比较性能。
- 采用保形预测报告预测不确定性,并使用自定义框架进行离群检测。
主要发现
- THA-AID内部测试集股骨和髋臼组件准确率均为98.9%,不同X线投照体位间无显著差异。
- 股骨分类器在外部测试集准确率为97.0%。
- 加入保形预测后,髋臼真标签预测提高0.1%,股骨组件提高0.7%至0.9%。
- 超过99%的域外离群数据和超过89%的域内离群数据被THA-AID正确识别。
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: Revision total hip arthroplasty (THA) requires preoperatively identifying in situ implants, a time-consuming and sometimes unachievable task. Although deep learning (DL) tools have been attempted to automate this process, existing approaches are limited by classifying few femoral and zero acetabular components, only classify on anterior-posterior (AP) radiographs, and do not report prediction uncertainty or flag outlier data. METHODS: This study introduces Total Hip Arhtroplasty Automated Implant Detector (THA-AID), a DL tool trained on 241,419 radiographs that identifies common designs of 20 femoral and 8 acetabular components from AP, lateral, or oblique views and reports prediction uncertainty using conformal prediction and outlier detection using a custom framework. We evaluated THA-AID using internal, external, and out-of-domain test sets and compared its performance with human experts. RESULTS: THA-AID achieved internal test set accuracies of 98.9% for both femoral and acetabular components with no significant differences based on radiographic view. The femoral classifier also achieved 97.0% accuracy on the external test set. Adding conformal prediction increased true label prediction by 0.1% for acetabular and 0.7 to 0.9% for femoral components. More than 99% of out-of-domain and >89% of in-domain outlier data were correctly identified by THA-AID. CONCLUSIONS: The THA-AID is an automated tool for implant identification from radiographs with exceptional performance on internal and external test sets and no decrement in performance based on radiographic view. Importantly, this is the first study in orthopedics to our knowledge including uncertainty quantification and outlier detection of a DL model.
引用
- Rouzrokh P, Mickley JP, Khosravi B, et al. THA-AID: Deep Learning Tool for Total Hip Arthroplasty Automatic Implant Detection With Uncertainty and Outlier Quantification. J Arthroplasty. 2023. PMID: 37770007. doi:10.1016/j.arth.2023.09.025
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。