文献速递神经MR

卷积神经网络用于临床脑MR成像FLAIR病灶自动分割

Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging.
PubMed 文献 · AJNR Am J Neuroradiol · 2019-07-25

该研究基于U-Net架构构建3D卷积神经网络,回顾性训练295例脑MRI用于FLAIR病灶自动分割,在92例验证集上评估。验证集Dice中位数0.79,高于现有方法(Dice 0.56和0.41),接近人工分割(Dice 0.81),病灶体积预测与真实体积强相关(ρ=0.99)。

要点

  • 3D U-Net卷积神经网络在92例验证集上FLAIR病灶分割Dice中位数0.79,接近人工分割的0.81。
  • 在19种神经系统疾病中分割性能显著高于现有方法(Dice 0.56和0.41)。
  • 算法预测病灶体积与真实体积强相关(ρ=0.99),可整合进疾病负荷评估或影像报告。

核心结论

  • 源自U-Net架构的3D卷积神经网络可在多种基础病理和图像采集参数的临床脑MR成像上实现高水平的FLAIR自动分割。
  • 该方法提供准确的病灶体积数据,可整合进疾病负荷评估或影像报告。

研究设计与样本

  • 研究为回顾性训练与验证研究,网络基于U-Net卷积神经网络架构并采用3D volumes处理脑MRI。
  • 使用295例脑MRI进行回顾性训练,在92例验证病例上评估性能。
  • 以放射科医师人工分割为参考标准,采用Dice分数及体素级敏感度和特异度评价,并评估总病灶体积测量。

关键影像表现/征象

  • 对FLAIR高信号病灶进行自动分割,在较大范围病灶特征上表现准确,验证集Dice中位数0.79。
  • 在19种神经系统疾病中分割性能显著高于现有方法(Dice 0.56和0.41),并接近人工分割性能(Dice 0.81)。
  • 算法预测的病灶体积与真实病灶体积强相关(ρ=0.99)。
  • 在超过30种不同MR成像扫描仪及较大范围图像采集参数下分割均准确。

诊断标准与关键数值

  • 验证集自动FLAIR病灶分割Dice中位数0.79。
  • 在19种神经系统疾病中,本方法Dice为0.79,显著高于现有方法的0.56和0.41,并接近人工分割的0.81。
  • 病灶体积预测值与真实值相关系数ρ=0.99。

临床应用与阅片要点

  • 该算法可用于临床脑MRI的FLAIR病灶自动分割,并提供可纳入影像报告的病灶体积数据。
  • 方法在多种病理和多种扫描仪及采集参数下验证,但原文未给出具体临床使用流程或阈值建议。

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: Most brain lesions are characterized by hyperintense signal on FLAIR. We sought to develop an automated deep learning-based method for segmentation of abnormalities on FLAIR and volumetric quantification on clinical brain MRIs across many pathologic entities and scanning parameters. We evaluated the performance of the algorithm compared with manual segmentation and existing automated methods.

MATERIALS AND METHODS: We adapted a U-Net convolutional neural network architecture for brain MRIs using 3D volumes. This network was retrospectively trained on 295 brain MRIs to perform automated FLAIR lesion segmentation. Performance was evaluated on 92 validation cases using Dice scores and voxelwise sensitivity and specificity, compared with radiologists' manual segmentations. The algorithm was also evaluated on measuring total lesion volume.

RESULTS: Our model demonstrated accurate FLAIR lesion segmentation performance (median Dice score, 0.79) on the validation dataset across a large range of lesion characteristics. Across 19 neurologic diseases, performance was significantly higher than existing methods (Dice, 0.56 and 0.41) and approached human performance (Dice, 0.81). There was a strong correlation between the predictions of lesion volume of the algorithm compared with true lesion volume (ρ = 0.99). Lesion segmentations were accurate across a large range of image-acquisition parameters on >30 different MR imaging scanners.

CONCLUSIONS: A 3D convolutional neural network adapted from a U-Net architecture can achieve high automated FLAIR segmentation performance on clinical brain MR imaging across a variety of underlying pathologies and image acquisition parameters. The method provides accurate volumetric lesion data that can be incorporated into assessments of disease burden or into radiologic reports.

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

引用

  1. Duong MT, Rudie JD, Wang J, et al. Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging. AJNR Am J Neuroradiol. 2019. PMID: 31345943. doi:10.3174/ajnr.A6138

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。