文献速递骨肌DR

使用分割模型集成在X线平片上检测椎体

Using an Ensemble of Segmentation Methods to Detect Vertebral Bodies on Radiographs.
PubMed 文献 · AJNR Am J Neuroradiol · 2024-10-03

本研究基于骨松性骨折男性研究(MrOS)数据集(5994例≥65岁男性,6个临床中心)回顾性训练U-Net与Mask-RCNN椎体分割模型并构建集成模型,在留出测试集上检测所有椎体的F1分数集成模型为88.34%,检测严重骨折椎体的F1分数为97.14%;外部数据集上集成模型检测所有椎体的F1分数为87.72%。结论认为集成模型在侧位X线平片上检测椎体表现最佳且泛化良好,可作为自动化机会性筛查工具的关键组成部分。

要点

  • 集成模型检测所有椎体的F1分数为88.34%,高于U-Net的83.42%和Mask-RCNN的86.30%。
  • 集成模型检测严重骨折椎体的F1分数为97.14%,高于U-Net的87.88%和Mask-RCNN的92.31%。
  • 外部数据集上集成模型检测所有椎体的F1分数为87.72%,显示泛化良好。

核心结论

  • 结合U-Net与Mask-RCNN预测的集成模型在侧位X线平片上检测椎体表现最佳,并在外部数据集上泛化良好;该模型可能成为自动化机会性筛查工具中检测所有椎体骨折的关键组成部分。

研究设计与样本

  • 回顾性研究,使用骨松性骨折男性研究(MrOS)数据集,包含来自6个临床中心的5994例≥65岁男性的脊柱X线平片;U-Net与Mask-RCNN两种分割模型独立训练后构建集成模型;以留出测试集评估椎体检测性能,并采用来自四级医疗企业的独立外部数据集(≥65岁男性和女性的诊断性临床X线平片)测试泛化性。

诊断标准与关键数值

  • 椎体检测成功的主要性能指标为精确率、召回率和F1分数;所有椎体检测F1分数:U-Net 83.42%、Mask-RCNN 86.30%、集成模型88.34%;严重骨折椎体检测F1分数:U-Net 87.88%、Mask-RCNN 92.31%、集成模型97.14%;平均每个椎体的IoU:U-Net 0.759、Mask-RCNN 0.709;外部数据集所有椎体检测F1分数:U-Net 81.11%、Mask-RCNN 79.24%、集成模型87.72%。

临床应用与阅片要点

  • 作者认为该集成模型可能成为自动化机会性筛查工具中检测X线平片上所有椎体骨折的关键组成部分。

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

BACKGROUND AND PURPOSE: Vertebral compression fractures may indicate osteoporosis but are underdiagnosed and underreported by radiologists. We have developed an ensemble of vertebral body (VB) segmentation models for lateral radiographs as a critical component of an automated, opportunistic screening tool. Our goal is to detect the approximate location of thoracic and lumbar VBs, including fractured vertebra, on lateral radiographs.

MATERIALS AND METHODS: The Osteoporotic Fractures in Men Study (MrOS) data set includes spine radiographs of 5994 men aged ≥65 years from 6 clinical centers. Two segmentation models, U-Net and Mask-RCNN (Region-based Convolutional Neural Network), were independently trained on the MrOS data set retrospectively, and an ensemble was created by combining them. Primary performance metrics for VB detection success included precision, recall, and F1 score for object detection on a held-out test set. Intersection over union (IoU) and Dice coefficient were also calculated as secondary metrics of performance for the test set. A separate external data set from a quaternary health care enterprise was acquired to test generalizability, comprising diagnostic clinical radiographs from men and women aged ≥65 years.

RESULTS: The trained models achieved F1 score of U-Net = 83.42%, Mask-RCNN = 86.30%, and ensemble = 88.34% in detecting all VBs, and F1 score of U-Net = 87.88%, Mask-RCNN = 92.31%, and ensemble = 97.14% in detecting severely fractured vertebrae. The trained models achieved an average IoU per VB of 0.759 for U-Net and 0.709 for Mask-RCNN. The trained models achieved F1 score of U-Net = 81.11%, Mask-RCNN = 79.24%, and ensemble = 87.72% in detecting all VBs in the external data set.

CONCLUSIONS: An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Chang BC, Renslo J, Dong Q, et al. Using an Ensemble of Segmentation Methods to Detect Vertebral Bodies on Radiographs. AJNR Am J Neuroradiol. 2024. PMID: 39209486. doi:10.3174/ajnr.A8343

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。