文献速递脑血管病

基于深度学习的自动TICI评分:一项及时的验证性研究

Deep Learning-Based Automated Thrombolysis in Cerebral Infarction Scoring: A Timely Proof-of-Principle Study.
PubMed 文献 · Stroke · 2021-09-09

本研究针对大脑中动脉M1段闭塞,开发深度学习系统自动进行改良TICI评分,并与专家评分比较。内部数据集上Cohen's kappa为0.61,外部数据集为0.52,模型更新后升至0.65,与已发表的专家间评分一致性(约0.6)相当。

要点

  • 深度学习自动TICI评分与专家评分的一致性达到已发表专家间变异范围。
  • 内部数据集Cohen's kappa为0.61,外部数据集为0.52,更新后为0.65。
  • 该方法有望为多中心研究提供客观的机械取栓结局评估。

核心结论

  • 深度学习与专家基于改良TICI评分的一致性处于已发表的临床专家间观察者变异范围内,表明自动TICI评分具有潜力。

研究设计与样本

  • 研究包含两个独立数据集:内部数据集含491个数字减影血管造影序列和236例M1闭塞患者的改良TICI评分,用于训练和初步评估;外部独立数据集含95个数字减影血管造影序列,用于测试模型泛化能力。

主要发现

  • 内部数据集上,深度学习系统与专家评分的Cohen's kappa为0.61,总体准确率为71%,特定一致性为63%至84%。
  • 外部数据集上,模型未更新时Cohen's kappa为0.52,总体准确率为64%,特定一致性为43%至87%。
  • 模型更新后,外部数据集上Cohen's kappa升至0.65,总体准确率为74%,特定一致性为60%至90%。
  • 文献中专家间TICI评分一致性的Cohen's kappa值约为0.6。

临床怎么用

  • 深度学习自动TICI评分可作为客观评估机械取栓成功与否的辅助工具,减少观察者依赖性。

局限性

  • 研究聚焦于M1段闭塞,结论可能不适用于其他血管闭塞部位。
  • 外部数据集上模型未更新时一致性略低,需模型更新后提升。

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)。

原文

BACKGROUND AND PURPOSE: Mechanical thrombectomy is an established procedure for treatment of acute ischemic stroke. Mechanical thrombectomy success is commonly assessed by the Thrombolysis in Cerebral Infarction (TICI) score, assigned by visual inspection of X-ray digital subtraction angiography data. However, expert-based TICI scoring is highly observer-dependent. This represents a major obstacle for mechanical thrombectomy outcome comparison in, for instance, multicentric clinical studies. Focusing on occlusions of the M1 segment of the middle cerebral artery, the present study aimed to develop a deep learning (DL) solution to automated and, therefore, objective TICI scoring, to evaluate the agreement of DL- and expert-based scoring, and to compare corresponding numbers to published scoring variability of clinical experts. METHODS: The study comprises 2 independent datasets. For DL system training and initial evaluation, an in-house dataset of 491 digital subtraction angiography series and modified TICI scores of 236 patients with M1 occlusions was collected. To test the model generalization capability, an independent external dataset with 95 digital subtraction angiography series was analyzed. Characteristics of the DL system were modeling TICI scoring as ordinal regression, explicit consideration of the temporal image information, integration of physiological knowledge, and modeling of inherent TICI scoring uncertainties. RESULTS: For the in-house dataset, the DL system yields Cohen’s kappa, overall accuracy, and specific agreement values of 0.61, 71%, and 63% to 84%, respectively, compared with the gold standard: the expert rating. Values slightly drop to 0.52/64%/43% to 87% when the model is, without changes, applied to the external dataset. After model updating, they increase to 0.65/74%/60% to 90%. Literature Cohen’s kappa values for expert-based TICI scoring agreement are in the order of 0.6. CONCLUSIONS: The agreement of DL- and expert-based modified TICI scores in the range of published interobserver variability of clinical experts highlights the potential of the proposed DL solution to automated TICI scoring.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Nielsen M, Waldmann M, Frölich AM, et al. Deep Learning-Based Automated Thrombolysis in Cerebral Infarction Scoring: A Timely Proof-of-Principle Study. Stroke. 2021. PMID: 34496622. doi:10.1161/STROKEAHA.120.033807

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。