文献速递神经技术与安全CT

深度学习对脑出血、脑室内扩展及周围水肿的自动分割与体积测量显示出良好可靠性

Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema.
PubMed 文献 · Eur Radiol · 2021-01-06

研究基于no-new-Net深度学习模型,在380例原发性脑出血患者CT上评估自动分割与体积测量脑出血(ICH)、脑室内扩展(IVH)及血肿周围水肿(PHE)的性能。测试队列中ICH、IVH、PHE的Dice分数分别为0.92、0.79、0.71,手动与自动测量体积的CCC分别≥0.98、≥0.98、≥0.92,每例分析约需15秒。

要点

  • ICH分割Dice 0.92、敏感度0.93,IVH Dice 0.79、敏感度0.88,PHE Dice 0.71、敏感度0.81。
  • 手动与自动体积测量一致性:ICH和IVH的CCC≥0.98,PHE的CCC≥0.92。
  • 模型每例自动分割与体积分析约需15秒,可减少医生计算体积的工作量和时间。

核心结论

  • 模型对原发性ICH的ICH、IVH和PHE自动分割与体积测量显示出良好可靠性,可帮助减少医生计算体积的工作量和时间。

研究设计与样本

  • 研究纳入380例入院时行CT的原发性ICH患者,分为训练队列300例和验证队列80例,另用80例独立队列进行测试。
  • 参考标准为放射科医生手动生成的分割掩膜,模型性能通过比较模型结果与放射科医生分割来评估。

诊断标准与关键数值

  • 测试队列中,ICH、IVH、PHE的Dice分数分别为0.92、0.79、0.71。
  • 测试队列中,ICH、IVH、PHE的敏感度分别为0.93、0.88、0.81。
  • 测试队列中,ICH、IVH、PHE的阳性预测值分别为0.92、0.76、0.69。
  • 手动与自动测量体积之间,ICH和IVH的CCC≥0.98,PHE的CCC≥0.92。

临床应用与阅片要点

  • 原文结论指出该模型可帮助减少医生分割和计算原发性ICH患者ICH、IVH和PHE体积的工作量和时间。

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 evaluate for the first time the performance of a deep learning method based on no-new-Net for fully automated segmentation and volumetric measurements of intracerebral hemorrhage (ICH), intraventricular extension of intracerebral hemorrhage (IVH), and perihematomal edema (PHE) in primary ICH on CT.

METHODS: Three hundred and eighty primary ICH patients who underwent CT at hospital arrival were divided into a training cohort (n = 300) and a validation cohort (n = 80). An independent cohort with 80 patients was used for testing. Ground truth (segmentation masks) was manually generated by radiologists. Model performance on lesion segmentation and volumetric measurement of ICH, IVH, and PHE were evaluated by comparing the model results with the segmentations performed by radiologists.

RESULTS: In the test cohort, the Dice scores of lesion segmentation were 0.92, 0.79, and 0.71 for ICH, IVH, and PHE, respectively. The sensitivities were 0.93 for ICH, 0.88 for IVH, and 0.81 for PHE. The positive predictive values were 0.92, 0.76, and 0.69 for ICH, IVH, and PHE, respectively. Excellent concordance (concordance correlation coefficients [CCCs] ≥ 0.98) of ICH and IVH and good concordance of PHE (CCCs ≥ 0.92) were demonstrated between manually and automatically measured volumes. The model took approximately 15 s to provide automatic segmentation and volume analysis for each patient.

CONCLUSION: Our model demonstrates good reliability for automatic segmentation and volume measurement of ICH, IVH, and PHE in primary ICH, which can be useful to reduce the effort and time of doctors to calculate volumes of ICH, IVH, and PHE.

KEY POINTS: • Deep learning algorithms can provide automatic and reliable assessment of intracerebral hemorrhage, intraventricular hemorrhage, and perihematomal edema on CT. • Non-contrast CT-based deep learning method can be helpful to provide efficient and accurate measurements of ICH, IVH, and PHE in primary ICH patients, thereby reducing the effort and time of doctors to segment and calculate volumes of ICH, IVH, and PHE in primary ICH patients.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Zhao X, Chen K, Wu G, et al. Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema. Eur Radiol. 2021. PMID: 33409788. doi:10.1007/s00330-020-07558-2

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。