指南与共识骨肌胸部技术与安全CTDR

基于胸部低剂量CT的视觉Transformer-卷积神经网络框架用于决策透明的双能X线吸收测定法推荐

A vision transformer-convolutional neural network framework for decision-transparent dual-energy X-ray absorptiometry recommendations using chest low-dose CT.
指南 / 共识 · Int J Med Inform · 2025-03-28

本研究构建并验证了一个融合视觉Transformer与卷积神经网络的集成框架,利用321例开发队列和186例独立测试队列的胸部低剂量CT图像,完成骨密度正常与异常分类及骨质疏松与非骨质疏松分类,并据此生成双能X线吸收测定法检查推荐。框架在两项分类任务中均显著优于单一模型,测试队列任务1准确率86.6%、任务2准确率76.9%,双能X线吸收测定法推荐准确率87.1%,骨质疏松检出准确率达100%。

要点

  • 集成框架在测试队列中双能X线吸收测定法推荐准确率为87.1%,骨质疏松检出准确率达100%。
  • fitFOV与largeFOV设置下模型表现较好,fitFOV用于任务2、largeFOV用于任务1。
  • 框架可可视化分类置信度与椎体异常,提升决策透明度。

核心结论

  • 融合视觉Transformer与卷积神经网络的框架能有效评估胸部低剂量CT图像中的骨状态,尤其在使用fitFOV和largeFOV设置时,并通过可视化分类置信度和椎体异常提升决策透明度,支持临床医生在机会性骨质疏松筛查后做出双能X线吸收测定法推荐。

研究设计与样本

  • 研究论文;框架开发使用321例个体数据,独立测试队列186例;分析fitFOV(整个椎体)、halfFOV(仅椎体)和largeFOV(fitFOV+20%)三种视野设置对模型性能的影响;以双能X线吸收测定法扫描作为推荐目标。

诊断标准与关键数值

  • 任务1(骨密度正常与异常分类):开发队列largeFOV准确率91.6%、AUROC 0.97;测试队列准确率86.6%、AUROC 0.93。
  • 任务2(骨质疏松与非骨质疏松分类):开发队列fitFOV准确率86.0%、AUROC 0.94;测试队列准确率76.9%、AUROC 0.99。
  • 双能X线吸收测定法推荐准确率:开发队列91.6%,测试队列87.1%。
  • 骨质疏松检出准确率:开发队列98.7%,测试队列100%。
  • 集成框架在两项分类任务中均显著优于单一模型(McNemar检验,p<0.001)。

临床应用与阅片要点

  • 对胸部低剂量CT图像可机会性评估骨状态,框架对骨密度异常或骨质疏松分类者生成双能X线吸收测定法检查推荐。
  • 阅片时可参考框架输出的分类置信度与椎体异常可视化信息辅助决策。
  • 模型性能与视野设置相关,fitFOV和largeFOV设置下表现较好。

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

OBJECTIVE: This study introduces an ensemble framework that integrates Vision Transformer (ViT) and Convolutional Neural Networks (CNN) models to leverage their complementary strengths, generating visualized and decision-transparent recommendations for dual-energy X-ray absorptiometry (DXA) scans from chest low-dose computed tomography (LDCT).

METHODS: The framework was developed using data from 321 individuals and validated with an independent test cohort of 186 individuals. It addresses two classification tasks: (1) distinguishing normal from abnormal bone mineral density (BMD) and (2) differentiating osteoporosis from non-osteoporosis. Three field-of-view (FOV) settings-fitFOV (entire vertebra), halfFOV (vertebral body only), and largeFOV (fitFOV + 20 %)-were analyzed to assess their impact on model performance. Model predictions were weighted and combined to enhance classification accuracy, and visualizations were generated to improve decision transparency. DXA scans were recommended for individuals classified as having abnormal BMD or osteoporosis.

RESULTS: The ensemble framework significantly outperformed individual models in both classification tasks (McNemar test, p < 0.001). In the development cohort, it achieved 91.6 % accuracy for task 1 with largeFOV (area under the receiver operating characteristic curve [AUROC]: 0.97) and 86.0 % accuracy for task 2 with fitFOV (AUROC: 0.94). In the test cohort, it demonstrated 86.6 % accuracy for task 1 (AUROC: 0.93) and 76.9 % accuracy for task 2 (AUROC: 0.99). DXA recommendation accuracy was 91.6 % and 87.1 % in the development and test cohorts, respectively, with notably high accuracy for osteoporosis detection (98.7 % and 100 %).

CONCLUSIONS: This combined ViT-CNN framework effectively assesses bone status from LDCT images, particularly when utilizing fitFOV and largeFOV settings. By visualizing classification confidence and vertebral abnormalities, the proposed framework enhances decision transparency and supports clinicians in making informed DXA recommendations following opportunistic osteoporosis screening.

来源:Int J Med Inform,查看原文。版权归原作者所有。

引用

  1. Kuo DP, Chen YC, Cheng SJ, et al. A vision transformer-convolutional neural network framework for decision-transparent dual-energy X-ray absorptiometry recommendations using chest low-dose CT. Int J Med Inform. 2025. PMID: 40187299. doi:10.1016/j.ijmedinf.2025.105901

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。