Whole-Body MRI Classification via Prompt-Based Clinical Conditioning

2026-08-31

AI Summary

本文提出TACTIC模型，通过提示条件下的视觉特征学习整合全身MRI和临床数据，解决传统方法中临床变量缺失的问题，提高疾病诊断性能。

Abstract

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

Problem

• Whole-Body MRI
• Clinical Variables
• Incomplete Data
• Multimodal Fusion
• Disease Diagnosis

Innovation

• Prompt-based multimodal framework
• Conditional visual feature learning
• Flexible handling of missing data
• Whole-body MRI classification