PO.BCS02.01 · 生物信息与计算
一款基于AI的软件（PanClaudinAI）通过增强CT预测胰腺癌claudin 18.2表达的多中心前瞻性验证
A multicenter, prospective validation of an AI-based software (PanClaudinAI) for predicting claudin 18.2 expression via contrast-enhanced CT in pancreatic cancer
该海报暂无可下载的资料
AACR 官方页面
作者与单位 Authors & Affiliations
摘要 Abstract
中文摘要
背景：Claudin 18.2（CLDN18.2）是胰腺癌中一个有前景的治疗靶点。目前基于免疫组化（IHC）的评估具有侵入性，且受肿瘤异质性的限制。我们利用增强CT（CECT）开发了一个深度学习模型来预测CLDN18.2表达，并通过一款专用软件应用程序（PanClaudinAI）在多中心前瞻性队列中对其进行了验证。
方法：我们回顾性地收集了来自三个中心800例患者（A中心：n=400；B中心：n=230；C中心：n=170）的CECT图像及匹配的CLDN18.2 IHC数据。CLDN18.2阳性定义为≥75%的中至强染色。使用动脉期CT图像训练了一个视觉Transformer（ViT）模型。该模型被集成到一款用户友好的软件应用程序（PanClaudinAI）中以进行实时推理。随后我们开展了一项前瞻性多中心验证（D中心：n=100；E中心：n=120；F中心：n=140）以评估其临床实用性。
结果：CLDN18.2阳性的患病率在回顾性队列中为45.7%，在前瞻性队列中为50.2%。在回顾性训练集中，AI模型在A中心取得了0.81的AUROC（95% CI：0.76-0.86），灵敏度为78.2%，特异性为75.4%；在B中心取得了0.84的AUROC（95% CI：0.81-0.89），灵敏度为81.5%，特异性为79.3%；在C中心取得了0.86的AUROC（95% CI：0.83-0.89），灵敏度为82.7%，特异性为80.1%。在前瞻性多中心验证中，该模型在D中心保持了0.79的AUROC（95% CI：0.73-0.84），灵敏度为76.5%，特异性为74.2%；在E中心为0.78的AUROC（95% CI：0.74-0.82），灵敏度为75.8%，特异性为73.6%；在F中心为0.85的AUROC（95% CI：0.82-0.91），灵敏度为81.2%，特异性为79.0%。此外，PanClaudinAI软件展现出很高的可用性和临床工作流程集成度，每个病例的平均处理时间<2分钟。
结论：我们开发并前瞻性验证了一款稳健的基于AI的软件（PanClaudinAI），它能够跨多个中心从常规CECT图像中无创预测CLDN18.2表达。该工具有助于快速、可重复且便捷的生物标志物识别，有可能指导CLDN18.2靶向治疗的患者选择，并减少对侵入性活检的需求。
查看英文原文 English abstract
Background: Claudin 18.2 (CLDN18.2) is a promising therapeutic target in pancreatic cancer. Current immunohistochemistry (IHC)-based assessment is invasive and limited by tumor heterogeneity. We developed a deep learning model using contrast-enhanced CT (CECT) to predict CLDN18.2 expression and validated it in a multicenter prospective cohort via a dedicated software application (PanClaudinAI).
Methods: We retrospectively collected CECT images and matched CLDN18.2 IHC data from 800 patients across three centers (Center A: n=400; Center B: n=230; Center C: n=170). CLDN18.2 positivity was defined as ≥75% moderate-to-strong staining. A Vision Transformer (ViT) model was trained using arterial-phase CT images. The model was integrated into a user-friendly software application (PanClaudinAI) for real-time inference. We subsequently conducted a prospective multicenter validation (Center D: n=100; Center E: n=120; Center F: n=140) to evaluate its clinical utility.
Results: The prevalence of CLDN18.2 positivity was 45.7% in the retrospective cohort and 50.2% in the prospective cohort. The AI model achieved an AUROC of 0.81 (95% CI: 0.76-0.86) with a sensitivity of 78.2% and specificity of 75.4% in center A; an AUROC of 0.84 (95% CI: 0.81-0.89) with a sensitivity of 81.5% and specificity of 79.3% in center B; and an AUROC of 0.86 (95% CI: 0.83-0.89) with a sensitivity of 82.7% and specificity of 80.1% in center C within the retrospective training set. In the prospective multicenter validation, the model maintained an AUROC of 0.79 (95% CI: 0.73-0.84) with a sensitivity of 76.5% and specificity of 74.2% in center D; an AUROC of 0.78 (95% CI: 0.74-0.82) with a sensitivity of 75.8% and specificity of 73.6% in center E; and an AUROC of 0.85 (95% CI: 0.82-0.91) with a sensitivity of 81.2% and specificity of 79.0% in center F. Moreover, the PanClaudinAI software demonstrated high usability and integration into clinical workflow, with an average processing time of <2 minutes per case.
Conclusions: We developed and prospectively validated a robust AI-based software (PanClaudinAI) that non-invasively predicts CLDN18.2 expression from routine CECT images across multiple centers. This tool facilitates rapid, reproducible, and accessible biomarker identification, potentially guiding patient selection for CLDN18.2-targeted therapies and reducing the need for invasive biopsies.
利益披露 Disclosure
Y. Zhang, None.