文献速递神经MR

人工智能辅助海马分割及其对阿尔茨海默病的诊断价值:一项Meta分析

Artificial Intelligence-Assisted Hippocampal Segmentation and Its Diagnostic Value for Alzheimer's Disease: A Meta-analysis.
PubMed 文献 · Acad Radiol · 2025-05-08

该Meta分析纳入27项研究,评估AI辅助海马分割在AD和MCI中的分割准确性与诊断性能。汇总DSC在AD为0.82、MCI为0.85、正常对照为0.86;AD vs NC的敏感度0.87、特异度0.91、AUC 0.95,AD vs MCI的AUC 0.80,MCI vs NC的AUC 0.83。结论认为AI辅助海马分割准确性良好,对AD与NC的区分有前景,但AD与MCI的鉴别仍具挑战。

要点

  • AI辅助海马分割汇总DSC:AD 0.82、MCI 0.85、正常对照0.86。
  • AD vs NC诊断AUC 0.95,敏感度0.87,特异度0.91。
  • AD vs MCI的AUC 0.80,MCI vs NC的AUC 0.83。

核心结论

  • AI辅助海马分割达到良好准确性,对区分AD与正常对照显示出有前景的诊断能力,但AD与MCI的鉴别仍具挑战性。

研究设计与样本

  • 系统检索PubMed、Embase、Web of Science和Cochrane Library截至2024年12月,纳入27项使用神经影像数据评估AI海马分割与AD或MCI诊断的研究,采用随机效应模型汇总DSC、双变量混合效应模型评估诊断性能。

诊断标准与关键数值

  • 汇总DSC:AD 0.82(95% CI 0.80-0.85),MCI 0.85(95% CI 0.83-0.88),正常对照0.86(95% CI 0.84-0.88)。
  • 亚组分析左右海马DSC均为0.87。
  • AD vs NC:敏感度0.87,特异度0.91,AUC 0.95。
  • AD vs MCI:AUC 0.80;MCI vs NC:AUC 0.83。

临床应用与阅片要点

  • 作者认为AI辅助海马分割对AD与正常对照的区分有前景,但AD与MCI的鉴别仍具挑战性。
  • 作者提出未来需要应用标准化协议、外部验证和临床整合的高质量研究以提高临床实践中的可靠性。

局限性

  • 作者指出AD与MCI的鉴别仍具挑战性。
  • 作者提出未来需要应用标准化协议、外部验证和临床整合的高质量研究以提高可靠性。

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

BACKGROUND: Hippocampal atrophy is a key marker of Alzheimer's disease (AD) and mild cognitive impairment (MCI). Diverse artificial intelligence (AI) architectures for automated hippocampal segmentation have been increasingly reported in neuroimaging research. Different hippocampal automated segmentation methods can be of added value for the AD diagnostic work-up and treatment planning. This study aims to conduct a thorough meta-analysis to evaluate the segmentation accuracy and diagnostic performance of AI-assisted hippocampal segmentation in AD and MCI.

METHODS: We searched PubMed, Embase, Web of Science, and the Cochrane Library up to December 2024. Studies using neuroimaging data to assess AI algorithms for hippocampal segmentation and diagnosis in AD or MCI populations were included. Pooled segmentation accuracy was estimated using the Dice similarity coefficient (DSC) through a random-effects model, while diagnostic performance (sensitivity, specificity, and area under the curve [AUC]) was evaluated using a bivariate mixed-effects model.

RESULTS: A total of 27 studies were included. For segmentation accuracy, pooled DSC values were 0.82 (95% CI: 0.80-0.85) for AD, 0.85 (0.83-0.88) for MCI, and 0.86 (0.84-0.88) for normal controls (NC). Subgroup analyses indicated comparable performance between left and right hippocampi (both DSC: 0.87). Diagnostic meta-analysis demonstrated the highest accuracy for AD vs. NC (sensitivity: 0.87, specificity: 0.91, AUC: 0.95), but lower performance for AD vs. MCI (AUC: 0.80) and MCI vs. NC (AUC: 0.83).

CONCLUSION: AI-assisted hippocampal segmentation achieves good accuracy and demonstrates promising diagnostic capabilities for distinguishing AD from NC, though differentiation between AD and MCI remains challenging. Future high-quality research that applied standardized protocols, external validation, and clinical integration is needed to improve reliability in clinical practice.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wu Q, Huang C, Zhang J, et al. Artificial Intelligence-Assisted Hippocampal Segmentation and Its Diagnostic Value for Alzheimer's Disease: A Meta-analysis. Acad Radiol. 2025. PMID: 40340118. doi:10.1016/j.acra.2025.04.038

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。