文献速递骨肌技术与安全CT

多发性骨髓瘤患者纵向CT扫描中基于结构不确定性分析的自动椎骨识别与分割

Automated vertebrae identification and segmentation with structural uncertainty analysis in longitudinal CT scans of patients with multiple myeloma.
PubMed 文献 · Eur J Radiol · 2025-05-03

回顾性纳入474例多发性骨髓瘤患者的纵向CT,在训练队列开发整合Payer深度学习法与事后结构不确定性分析的分割流程,测试队列显示识别率由95.8%升至98.8%、成功率由86.7%升至96.0%(p<0.001),椎骨匹配率与序列成功率亦显著提高。

要点

  • 该流程在测试队列将椎骨识别率由95.8%提升至98.8%、成功率由86.7%提升至96.0%(p<0.001)。
  • 流程将3.6%的扫描标记为需人工复核,复核后成功率由96.0%升至98.8%(p<0.001)。
  • 纵向椎骨匹配率由97.0%升至99.7%,序列成功率由80.0%升至95.4%(p<0.001)。

核心结论

  • 所提出的流程显著优于Payer方法,提高分割准确性并减少纵向匹配错误,同时减少评估工作量。

研究设计与样本

  • 回顾性研究,474例多发性骨髓瘤患者的CT扫描分为训练队列(179例患者、349次扫描,2005-2011年)和测试队列(295例患者、671次扫描,2012-2020年),在训练队列开发整合Payer开源深度学习椎骨分割与事后结构不确定性分析的增强分割流程。

诊断标准与关键数值

  • Payer方法识别率95.8%、成功率86.7%。
  • 所提出流程识别率98.8%、成功率96.0%(p<0.001)。
  • 流程标记3.6%的扫描需人工复核,复核后成功率由96.0%升至98.8%(p<0.001)。
  • 椎骨匹配率由97.0%升至99.7%(p<0.001),序列成功率由80.0%升至95.4%(p<0.001)。

临床应用与阅片要点

  • 结构不确定性分析可自动纠正不一致或标记不确定区域供人工复核,减少评估工作量。
  • 亚组分析显示流程在不同年龄和性别组间表现更一致。

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

OBJECTIVES: Optimize deep learning-based vertebrae segmentation in longitudinal CT scans of multiple myeloma patients using structural uncertainty analysis.

MATERIALS &amp; METHODS: Retrospective CT scans from 474 multiple myeloma patients were divided into train (179 patients, 349 scans, 2005-2011) and test cohort (295 patients, 671 scans, 2012-2020). An enhanced segmentation pipeline was developed on the train cohort. It integrated vertebrae segmentation using an open-source deep learning method (Payer's) with a post-hoc structural uncertainty analysis. This analysis identified inconsistencies, automatically correcting them or flagging uncertain regions for human review. Segmentation quality was assessed through vertebral shape analysis using topology. Metrics included 'identification rate', 'longitudinal vertebral match rate', 'success rate' and 'series success rate' and evaluated across age/sex subgroups. Statistical analysis included McNemar and Wilcoxon signed-rank tests, with p < 0.05 indicating significant improvement.

RESULTS: Payer's method achieved an identification rate of 95.8% and success rate of 86.7%. The proposed pipeline automatically improved these metrics to 98.8% and 96.0%, respectively (p < 0.001). Additionally, 3.6% of scans were marked for human inspection, increasing the success rate from 96.0% to 98.8% (p < 0.001). The vertebral match rate increased from 97.0% to 99.7% (p < 0.001), and the series success rate from 80.0% to 95.4% (p < 0.001). Subgroup analysis showed more consistent performance across age and sex groups.

CONCLUSION: The proposed pipeline significantly outperforms Payer's method, enhancing segmentation accuracy and reducing longitudinal matching errors while minimizing evaluation workload. Its uncertainty analysis ensures robust performance, making it a valuable tool for longitudinal studies in multiple myeloma.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Madzia-Madzou DK, Jak M, de Keizer B, et al. Automated vertebrae identification and segmentation with structural uncertainty analysis in longitudinal CT scans of patients with multiple myeloma. Eur J Radiol. 2025. PMID: 40349413. doi:10.1016/j.ejrad.2025.112160

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。