文献速递神经MR

深度学习在急性卒中中评估组织风险与缺血核心

Tissue at Risk and Ischemic Core Estimation Using Deep Learning in Acute Stroke.
PubMed 文献 · AJNR Am J Neuroradiol · 2021-03-25

研究基于3项多中心试验的237例急性缺血性卒中患者,训练注意力门控卷积神经网络,以入院MRI预测最终梗死。预训练策略在预测组织风险和缺血核心方面Dice系数最高,优于独立训练和传统阈值法。

要点

  • 预训练策略预测组织风险中位Dice系数0.60,缺血核心0.57,均优于其他方法。
  • 独立训练与阈值法在组织风险和核心预测上Dice系数均较低。
  • 深度学习模型结合微调可提升组织风险与缺血核心的预测性能。

核心结论

  • 带有微调的深度学习模型能更好地预测组织风险和缺血核心,性能优于传统阈值法。

研究设计与样本

  • 研究纳入3项多中心试验的237例急性缺血性卒中患者,根据4至24小时随访MRI将再灌注状态分为最小(≤20%)、部分(20%-80%)、主要(≥80%)和未知四组。
  • 使用注意力门控卷积神经网络,以入院影像为输入、最终梗死为金标准,探索独立训练、预训练和阈值法三种策略。

诊断标准与关键数值

  • 以Dice分数(中位数及四分位距)评估模型:预训练策略组织风险0.60(0.43-0.70)、核心0.57(0.30-0.69);独立训练组织风险0.55(0.41-0.69)、核心0.49(0.35-0.66);阈值法组织风险0.56(0.42-0.65)、核心0.46(0.16-0.54)。
  • 预训练策略与独立训练比较:组织风险P=0.01,核心P=0.04;与阈值法比较:组织风险P=0.008,核心P<0.001。
  • 分组样本量:最小再灌注52例,主要再灌注80例,部分再灌注57例,未知再灌注48例。

临床应用与阅片要点

  • 深度学习模型结合微调可能有助于基于入院MRI预测组织风险和缺血核心,性能优于传统阈值法。
  • 预训练策略在整体预测性能上表现最佳。

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: In acute stroke patients with large vessel occlusions, it would be helpful to be able to predict the difference in the size and location of the final infarct based on the outcome of reperfusion therapy. Our aim was to demonstrate the value of deep learning-based tissue at risk and ischemic core estimation. We trained deep learning models using a baseline MR image in 3 multicenter trials.

MATERIALS AND METHODS: Patients with acute ischemic stroke from 3 multicenter trials were identified and grouped into minimal (≤20%), partial (20%-80%), and major (≥80%) reperfusion status based on 4- to 24-hour follow-up MR imaging if available or into unknown status if not. Attention-gated convolutional neural networks were trained with admission imaging as input and the final infarct as ground truth. We explored 3 approaches: 1) separate: train 2 independent models with patients with minimal and major reperfusion; 2) pretraining: develop a single model using patients with partial and unknown reperfusion, then fine-tune it to create 2 separate models for minimal and major reperfusion; and 3) thresholding: use the current clinical method relying on apparent diffusion coefficient and time-to-maximum of the residue function maps. Models were evaluated using area under the curve, the Dice score coefficient, and lesion volume difference.

RESULTS: Two hundred thirty-seven patients were included (minimal, major, partial, and unknown reperfusion: n = 52, 80, 57, and 48, respectively). The pretraining approach achieved the highest median Dice score coefficient (tissue at risk = 0.60, interquartile range, 0.43-0.70; core = 0.57, interquartile range, 0.30-0.69). This was higher than the separate approach (tissue at risk = 0.55; interquartile range, 0.41-0.69; P = .01; core = 0.49; interquartile range, 0.35-0.66; P = .04) or thresholding (tissue at risk = 0.56; interquartile range, 0.42-0.65; P = .008; core = 0.46; interquartile range, 0.16-0.54; P < .001).

CONCLUSIONS: Deep learning models with fine-tuning lead to better performance for predicting tissue at risk and ischemic core, outperforming conventional thresholding methods.

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

引用

  1. Yu Y, Xie Y, Thamm T, et al. Tissue at Risk and Ischemic Core Estimation Using Deep Learning in Acute Stroke. AJNR Am J Neuroradiol. 2021. PMID: 33766823. doi:10.3174/ajnr.A7081

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。