用CT影像和临床数据预测胃肠道间质瘤对伊马替尼的反应，效果优于单一数据源。
Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study
- 融合影像与临床数据的交叉注意力模型，提升预测准确性。
- 内部验证AUC达0.99，外部测试仍保持0.60-0.63，具备临床潜力。
- 可解释性分析揭示关键影响因素，适合肿瘤精准治疗研究者参考。
背景：胃肠道间质瘤（GIST）对新辅助伊马替尼的反应差异大，现有临床或分子标志物难以可靠预测。本研究开发并评估了一种可解释的多模态深度学习框架，整合计算机断层扫描（CT）影像与临床变量以预测治疗反应。方法：从四家三甲医院回顾性纳入2000–2023年患者，分为预训练队列（n=935）与预测队列（n=213）。构建结合临床变量与肿瘤中心化CT影像的交叉注意力框架，评估两种训练策略：（1）低秩适配的自监督预训练；（2）从零开始训练。超参数通过SMAC3优化，性能通过内部交叉验证与外部测试评估。消融分析与基于注意力的解释用于量化模态贡献。结果：213例患者中54.5%为应答者，应答者肿瘤更大（112 vs. 89 mm，P=0.026），有丝分裂指数更高（3 vs. 0，P<0.001），KIT突变更常见（69.0% vs. 56.7%，P=0.019）。交叉注意力模型在内部验证中表现最佳（AUC最高达0.99），但外部表现较弱（AUC 0.60–0.63）。仅临床数据表现中等（AUC 0.66），仅影像模型泛化能力差（AUC 0.56–0.66）。可解释性分析显示应答者与非应答者在特征重要性上存在显著差异，包括CD117、BRAF、PDGFRA、年龄、性别、疾病状态及合并症（FDR校正后P≤0.036）。结论：交叉注意力框架在提升伊马替尼反应预测方面具有潜力，并可提供多模态决定因素的可解释洞察。
原文摘要 · Abstract (English)
Background: Response to neoadjuvant imatinib in gastrointestinal stromal tumors (GISTs) is highly variable and cannot be reliably predicted using current clinical or molecular markers. This study developed and evaluated an explainable multimodal deep learning framework integrating computed tomography (CT) imaging and clinical variables to predict treatment response. Methods: Patients from four tertiary centers were retrospectively included between 2000-2023 in independent pretraining (n=935) and prediction (n=213) cohorts. A cross-attention framework integrating clinical variables and tumor-centered CT imaging was developed to predict response to neoadjuvant imatinib. Two training strategies were evaluated: (1) self-supervised pretraining with low-rank adaptation and (2) training from scratch. Hyperparameters were optimized using SMAC3. Performance was assessed through internal cross-validation and external testing. Ablation analyses and attention-based explanations were used to quantify modality contributions. Results: Among 213 patients (54.5% responders), responders had larger tumors (112 vs. 89 mm, P=0.026), higher mitotic index (3 vs. 0, P<0.001), and more frequent KIT mutations (69.0% vs. 56.7%, P=0.019). Cross-attention models achieved the highest internal performance (AUC up to 0.99) but lower external performance (AUC 0.60-0.63). Clinical-only performance was moderate (AUC 0.66), whereas imaging-only models showed limited generalizability (AUC 0.56-0.66). Explainability analyses identified significant differences in feature importance between responders and non-responders, including CD117, BRAF, PDGFRA, age, sex, disease status, and comorbidities (FDR-adjusted P<=0.036). Conclusion: The cross-attention framework shows potential for improving imatinib response prediction in GIST while providing interpretable insights into multimodal determinants of treatment response.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。