基于Genant半定量标准改编的深度学习在X线片上分类脊柱骨质疏松性压缩骨折
研究基于男性骨质疏松性骨折研究(MrOS)中4461名受试者的15524张脊柱X线片,提取100409个椎体,训练GoogLeNet深度学习模型将椎体分为中度至重度骨折与正常/微量/轻度骨折两类。模型敏感度59.8%、阳性预测值91.2%、F1分数0.72,AUC-ROC 0.99,精确率-召回率曲线下面积0.82。作者认为该模型可作为未来自动化机会性筛查工具的关键组成部分,有望促进骨质疏松性压缩骨折的早期发现和治疗。
要点
- 模型以预测概率最高的0.75%椎体判定为中度至重度骨质疏松性压缩骨折。
- 模型敏感度59.8%、阳性预测值91.2%、F1分数0.72,AUC-ROC为0.99。
- 标签基于Genant半定量标准改编:中度至重度骨折 vs 正常/微量/轻度骨折。
核心结论
- 模型以AUC-ROC 0.99对椎体进行分类,为未来自动化机会性筛查工具提供了关键组成部分,可能促进骨质疏松性压缩骨折的早期发现和治疗。
研究设计与样本
- 研究数据来自男性骨质疏松性骨折研究(Osteoporotic Fractures in Men Study),包含4461名受试者和15524张脊柱X线片,按受试者划分为76.5%训练集、8.5%验证集和15%测试集。从X线片中提取100409个椎体,每个椎体按改编自Genant半定量系统的标准标注为中度至重度骨折或正常/微量/轻度骨折两类。采用GoogLeNet深度学习模型对椎体进行分类,分类阈值设为优先保证阳性预测值并兼顾敏感度,预测概率最高的0.75%椎体被判为中度至重度骨折。
诊断标准与关键数值
- 标签采用改编自Genant半定量系统的二分类标准:中度至重度骨折 vs 正常/微量/轻度骨折。模型敏感度59.8%、阳性预测值91.2%、F1分数0.72,AUC-ROC 0.99,精确率-召回率曲线下面积0.82;预测概率最高的0.75%椎体被判为中度至重度骨折。
临床应用与阅片要点
- 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)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Osteoporosis affects 9% of individuals over 50 in the United States and 200 million women globally. Spinal osteoporotic compression fractures (OCFs), an osteoporosis biomarker, are often incidental and under-reported. Accurate automated opportunistic OCF screening can increase the diagnosis rate and ensure adequate treatment. We aimed to develop a deep learning classifier for OCFs, a critical component of our future automated opportunistic screening tool.
MATERIALS AND METHODS: The dataset from the Osteoporotic Fractures in Men Study comprised 4461 subjects and 15,524 spine radiographs. This dataset was split by subject: 76.5% training, 8.5% validation, and 15% testing. From the radiographs, 100,409 vertebral bodies were extracted, each assigned one of two labels adapted from the Genant semiquantitative system: moderate to severe fracture vs. normal/trace/mild fracture. GoogLeNet, a deep learning model, was trained to classify the vertebral bodies. The classification threshold on the predicted probability of OCF outputted by GoogLeNet was set to prioritize the positive predictive value (PPV) while balancing it with the sensitivity. Vertebral bodies with the top 0.75% predicted probabilities were classified as moderate to severe fracture.
RESULTS: Our model yielded a sensitivity of 59.8%, a PPV of 91.2%, and an F1 score of 0.72. The areas under the receiver operating characteristic curve (AUC-ROC) and the precision-recall curve were 0.99 and 0.82, respectively.
CONCLUSION: Our model classified vertebral bodies with an AUC-ROC of 0.99, providing a critical component for our future automated opportunistic screening tool. This could lead to earlier detection and treatment of OCFs.
引用
- Dong, Luo, Lane, et al. Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs using an Adaptation of the Genant Semiquantitative Criteria. Acad Radiol. 2022. PMID: 35351363. doi:10.1016/j.acra.2022.02.020
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。