用提示学习融合影像与临床数据，提升全身MRI诊断准确率
Whole-Body MRI Classification via Prompt-Based Clinical Conditioning
- 将临床变量转为提示，动态整合影像与不完整病历
- 5个疾病任务中均优于纯影像模型，缺失数据下仍稳定
- 适合医疗多模态分析，尤其临床信息不全场景
将全身磁共振成像（WB-MRI）与临床变量结合，有望通过互补患者信息提升系统性疾病诊断能力。然而，结构化临床变量常缺失或不完整，限制了传统多模态融合方法的应用，后者通常假设输入固定。本文提出TACTIC（Tabular-Attribute Conditioned Transformer for Image Classification），一种基于提示的多模态框架，通过条件视觉特征学习融合WB-MRI与结构化临床数据。通过将临床属性编码为提示，TACTIC可支持任意数量的表格输入，并自然处理缺失数据，无需插补或固定输入结构。我们在五个涵盖系统性和肿瘤学应用的WB-MRI分类任务上评估TACTIC，包括糖尿病、慢性阻塞性肺病（COPD）、乳腺癌、前列腺癌和转移瘤诊断。在所有任务中，当临床信息可用时，TACTIC性能持续优于仅使用图像的基线模型，且在表格输入不完整时仍保持强预测能力。结果表明，基于提示的模型是利用临床背景改进WB-MRI分析的一种灵活有效方法。模型权重与代码已公开于https://github.com/lauradaza/TACTIC。
原文摘要 · Abstract (English)
Combining whole-body magnetic resonance imaging (WB-MRI) with clinical variables has the potential to improve systemic disease diagnosis by leveraging complementary sources of patient information. However, structured clinical variables are often incomplete or missing, limiting the applicability of conventional multimodal fusion methods that assume fixed inputs. In this work, we propose TACTIC (Tabular-Attribute Conditioned Transformer for Image Classification), a prompt-based multimodal framework that integrates WB-MRI and structured clinical data through conditional visual feature learning. By encoding clinical attributes as prompts, TACTIC supports an arbitrary number of tabular inputs and naturally handles missing data without requiring imputation or fixed input structures. We evaluate TACTIC on five WB-MRI classification tasks spanning systemic and oncologic applications, including diabetes, chronic obstructive pulmonary disease (COPD), breast cancer, prostate cancer, and metastasis diagnosis. Across all tasks, TACTIC consistently improves performance over image-only baselines when clinical information is available while maintaining strong predictive capability under incomplete tabular inputs. Our results demonstrate the effectiveness of prompt-based models as a flexible approach for improving WB-MRI analysis using clinical context. The model weights and code are available at https://github.com/lauradaza/TACTIC
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。