文献速递泌尿生殖技术与安全US

人工智能算法在基于超声的肾结石检测、分类、预测与管理中的应用:一项系统综述

Applications of artificial intelligence algorithms in ultrasound-based kidney stone detection, classification, prediction, and management: a systematic review.
PubMed 文献 · Abdom Radiol (NY) · 2026-03-09

该系统综述遵循PRISMA指南,检索多个数据库后纳入9项研究,评估AI/深度学习在超声肾结石检测、分类、并发症/结局预测及操作引导中的表现;结果显示准确率最高达96.54%,预测AUC>0.90,但数据异质性限制荟萃分析,证据确定性低至极低。

要点

  • AI/深度学习在超声肾结石检测与分割中准确率最高达96.54%,预测模型AUC>0.90。
  • 多数研究偏倚风险低(5/9),但数据集和验证异质性限制荟萃分析。
  • 证据确定性低至极低(按GRADE),需标准化外部验证和多模态整合。

核心结论

  • AI和深度学习算法在基于超声的肾结石管理中显示出高诊断准确性和临床效用,按应用类型分层显示各项任务均表现良好,但方法学变异性和低至极低证据确定性需要标准化外部验证和多模态整合以更广泛采用。

研究设计与样本

  • 系统综述,遵循PRISMA指南(PROSPERO:CRD420251247650),检索PubMed、Embase、Scopus等数据库自建库起无语言限制,纳入9项经同行评议的原始研究,以CT或手术所见为参考标准,采用QUADAS-2及AI扩展评估质量。

诊断标准与关键数值

  • 深度学习用于图像检测/分割的研究3项,预测并发症/结局的建模研究4项,操作引导研究2项。
  • 方法学包括CNN变体和机器学习集成模型。
  • 性能指标高,准确率最高达96.54%,预测的AUC>0.90。

局限性

  • 数据集和验证的异质性限制荟萃分析。
  • 方法学变异性需要标准化外部验证和多模态整合以更广泛采用。
  • 证据确定性低至极低(按GRADE)。

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: Kidney stones are a prevalent urological condition with significant global burden, often diagnosed using ultrasound (US) as a first-line modality despite its limitations in sensitivity and operator dependency. Artificial intelligence (AI) and deep learning (DL) algorithms have shown promise in enhancing US-based kidney stone applications, including detection, classification, complication prediction, and procedural guidance, but evidence remains heterogeneous.

OBJECTIVE: To systematically review and synthesize the applications of AI and DL algorithms in US-based kidney stone detection, classification, prediction of complications/outcomes, and procedural guidance.

METHODS: This systematic review followed PRISMA guidelines (PROSPERO: CRD420251247650). Databases including PubMed, Embase, Scopus, and others were searched from inception without language restrictions. Eligible studies were original peer-reviewed articles evaluating AI/DL in US for kidney stone diagnostics against reference standards like CT or surgical findings. Two reviewers independently screened, extracted data, and assessed quality using QUADAS-2 with AI extensions.

RESULTS: From 1,285 records, 9 studies were included after exclusions. These encompassed DL for image detection/segmentation (n = 3), predictive modeling for complications/outcomes (n = 4), and procedural guidance (n = 2). Methodologies included CNN variants and ML ensembles. Performance metrics were high, with accuracies up to 96.54%, AUCs > 0.90 for predictions, and improved procedural outcomes. Risk of bias was low in most studies (5/9), with some concerns in others. Heterogeneity in datasets and validation limited meta-analysis.

CONCLUSIONS: AI and DL algorithms demonstrate high diagnostic accuracy and clinical utility in enhancing US for kidney stone management, with stratification by application type revealing high performance across tasks, addressing traditional limitations. However, methodological variability and low to very low certainty of evidence (per GRADE) necessitate standardized external validation and multimodal integration for broader adoption.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Elhaie M, Koozari A, Albeshan SM, et al. Applications of artificial intelligence algorithms in ultrasound-based kidney stone detection, classification, prediction, and management: a systematic review. Abdom Radiol (NY). 2026. PMID: 41801379. doi:10.1007/s00261-026-05419-y

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。