学习纵向胸部X光分析的方向性语义转变
Learning Directional Semantic Transitions for Longitudinal Chest X-ray Analysis
AI总结：
提出ProTrans框架，将疾病进展建模为配对CXR研究间的方向性语义转变，利用放射学报告和可学习进展特征图显式编码语义变化，通过反向时间建模和双向重建一致性实现方向感知，在纵向下游任务中优于现有方法。
摘要：
胸部X光（CXR）解读通常需要纵向比较以评估疾病进展。现有方法通常依赖于时间特征融合或研究间差异建模，但在捕捉细微进展语义方面仍有限，且忽视了疾病轨迹固有的方向性。本文提出ProTrans，一种新颖的视觉-语言预训练框架，将疾病进展建模为配对CXR研究间的方向性语义转变。ProTrans利用放射学报告将单个CXR表示锚定到可解释的疾病状态，并引入可学习的进展特征图以显式编码状态间的语义转变，与报告导出的进展描述对齐。为强制方向感知，ProTrans结合了反向时间建模过程，并在状态和转变间施加双向重建一致性，从而解耦方向语义并促进连贯的轨迹建模。在纵向下游任务（包括疾病进展分类和进展描述）上的大量实验表明，ProTrans始终优于现有方法，为纵向CXR理解建立了统一的预训练框架。https://github.com/RPIDIAL/ProTrans
英文摘要：
Chest X-ray (CXR) interpretation often requires longitudinal comparison to assess disease progression. Existing approaches typically rely on temporal feature fusion or inter-study discrepancy modeling, yet remain limited in capturing subtle progression semantics and overlook the inherently directional nature of disease trajectories. In this paper, we propose ProTrans, a novel vision-language pretraining framework that formulates disease progression as a directional semantic transition between paired CXR studies. ProTrans leverages radiology reports to anchor individual CXR representations within interpretable disease states, and introduces a learnable progression feature map to explicitly encode semantic shifts between states, aligned with report-derived progression descriptions. To enforce direction-aware perception, ProTrans incorporates a reversed temporal modeling process and imposes bidirectional reconstruction consistency across states and transitions, thereby disentangling directional semantics and promoting coherent trajectory modeling. Extensive experiments on longitudinal downstream tasks, including disease progression classification and progression captioning, demonstrate that ProTrans consistently outperforms existing methods, establishing a unified pretraining framework for longitudinal CXR understanding. https://github.com/RPIDIAL/ProTrans
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。
