文献速递神经MR

基于深度学习的脑白质高信号自动分割与分类模型的开发与验证

Development and validation of a deep learning-based automatic segmentation and classification of cerebral white matter hyperintensities.
PubMed 文献 · Eur Radiol · 2025-12-15

本研究为回顾性研究,纳入2016年1月至2019年12月连续1974例认知障碍患者,开发并验证深度学习模型同步自动分割和分类脑白质高信号。分割模型在内部和外部测试集单类分割Dice分别为0.88和0.85,多类分割为0.77和0.72;Fazekas分类准确率内部脑室旁/深部为0.88/0.87,外部为0.68/0.75。作者认为模型性能高,有潜力作为定量评估白质高信号的诊断支持工具。

要点

  • 分割模型单类分割Dice内部0.88、外部0.85,多类分割内部0.77、外部0.72。
  • Fazekas分类准确率脑室旁内部0.88、外部0.68,深部内部0.87、外部0.75。
  • 分类按Fazekas量表分正常/轻度、中度、重度三类,并分别报告脑室旁和深部白质高信号。

核心结论

  • 深度学习模型在白质高信号分割和Fazekas分类上表现出较高性能,作者认为其有潜力作为定量评估白质高信号的准确诊断支持工具。

研究设计与样本

  • 回顾性研究,纳入一家三级医院2016年1月至2019年12月连续1974例认知障碍患者(平均年龄71.1±9.7岁),分割模型在448例和149例受试者上训练和调优,分类模型在1186例和394例受试者上训练和调优,分割与分类任务分别在内部测试集149例和394例及外部数据集100例受试者上测试,分割分支从五种不同模型中选出。

诊断标准与关键数值

  • Fazekas分类使用三类(正常/轻度、中度、重度),并分别报告脑室旁和深部白质高信号;UNet结合Resnet-34编码器模型在内部和外部测试集单类分割Dice分别为0.88(95%CI:0.88-0.89)和0.85(95%CI:0.84-0.86),多类分割Dice分别为0.77(95%CI:0.76-0.79)和0.72(95%CI:0.71-0.74);Fazekas分类模型准确率在内部数据集脑室旁和深部分别为0.88和0.87,在外部数据集分别为0.68和0.75。

临床应用与阅片要点

  • 分类评估由三名经验丰富的神经放射科医师对测试数据集进行评价;作者认为模型有潜力作为定量评估白质高信号的准确诊断支持工具。

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

OBJECTIVES: White matter hyperintensities (WMH) represent neuroimaging markers of cerebral small vessel disease. We aimed to develop and validate a deep learning-based simultaneous, automatic WMH segmentation and classification model in patients with cognitive impairment.

MATERIALS AND METHODS: This retrospective study included images from consecutive patients with cognitive impairment from a tertiary hospital. A segmentation model was trained and tuned on 448 and 149 subjects. A classification compartment inherited from the segmentation model, utilizing the multi-task multiple instance learning framework (MTMIL), was trained and tuned on 1186 and 394 subjects. Tests of segmentation and classification tasks were performed on 149 and 394 subjects in the internal testing dataset and 100 subjects in the external dataset. We evaluated five different models to select the segmentation branch. Classification according to the Fazekas scale used three categories (normal/mild, moderate, severe), and locations were separately reported as periventricular and deep WMH. For classification evaluation, three experienced neuroradiologists evaluated test datasets.

RESULTS: Between January 2016 and December 2019, 1974 consecutive patients (mean age 71.1 ± 9.7) were included. Dice score performance of the UNet with Resnet-34 encoder model on internal and external testing datasets was 0.88 (95% CI: 0.88-0.89) and 0.85 (95% CI: 0.84-0.86) for single-class segmentation, and 0.77 (95% CI: 0.76-0.79) and 0.72 (95% CI: 0.71-0.74) for multi-class segmentation. The accuracy of the Fazekas scale classification model was 0.88 and 0.87 at periventricular and deep WMH with internal datasets and 0.68 and 0.75 with external datasets.

CONCLUSION: These results demonstrate the high segmentation and classification performance of our models and their potential for deployment as accurate diagnostic support tools for quantified evaluation of WMH.

KEY POINTS: Question We developed a deep learning-based, simultaneous, automatic white matter hyperintensity (WMH) segmentation and classification model using data from patients with cognitive impairment. Findings Segmentation model achieved Dice scores of 0.72-0.88 for single-class and multi-class segmentation. Fazekas score classification accuracy ranged from 0.68 to 0.88 for periventricular/deep WMH. Clinical relevance Our study demonstrated high segmentation and classification performance of deep learning-based models and potential for deployment as accurate diagnostic support tools for quantified evaluation of white matter hyperintensities.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Jeong SY, Jung W, Suh CH, et al. Development and validation of a deep learning-based automatic segmentation and classification of cerebral white matter hyperintensities. Eur Radiol. 2025. PMID: 41398110. doi:10.1007/s00330-025-12174-z

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。