文献速递神经MR

正交三维卷积神经网络堆叠泛化提升3D FLAIR白质高信号检测

A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images.
PubMed 文献 · AJNR Am J Neuroradiol · 2021-02-11

本研究提出StackGen-Net,一种基于正交3D卷积神经网络堆叠泛化的集成模型,用于3D T2-FLAIR图像中白质高信号的自动检测与分割。在独立测试队列(ADNI-3,n=20)中,StackGen-Net的Dice评分(0.76±0.08)、F1-lesion(0.74±0.13)和PR曲线下面积(0.84±0.09)显著高于现有方法,绝对体积差最低(13.3%±9.1%)。其Dice评分中位数(0.74)与两位神经放射科医师间观察者变异(中位数0.73)无显著差异(P=.22),预测病灶体积与真实标注无显著差异(P=.15)。

要点

  • StackGen-Net在3D FLAIR白质高信号分割中Dice评分0.76,与两位神经放射科医师间观察者变异(中位数0.73)无显著差异(P=.22)。
  • 模型绝对体积差为13.3%±9.1%,预测病灶体积与真实标注无显著差异(P=.15),体积定量可靠。
  • 正交平面2.5D空间上下文集成策略优于单网络及平均/多数投票等传统集成方法。

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: Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images.

MATERIALS AND METHODS: Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer's Disease Neuroimaging Initiative-3 (n = 20).

RESULTS: StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations.

CONCLUSIONS: A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

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

引用

  1. Umapathy L, Perez-Carrillo GG, Keerthivasan MB, et al. A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images. AJNR Am J Neuroradiol. 2021. PMID: 33574101. doi:10.3174/ajnr.A6970

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。