文献速递腹部技术与安全CTMRUS

AI影像检测肝细胞癌:系统综述与荟萃分析

Deep learning and machine learning in image-based hepatocellular carcinoma detection: a systematic review and meta-analysis.
PubMed 文献 · Abdom Radiol (NY) · 2026-06-30

AI合并敏感度87%、特异度91%、AUC 0.95,人类医生敏感度78%、特异度91%、AUC 0.91。结果显示AI具有较高诊断效能,数值上优于人类医生,但异质性较高。

要点

  • AI检测肝细胞癌的合并敏感度87%、特异度91%、AUC 0.95
  • AI在敏感度和AUC上数值高于人类医生的78%和0.91
  • AI在US、CT、MRI及不同算法亚组均表现高诊断效能

核心结论

  • AI算法在影像检测肝细胞癌中具有高诊断准确性,数值上可能优于人类医生
  • 仍需更多前瞻性研究、严格外部验证和更大样本量进一步证实

研究设计与样本

  • 系统综述与荟萃分析,检索PubMed、Embase、Cochrane、Web of Science、IEEE Xplore共5个数据库
  • 纳入研究覆盖US、CT、MRI三种影像模态,AI方法含深度学习与机器学习
  • 按分类任务类型、验证类型、算法方法、影像模态进行亚组分析

诊断标准与关键数值

  • AI检测肝细胞癌的合并敏感度87%(95% CI 84-90%)、特异度91%(95% CI 89-93%)、AUC 0.95(95% CI 0.92-0.96)
  • 人类医生检测肝细胞癌的合并敏感度78%(95% CI 73-83%)、特异度91%(95% CI 86-94%)、AUC 0.91(95% CI 0.88-0.93)
  • 亚组分析显示AI在不同影像模态(US、CT、MRI)中均保持高诊断效能

临床应用与阅片要点

  • AI在敏感度上较人类医生高9个百分点,可作为肝细胞癌影像检测的辅助筛查工具
  • AI在CT、MRI、US多模态场景下均有较高诊断效能,适用于不同临床影像流程
  • 注意AI与人类医生特异度均为91%,AI主要改善检测敏感度而非降低假阳性

局限性

  • 整体及各亚组内存在显著异质性,且未明确异质性来源
  • 缺乏严格外部验证的研究证据,AI模型泛化性仍存疑
  • 纳入研究样本量普遍偏小,需更大规模前瞻性研究进一步验证

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: Early detection and management are essential in hepatocellular carcinoma (HCC) care. Artificial intelligence (AI) is enhancing the precision and efficiency of diagnostic imaging for liver tumor assessment.

OBJECTIVE: This study aimed to characterize the diagnostic performance of AI algorithms for detecting HCC via systematic review and meta-analysis.

METHODS: A systematic literature search was conducted in PubMed, Embase, Cochrane, Web of Science, and IEEE Xplore Digital Library in November 2024 to identify studies evaluating AI algorithms for detecting HCC. Diagnostic performance data from the included studies were pooled via meta-analysis and compared against human clinicians (11 studies). Subgroup analyses were conducted based on classification task (binary classification tasks (BCTs) vs. multi-class classification tasks (MCCTs)), validation type, algorithmic approach (deep learning (DL) vs. machine learning (ML)), and imaging modality (ultrasound (US), computed tomography (CT), or magnetic resonance imaging (MRI)).

RESULTS: Forty-one studies evaluating AI-based diagnostic models were included. The pooled sensitivity (SEN), specificity (SPC), and area under the curve (AUC) were 87% (95% CI 84-90%), 91% (95% CI 89-93%), and 0.95 (95% CI 0.92-0.96). In comparison, 11 studies assessing human clinicians yielded a pooled SEN, SPC, and AUC of 78% (95% CI 73-83%), 91% (95% CI 86-94%), and 0.91 (95% CI 0.88-0.93). These findings indicated that AI algorithms were related to high diagnostic accuracy and exhibited numerically higher performance metrics than human clinicians. Among the encompassed studies, 31 addressed BCTs and ten addressed MCCTs. Subgroup analyses across validation type, algorithmic approach, and imaging modality consistently demonstrated high diagnostic performance for AI. However, substantial heterogeneity was observed overall and within subgroups, with no clear source identified.

CONCLUSIONS: AI algorithms are associated with high diagnostic accuracy for image-based detection of HCC, potentially surpassing human performance. However, additional prospective investigations with rigorous external validation and larger sample sizes are still necessary to detect HCC in medical imaging (MI).

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Wang, Bai, Wang, et al. Deep learning and machine learning in image-based hepatocellular carcinoma detection: a systematic review and meta-analysis. Abdom Radiol (NY). 2026. PMID: 42377542. doi:10.1007/s00261-026-05627-6

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。