文献速递胸部儿科影像CT

深度学习在多模型集成下实现全肺及肺病灶量化:应用于SARS-CoV-2非人灵长类模型CT

Deep-Learning-Based Whole-Lung and Lung-Lesion Quantification Despite Inconsistent Ground Truth: Application to Computerized Tomography in SARS-CoV-2 Nonhuman Primate Models.
PubMed 文献 · Acad Radiol · 2023-02-27

本研究在SARS-CoV-2暴露的非人灵长类模型CT上,提出多模型集成与特征金字塔网络(FPN)的深度学习方法,解决手动标注不一致问题,实现全肺和肺病灶自动分割。全肺分割平均Dice系数99.4%,病灶分割60.2%,优于U-Net(50.5%)、V-Net(54.5%)和Inception(53.4%)。分割输出可用于纵向量化肺病,提示深度学习应针对临床前研究需求优化。

要点

  • 全肺分割Dice达99.4%,可稳定用于肺容积定量。
  • 病灶分割Dice仅60.2%,阅片报告需谨慎解读自动病灶定量。
  • 多模型集成FPN优于U-Net、V-Net和Inception,适合大小不一的病灶。

核心结论

  • 深度学习多模型集成FPN可实现非人灵长类SARS-CoV-2模型CT的全肺和肺病灶自动分割,全肺Dice 99.4%、病灶Dice 60.2%。
  • 病灶分割性能优于U-Net(50.5%)、V-Net(54.5%)和Inception(53.4%),分割结果可用于纵向疾病量化。

研究设计与样本

  • 临床前研究,使用暴露于SARS-CoV-2的非人灵长类(NHP)CT扫描。
  • 采用深度学习卷积神经网络,提出多模型集成技术:在不同训练数据子集上训练多个CNN模型,而非单一模型使用全部训练数据。
  • 使用特征金字塔网络(FPN)提供不同分辨率预测,以适应大小变化的病灶。
  • 参考标准为手动勾画的全肺和肺病灶,但原文指出手动勾画存在专家间及专家自身的不一致性。
  • 原文未报告样本量、中心数及具体CT设备/序列参数。

关键影像表现/征象

  • 原文聚焦于自动分割量化,未描述具体影像征象(如磨玻璃影、实变等)的视觉特征。

诊断标准与关键数值

  • 全肺分割平均Dice系数99.4%。
  • 肺病灶分割平均Dice系数60.2%。
  • 对比方法病灶分割Dice:U-Net 50.5%、V-Net 54.5%、Inception 53.4%。

临床应用与阅片要点

  • 全肺分割高度可靠,可用于肺容积等定量指标。
  • 病灶分割Dice仅60.2%,自动病灶定量结果需结合视觉阅片验证,避免过度依赖。
  • 多模型集成策略可应对标注不一致,但临床前模型向人类临床转化仍需验证。

局限性

  • 手动标注存在专家间和专家自身的不一致性,影响病灶分割参考标准。
  • 研究为临床前非人灵长类模型,向人类临床应用的转化具有挑战性。
  • 原文未报告样本量、多中心验证等细节,外部泛化性未知。

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: Animal modeling of infectious diseases such as coronavirus disease 2019 (COVID-19) is important for exploration of natural history, understanding of pathogenesis, and evaluation of countermeasures. Preclinical studies enable rigorous control of experimental conditions as well as pre-exposure baseline and longitudinal measurements, including medical imaging, that are often unavailable in the clinical research setting. Computerized tomography (CT) imaging provides important diagnostic, prognostic, and disease characterization to clinicians and clinical researchers. In that context, automated deep-learning systems for the analysis of CT imaging have been broadly proposed, but their practical utility has been limited. Manual outlining of the ground truth (i.e., lung-lesions) requires accurate distinctions between abnormal and normal tissues that often have vague boundaries and is subject to reader heterogeneity in interpretation. Indeed, this subjectivity is demonstrated as wide inconsistency in manual outlines among experts and from the same expert. The application of deep-learning data-science tools has been less well-evaluated in the preclinical setting, including in nonhuman primate (NHP) models of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection/COVID-19, in which the translation of human-derived deep-learning tools is challenging. The automated segmentation of the whole lung and lung lesions provides a potentially standardized and automated method to detect and quantify disease.

MATERIALS AND METHODS: We used deep-learning-based quantification of the whole lung and lung lesions on CT scans of NHPs exposed to SARS-CoV-2. We proposed a novel multi-model ensemble technique to address the inconsistency in the ground truths for deep-learning-based automated segmentation of the whole lung and lung lesions. Multiple models were obtained by training the convolutional neural network (CNN) on different subsets of the training data instead of having a single model using the entire training dataset. Moreover, we employed a feature pyramid network (FPN), a CNN that provides predictions at different resolution levels, enabling the network to predict objects with wide size variations.

RESULTS: We achieved an average of 99.4 and 60.2% Dice coefficients for whole-lung and lung-lesion segmentation, respectively. The proposed multi-model FPN outperformed well-accepted methods U-Net (50.5%), V-Net (54.5%), and Inception (53.4%) for the challenging lesion-segmentation task. We show the application of segmentation outputs for longitudinal quantification of lung disease in SARS-CoV-2-exposed and mock-exposed NHPs.

CONCLUSION: Deep-learning methods should be optimally characterized for and targeted specifically to preclinical research needs in terms of impact, automation, and dynamic quantification independently from purely clinical applications.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Reza, Chu, Homayounieh, et al. Deep-Learning-Based Whole-Lung and Lung-Lesion Quantification Despite Inconsistent Ground Truth: Application to Computerized Tomography in SARS-CoV-2 Nonhuman Primate Models. Acad Radiol. 2023. PMID: 36966070. doi:10.1016/j.acra.2023.02.027

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。