Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images. This does not only introduce poor alignment between the modalities but also a missed opportunity to exploit rich self-supervision through existing temporal content in the data. In this work, we explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model. It is designed to be versatile to arising challenges such as pose variations and missing input images across time. The resulting model excels on downstream tasks both in single- and multi-image setups, achieving state-of-the-art performance on (I) progression classification, (II) phrase grounding, and (III) report generation, whilst offering consistent improvements on disease classification and sentence-similarity tasks. We release a novel multi-modal temporal benchmark dataset, MS-CXR-T, to quantify the quality of vision-language representations in terms of temporal semantics. Our experimental results show the advantages of incorporating prior images and reports to make most use of the data.

翻译：自监督学习在视觉语言处理中利用了图像与文本模态之间的语义对齐。以往的生物医学VLP研究主要依赖单张图像与报告对的对齐，尽管临床记录通常涉及既往图像。这不仅导致模态间的对齐不佳，还错失了利用数据中现有时间内容进行丰富自监督学习的机会。在本工作中，我们明确考虑训练和微调过程中可用的既往图像与报告。我们的方法名为BioViL-T，采用CNN-Transformer混合多图像编码器，与文本模型联合训练。该方法设计灵活，可应对时间维度上的姿态变化和输入图像缺失等挑战。所得到的模型在单图像和多图像设置下的下游任务中均表现出色，在（I）进展分类、（II）短语定位和（III）报告生成上达到最先进性能，同时在疾病分类和句子相似度任务上持续改进。我们发布了一个新颖的多模态时间基准数据集MS-CXR-T，以量化视觉语言表示在时间语义方面的质量。实验结果表明，整合既往图像与报告能够最大化数据利用的优势。