文献速递神经CT

基于自监督学习自动检测脑出血患者的黑洞征

Automated Detection of the Black Hole Sign for Patients with Intracerebral Hemorrhage Using Self-Supervised Learning.
PubMed 文献 · AJNR Am J Neuroradiol · 2025-11-03

模型在扫描层面的AUC为0.75至0.89、F1分数为0.60至0.70,外部数据集扫描层面AUC最高0.85、F1分数最高0.60,但在样本异质性更大的数据集上表现较差。

要点

  • 自监督预训练模型在扫描层面识别黑洞征AUC为0.75至0.89、F1分数为0.60至0.70。
  • 外部数据集扫描层面AUC最高0.85、F1分数最高0.60,但异质性大的数据集表现较差。
  • 将外部数据部分纳入微调可减轻异质性带来的负面影响。

核心结论

  • 该框架将自监督学习整合进医学图像分类,预训练头颅CT编码器模型有望减少人工标注,微调后在识别黑洞征以预测血肿扩大这一下游任务上表现有前景,尤其适用于数据有限场景。

关键影像表现/征象

  • 模型在非增强CT上自动识别黑洞征,扫描层面AUC为0.75至0.89、F1分数为0.60至0.70。
  • 外部数据集扫描层面AUC最高0.85、F1分数最高0.60,但在样本异质性更大的另一数据集上表现较差。
  • 将外部数据集部分纳入微调后,异质性带来的负面影响可被减轻。

诊断标准与关键数值

  • 黑洞征识别性能以扫描层面和切片层面的AUC与F1分数评估,扫描层面AUC为0.75至0.89、F1分数为0.60至0.70。
  • 外部验证扫描层面AUC最高0.85、F1分数最高0.60。

临床应用与阅片要点

  • 作者认为该预训练头颅CT编码器模型有望减少人工标注,从而显著降低人力、时间和成本。
  • 作者认为微调后该框架在识别黑洞征以预测血肿扩大方面表现有前景,尤其适用于数据有限场景。

局限性

  • 模型在样本异质性更大的另一数据集上表现较差。

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: Intracerebral hemorrhage is a devastating form of stroke. Hematoma expansion (HE), growth of the hematoma on interval scans, predicts death and disability. Accurate prediction of HE is crucial for targeted interventions to improve patient outcomes. The black hole sign (BHS) on noncontrast CT scans is a predictive marker for HE. An automated method to recognize the BHS and predict HE could speed precise patient selection for treatment.

MATERIALS AND METHODS: In this article, we present a novel framework leveraging self-supervised learning (SSL) techniques for BHS identification on head CT images. A ResNet-50 encoder model was pretrained on more than 1.7 million unlabeled head CT images. Layers for binary classification were added on top of the pretrained model. The resulting model was fine-tuned using the training data and evaluated on the held out test set to collect area under the curve (AUC) and F1 scores. The evaluations were performed on scan and slice levels. We ran different panels, one using 2 multicenter data sets for external validation and one including parts of them in the pretraining.

RESULTS: Our model demonstrated strong performance in identifying the BHS compared with the baseline model. Specifically, the model achieved scan-level AUC scores between 0.75 and 0.89 and F1 scores between 0.60 and 0.70. Furthermore, it exhibited robustness and generalizability across an external data set, achieving a scan-level AUC score of up to 0.85 and an F1 score of up to 0.60, while it performed worse on another data set with more heterogeneous samples. The negative effects could be mitigated after including parts of the external data sets in the fine-tuning process.

CONCLUSIONS: This study introduced a novel framework integrating SSL into medical image classification, particularly on BHS identification from head CT scans. The resulting pretrained head CT encoder model showed the potential to minimize manual annotation, which would significantly reduce labor, time, and costs. After fine-tuning, the framework demonstrated a promising performance for a specific downstream task, identifying the BHS to predict HE on comprehensive evaluation on diverse data sets. This approach holds promise for enhancing medical image analysis, particularly in scenarios with limited data availability.

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

引用

  1. Wang H, Schwirtlich T, Houskamp E, et al. Automated Detection of the Black Hole Sign for Patients with Intracerebral Hemorrhage Using Self-Supervised Learning. AJNR Am J Neuroradiol. 2025. PMID: 40335283. doi:10.3174/ajnr.A8826

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。