文献速递神经技术与安全MR

基于磁共振T1图像的颅内动脉瘤自动分割与检测深度学习框架

A deep learning framework for intracranial aneurysms automatic segmentation and detection on magnetic resonance T1 images.
PubMed 文献 · Eur Radiol · 2023-10-16

本研究基于136例患者159个颅内动脉瘤的T1图像构建深度学习框架,用于动脉瘤自动分割与检测。模型整体Dice为0.802,动脉瘤水平检测敏感度达90.63%,每例假阳性0.58个;作者认为该框架可行且稳健,较基于DSA、CTA和MRA的方法有更多临床应用机会。

要点

  • 在临床常规T1序列上即可自动分割和检测颅内动脉瘤,无需依赖血管造影图像。
  • 动脉瘤水平检测敏感度为90.63%,每例假阳性0.58个。
  • 模型分割体积与专家标注体积高度一致。

核心结论

  • 该深度学习框架在颅内动脉瘤分割与检测上可行且稳健,较基于DSA、CTA和MRA的方法有更多临床应用机会。

研究设计与样本

  • 回顾性诊断研究,纳入136例患者的159个颅内动脉瘤,均行T1图像检查;随机选取127例用于训练和验证,32例用于评估算法的准确性和一致性。

诊断标准与关键数值

  • 模型整体Dice为0.802,体素水平敏感度0.874、特异度0.9998、平衡准确度0.937、F1分数0.802;模型预测动脉瘤与真实标注重合度大于0.7判为真阳性,动脉瘤检测敏感度达90.63%,每例假阳性0.58个。

临床应用与阅片要点

  • 作者认为该框架稳健并具有应用于临床环境的潜力,可提高隐匿性颅内动脉瘤的检出并实现早期识别。

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: To design a deep learning-based framework for automatic segmentation and detection of intracranial aneurysms (IAs) on magnetic resonance T1 images and test the robustness and performance of framework.

METHODS: A retrospective diagnostic study was conducted based on 159 IAs from 136 patients who underwent the T1 images. Among them, 127 cases were randomly selected for training and validation, and 32 cases were used to assess the accuracy and consistency of our algorithm. We developed and assembled three convolutional neural networks for the segmentation and detection of IAs. The segmentation and detection performance of the model were compared with the ground truth, and various metrics were calculated at the voxel level, IAs level, and patient level to show the performance of our framework.

RESULTS: Our assembled model achieved overall Dice, voxel-level sensitivity, specificity, balanced accuracy, and F1 score of 0.802, 0.874, 0.9998, 0.937, and 0.802, respectively. A coincidence greater than 0.7 between the aneurysms predicted by the model and the ground truth was considered as a true positive. For IAs detection, the sensitivity reached 90.63% with 0.58 false positives per case. The volume of IAs segmented by our model showed a high agreement and consistency with the volume of IAs labeled by experts.

CONCLUSION: The deep learning framework is achievable and robust for IAs segmentation and detection. Our model offers more clinical application opportunities compared to digital subtraction angiography (DSA)-based, CTA-based, and MRA-based methods.

CLINICAL RELEVANCE STATEMENT: Our deep learning framework effectively detects and segments intracranial aneurysms using clinical routine T1 sequences, showing remarkable effectiveness and offering great potential for improving the detection of latent intracranial aneurysms and enabling early identification.

KEY POINTS: •There is no segmentation method based on clinical routine T1 images. Our study shows that the proper deep learning framework can effectively localize the intracranial aneurysms. •The T1-based segmentation and detection method is more universal than other angiography-based detection methods, which can potentially reduce missed diagnoses caused by the absence of angiography images. •The deep learning framework is robust and has the potential to be applied in a clinical setting.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Qu J, Niu H, Li Y, et al. A deep learning framework for intracranial aneurysms automatic segmentation and detection on magnetic resonance T1 images. Eur Radiol. 2023. PMID: 37843574. doi:10.1007/s00330-023-10295-x

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。