用多模态深度学习区分脑胶质瘤放疗后复发与假性增强，准确率92%。
Multimodal classification of Radiation-Induced Contrast Enhancements and tumor recurrence using deep learning
- 融合动态MRI与放疗剂量图的3D深度学习模型
- 独立测试集F1达0.92，关键依赖放疗地图
- 可解释性强，适合神经肿瘤临床决策支持
术后脑胶质瘤患者中，区分肿瘤复发与放疗引起的对比增强仍是重大临床挑战。现有方法或依赖临床数据稀疏的弥散MRI，或未考虑日益受关注的放疗地图。本文提出RICE-NET，一种融合纵向MRI与放疗剂量分布的多模态3D深度学习模型，仅使用常规T1加权MRI数据实现自动病灶分类。在92例患者的队列中，模型在独立测试集上F1得分为0.92。通过大量消融实验量化各时间点与模态贡献，表明可靠分类主要依赖放疗地图。基于遮挡的可解释性分析进一步证实模型聚焦于临床相关区域。结果表明，多模态深度学习有望提升神经肿瘤诊断准确性并辅助临床决策。
原文摘要 · Abstract (English)
The differentiation between tumor recurrence and radiation-induced contrast enhancements in post-treatment glioblastoma patients remains a major clinical challenge. Existing approaches rely on clinically sparsely available diffusion MRI or do not consider radiation maps, which are gaining increasing interest in the tumor board for this differentiation. We introduce RICE-NET, a multimodal 3D deep learning model that integrates longitudinal MRI data with radiotherapy dose distributions for automated lesion classification using conventional T1-weighted MRI data. Using a cohort of 92 patients, the model achieved an F1 score of 0.92 on an independent test set. During extensive ablation experiments, we quantified the contribution of each timepoint and modality and showed that reliable classification largely depends on the radiation map. Occlusion-based interpretability analyses further confirmed the model's focus on clinically relevant regions. These findings highlight the potential of multimodal deep learning to enhance diagnostic accuracy and support clinical decision-making in neuro-oncology.
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。