PO.BCS02.04 · 生物信息与计算
基于基础模型、利用完整未经筛选的EGD图像序列进行胃癌分期
Foundation model-based gastric cancer staging from complete, uncurated EGD image sequences
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
背景：组织病理学评估仍是胃癌分期的金标准，但造成显著的治疗瓶颈。虽然基于AI从内镜图像预测病理结局展现出前景，现有方法依赖人工选择的图像，引入了选择偏倚，并遗漏了临床决策所必需的病例级背景信息。我们提出GastroFM，一种基于视觉Transformer的基础模型，从完整的食管胃十二指肠镜（EGD）图像序列中学习，实现与临床实践相契合的病例级预测。
方法：GastroFM采用改进的DINOv3框架，在三星医疗中心（2019-2023年）13,515例经病理确认的EGD病例的约500,000张图像上进行预训练。随后我们使用基于注意力的多示例学习（AbMIL）对预训练模型进行微调以用于胃癌分期，该方法将未经筛选、可变长度的图像序列（每个病例1至105张图像）聚合为病例级预测。我们采用75%/10%/15%的训练-验证-测试划分（8,121例胃癌病例），在多个粒度上评估该模型的胃癌分期能力：(1) 早期胃癌（EGC）vs. 进展期胃癌（AGC），(2) 四分类T分期（T1-T4），以及(3) 淋巴结转移（N0 vs. ≥N1）。
结果：在测试集上，GastroFM取得：AGC分类的AUC 0.93（准确率0.91），大幅超越专家内镜评估（在我们的队列中准确率为76.8%）；四分类T分期的AUC 0.84（总体准确率0.67）；以及淋巴结转移预测的AUC 0.85（准确率0.87）。
结论：与依赖人工选择图像的传统方法不同，GastroFM分析完整、未经筛选的图像序列，提供与临床实践工作流相契合的病例级预测。仍需与现有基础模型进行进一步比较研究以及大规模外部验证，以充分确立其在多样化环境中的优越性和临床效用。
查看英文原文 English abstract
Background: Histopathologic assessment remains the gold standard for gastric cancer staging but creates significant treatment bottlenecks. While AI-based prediction of pathologic outcomes from endoscopic images shows promise, existing approaches rely on manually selected images, introducing selection bias and missing the case-level context essential for clinical decisions. We present GastroFM, a vision transformer-based foundation model that learns from complete esophagogastroduodenoscopy (EGD) image sequences, enabling case-level predictions aligned with clinical practice.
Methods: GastroFM is pretrained using a modified DINOv3 framework on approximately 500,000 images from 13,515 pathology-confirmed EGD cases at Samsung Medical Center (2019-2023). We then fine-tuned the pretrained model for gastric cancer staging using Attention-based Multiple Instance Learning (AbMIL), which aggregates uncurated, variable-length image sequences (1 to 105 images per case) into case-level predictions. We evaluated the model on gastric cancer staging at multiple granularities using a 75%/10%/15% train-validation-test split (8,121 cases with gastric cancer): (1) early gastric cancer (EGC) vs. advanced gastric cancer (AGC), (2) four-class T-stage (T1-T4), and (3) lymph node metastasis (N0 vs. ≥N1).
Results: On the test set, GastroFM achieved: AUC 0.93 (accuracy 0.91) for AGC classification, substantially exceeding expert endoscopic assessment (76.8% accuracy in our cohort); AUC 0.84 (overall accuracy 0.67) for 4-class T-stage classification; and AUC 0.85 (accuracy 0.87) for lymph node metastasis prediction.
Conclusion: Unlike conventional approaches that rely on manually selected images, GastroFM analyzes complete, uncurated image sequences, providing case-level predictions aligned with clinical practice workflows. Further comparative studies with existing foundation models and large-scale external validation are necessary to fully establish its superiority and clinical utility in diverse settings.
利益披露 Disclosure
S. Kim, None..
H. Yoo, None..
Y. Min, None..
H. Lee, None.