时间倒置用于学习胸部X光片的区间变化
Temporal Inversion for Learning Interval Change in Chest X-Rays
AI总结：
本文提出TILA框架，通过时间倒置增强模型对时间变化的敏感性，改进了胸部X光片的区间变化检测与分类。
摘要：
最近的视觉-语言预训练进展使医疗基础模型变得强大，但大多数分析放射图像时孤立处理，忽略了关键的临床任务：比较前后图像以评估区间变化。对于胸部X光片（CXRs），捕捉区间变化至关重要，因为放射科医生不仅要评估发现的静态外观，还要评估其随时间的变化。我们介绍了TILA（时间倒置意识学习和对齐），一个简单而有效的框架，利用时间倒置，即反转图像对，作为监督信号，以增强现有时间视觉-语言模型对方向变化的敏感性。TILA在预训练、微调和推理中整合倒置意识目标，补充了传统外观建模，显式学习时间顺序。我们还提出了一种统一的评估协议，以评估在时间倒置下的顺序敏感性和一致性，并引入了MS-CXR-Tretrieval，一个通过通用协议构建的检索评估集，可应用于任何时间CXR数据集。在公共数据集和真实世界医院队列上的实验表明，当应用于多种现有架构时，TILA在进步分类和时间嵌入对齐方面始终改进。
英文摘要：
Recent advances in vision--language pretraining have enabled strong medical foundation models, yet most analyze radiographs in isolation, overlooking the key clinical task of comparing prior and current images to assess interval change. For chest radiographs (CXRs), capturing interval change is essential, as radiologists must evaluate not only the static appearance of findings but also how they evolve over time. We introduce TILA (Temporal Inversion-aware Learning and Alignment), a simple yet effective framework that uses temporal inversion, reversing image pairs, as a supervisory signal to enhance the sensitivity of existing temporal vision-language models to directional change. TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order. We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol that can be applied to any temporal CXR dataset. Experiments on public datasets and real-world hospital cohorts demonstrate that TILA consistently improves progression classification and temporal embedding alignment when applied to multiple existing architectures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
