仅基于H&E染色切片的AI驱动WHO 2021胶质瘤分类
本研究构建仅用H&E全切片图像进行WHO 2021成人型弥漫性胶质瘤分类的AI流程,基于多机构数据集(TCGA-GBM/TCGA-LGG n=1,320用于训练,EBRAINS n=794、IPD-Brain n=304为独立评估集)系统比较8种病理基础模型、9种聚合方法与15种放大倍数组合。最佳组合在训练队列AUC达97.95%,EBRAINS为96.30%,IPD为92.61%。作者认为直接从H&E切片判定胶质瘤诊断可省去分子检测、加快确诊与临床决策。
要点
- 仅用H&E全切片图像即可实现WHO 2021胶质瘤分类,最佳组合AUC在三个队列为97.95%、96.30%、92.61%。
- 领域特异性基础模型优于基于ImageNet的模型,多放大倍数融合可提升性能。
- 该流程有望省去分子检测、加快确诊,但需在更多机构外部验证。
核心结论
- 仅基于H&E全切片图像的AI流程可实现WHO 2021胶质瘤分类,有望省去分子检测并加快确诊与临床决策。
研究设计与样本
- 多机构数据集按WHO 2021标准重新分类:TCGA-GBM/TCGA-LGG(n=1,320)用于模型训练,并在两个留出集独立评估:EBRAINS(n=794)与IPD-Brain(n=304)。
- 每张全切片图像经预处理后,对8种病理基础模型、9种聚合方法及15种放大倍数组合(晚期融合)进行定量基准比较,并以热图进行可解释性分析。
主要发现
- 最佳基础模型、聚合方法与多放大倍数组合的AUC为:训练队列97.95%,EBRAINS(set 1)96.30%,IPD(set 2)92.61%。
- 领域特异性基础模型优于基于ImageNet的模型。
- 聚合方法与基于ImageNet的特征提取器联用时性能提升更大,而与基础模型联用时提升较小。
- 多放大倍数融合对性能有增益。
临床怎么用
- 在分子检测昂贵、耗时或需外送的情况下,可考虑以H&E切片AI分类辅助WHO 2021胶质瘤诊断并加速临床决策。
- 选用领域特异性基础模型并结合多放大倍数融合可获更优分类性能。
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: The WHO 2021 classification criteria for adult-type diffuse glioma integrate histology with molecular profiling for conclusive diagnosis. Since molecular profiling can be expensive and time-consuming, often necessitating outsourcing or leading to the "not otherwise specified (NOS) label," this study develops an AI-driven WHO 2021 classification of gliomas solely from H&E whole-slide images (WSIs). METHODS: Our pipeline is based on a multi-institutional dataset reclassified per WHO 2021 guidelines. This dataset includes (a) Primarily US-based TCGA-GBM/TCGA-LGG (n = 1,320) for model training, independently evaluated on two hold-out sets, (b) Austria-based EBRAINS (n = 794), and (c) India-based IPD-Brain (n = 304). Each WSI undergoes pre-processing followed by quantitative benchmarking across (i) eight pathology foundation models (FM), (ii) nine aggregation methods (AM), and (iii) 15 combinations of magnification levels through a late fusion approach. Model interpretability conducted through heatmaps highlights distinct, identifiable morphology features. RESULTS: Our best-performing combination of FM, AM, and multi-magnification achieved an AUC of 97.95% on the training cohort, 96.30% on EBRAINS (set 1), and 92.61% on IPD (set 2). The results yield the following key insights: (1) domain-specific FMs outperform ImageNet-based models, (2) AMs, while theoretically promising yield larger performance improvements when used with ImageNet-based feature extractor rather than FMs, and (3) Fusion of multiple magnifications adds value in performance. CONCLUSION: Determining glioma diagnosis directly from H&E slides can obviate the need for molecular profiling, expedite conclusive diagnosis, and, hence, clinical decision-making. These findings motivate the development of advanced domain-relevant FMs and the design of more adaptable slide-level aggregation techniques.
引用
- Innani S, Bell WR, Nasrallah MP, et al. AI-driven WHO 2021 classification of gliomas based only on H&E-stained slides. Neuro Oncol. 2026. PMID: 40888157. doi:10.1093/neuonc/noaf189
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。