RadJEPA：基于联合嵌入预测架构的胸部X光放射学编码器
RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture
AI总结：
提出RadJEPA，一种无需语言监督的自监督框架，通过联合嵌入预测架构在约84万张无标签胸部X光图像上预训练，学习预测掩码区域的潜在表示，在放射学报告生成等任务中达到或超越现有基线。
摘要：
视觉-语言预训练推动了医学图像表示学习的最新进展，但这种范式受限于配对图像-文本数据的可用性以及临床叙述的报告偏差。我们探究是否可以在没有任何语言监督的情况下学习具有竞争力的放射学编码器。我们引入了RadJEPA，这是一个基于联合嵌入预测架构的自监督框架，并在约84万张无标签胸部X光图像上进行了预训练。该模型学习从可见上下文区域预测掩码目标区域的潜在表示，这一目标与图像-文本对比预训练和DINO风格自蒸馏不同，它显式地建模表示空间中的条件结构。我们主要在冻结的Vicuna-7B解码器上进行放射学报告生成评估，并将其编码器替换到四个广泛使用的视觉-语言骨干网络（MedLLaVA、Qwen-2.5、BLIP-2和Phi-4）中。为完整性，我们还报告了疾病分类和语义分割结果。在两个数据集和四个指标上，RadJEPA匹配或超过了最强的纯图像和视觉-语言基线，同时使用ViT-B/14骨干网络和224×224分辨率。
英文摘要：
Vision-language pretraining has driven progress in medical image representation learning, but it depends on paired image-text data and can inherit reporting bias from clinical narratives. We study whether language-free predictive pretraining can produce an image encoder that transfers effectively to radiology report generation. RadJEPA is a chest-X-ray adaptation of I-JEPA, pretrained on approximately 840K unlabeled radiographs using latent context-to-target prediction. Our primary contribution is an extensive empirical evaluation of this language-free encoder for report generation: the frozen image encoder is coupled to a trainable two-layer projector and language decoder, and is also substituted into four established vision-language backbones. Across MIMIC-CXR and IU-Xray, RadJEPA matches or exceeds the evaluated image-only and image-text baselines on lexical, entity-relation, and clinical-label metrics. Controlled MIMIC-only comparisons provide evidence that the predictive objective contributes beyond domain-specific pretraining, while broader comparisons also reflect differences in pretraining data, model capacity, and input resolution. Complementary classification and segmentation experiments assess transfer beyond report generation.
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。
