文献速递胸部心血管CT

合作式人工智能训练用于CT心胸分割:一种迭代式多中心标注方法

Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.
PubMed 文献 · Eur J Radiol · 2024-05-25

本研究纳入132例临床胸部CT扫描,由13名放射科医生标注,通过三轮迭代训练实验评估AI预分割联合人工校正对心脏和纵隔分割精度与人工交互时间的影响。结果显示Dice系数随迭代持续提升(心脏0.91[0.88;0.92],纵隔0.95[0.94;0.95]),最强迭代中心脏和纵隔的人工交互时间分别减少50%和70%,仅用5例数据训练的模型Dice系数即大于0.90。

要点

  • AI预分割加人工校正的迭代流程可逐步提高心脏和纵隔分割模型质量。
  • 最强迭代中心脏和纵隔的人工交互时间分别减少50%和70%。
  • 仅用5例数据训练的模型即达到Dice系数大于0.90。

核心结论

  • 迭代训练流程为多中心研究中训练AI分割模型提供了高效方法,可随时间提高精度并同时减少人工干预。

研究设计与样本

  • 研究纳入132例临床胸部CT扫描,由13名放射科医生标注,进行三轮迭代训练实验,每轮初始手动分割5-25例CT作为nnU-Net训练数据,后续迭代纳入AI预分割与人工校正。

诊断标准与关键数值

  • 重采样数据集的心脏Dice相似系数为0.91[0.88;0.92]。
  • 重采样数据集的纵隔Dice相似系数为0.95[0.94;0.95]。
  • 仅用5例数据集训练的模型Dice系数大于0.90。

临床应用与阅片要点

  • 迭代AI预分割与人工校正流程可用于支持高分辨率胸部CT中心脏和纵隔的体素级分割标注任务。

局限性

  • 未来工作将探索使用更少的初始数据集和额外的预处理方法以提升模型质量。

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

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data.

METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time.

RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90).

CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Lassen-Schmidt B, Baessler B, Gutberlet M, et al. Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach. Eur J Radiol. 2024. PMID: 38820951. doi:10.1016/j.ejrad.2024.111534

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。