Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing

by   Shruthi Bannur, et al.

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.


page 4

page 5

page 14

page 15

page 16

page 20


Making the Most of Text Semantics to Improve Biomedical Vision–Language Processing

Multi-modal data abounds in biomedicine, such as radiology images and re...

Self-Supervised MultiModal Versatile Networks

Videos are a rich source of multi-modal supervision. In this work, we le...

Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting

Self-supervised learning has gained prominence due to its efficacy at le...

MoMo: A shared encoder Model for text, image and multi-Modal representations

We propose a self-supervised shared encoder model that achieves strong r...

3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment

3D vision-language grounding (3D-VL) is an emerging field that aims to c...

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

In this paper, we consider the problem of enhancing self-supervised visu...

ELVIS: Empowering Locality of Vision Language Pre-training with Intra-modal Similarity

Deep learning has shown great potential in assisting radiologists in rea...

Please sign up or login with your details

Forgot password? Click here to reset