TALON: A Temporally Aware Longitudinal Framework for Radiology Report Generation

TALON：一种用于放射学报告生成的时序感知纵向框架

Abstract: Current radiology report generation (RRG) models usually produce descriptive reports based on a single examination or only the most recent prior examination, limiting their ability to perform accurate and meaningful longitudinal comparisons and detect subtle interval changes.

摘要： 目前的放射学报告生成（RRG）模型通常基于单次检查或仅基于最近的一次既往检查来生成描述性报告，这限制了它们进行准确且有意义的纵向比较以及检测细微间隔变化的能力。

Although recent approaches have begun to incorporate multiple prior examinations, they usually aggregate a fixed-length history without explicitly modeling the role-dependent relevance of each prior examination before fusion.

尽管近期的一些方法已开始纳入多次既往检查，但它们通常只是聚合固定长度的历史记录，而未在融合前明确建模每次既往检查的角色相关性。

To address this, we propose TALON, a Temporally Aware LONgitudinal RRG framework that adaptively integrates variable-length patient histories.

为了解决这一问题，我们提出了 TALON，这是一个时序感知的纵向 RRG 框架，能够自适应地整合变长患者历史记录。

The underlying Dual-Channel Temporal Fusion Module (DCTFM) compares the current examination with each prior examination through complementary similarity and change channels to capture persistent findings and interval changes, respectively.

其核心的双通道时序融合模块（DCTFM）通过互补的相似性通道和变化通道，将当前检查与每次既往检查进行对比，从而分别捕捉持续存在的病灶和间隔变化。

The specially designed channel-specific attention estimates the relevance of each prior examination, while a learned prior-specific gate adaptively integrates informative longitudinal evidence and suppresses redundancy.

专门设计的通道特定注意力机制（channel-specific attention）用于评估每次既往检查的相关性，而学习型的既往检查特定门控（prior-specific gate）则能自适应地整合有价值的纵向证据并抑制冗余信息。

Experiments on MIMIC-CXR show that TALON outperforms the current state-of-the-art method on various clinical efficacy and graph-based metrics.

在 MIMIC-CXR 数据集上的实验表明，TALON 在多项临床疗效指标和基于图的指标上均优于当前最先进的方法。

When more prior examinations become available, TALON’s performance on these metrics improves even further, emphasizing the strength of TALON’s DCTFM in modeling longitudinal RRG across longer and more complex patient histories than existing approaches.

当有更多既往检查可用时，TALON 在这些指标上的表现会进一步提升，这凸显了 TALON 的 DCTFM 在处理比现有方法更长、更复杂的患者历史记录时，在纵向 RRG 建模方面的优势。