pith. sign in

arxiv: 2204.09817 · v4 · pith:V5VOWTROnew · submitted 2022-04-21 · 💻 cs.CV · cs.CL

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

classification 💻 cs.CV cs.CL
keywords languagemodellingvision--languagebiomedicalprocessingradiologysemanticstext
0
0 comments X
read the original abstract

Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision--language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision--language processing. We release a language model that achieves state-of-the-art results in radiology natural language inference through its improved vocabulary and novel language pretraining objective leveraging semantics and discourse characteristics in radiology reports. Further, we propose a self-supervised joint vision--language approach with a focus on better text modelling. It establishes new state of the art results on a wide range of publicly available benchmarks, in part by leveraging our new domain-specific language model. We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision--language processing. A broad evaluation, including on this new dataset, shows that our contrastive learning approach, aided by textual-semantic modelling, outperforms prior methods in segmentation tasks, despite only using a global-alignment objective.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts

    cs.CV 2026-05 unverdicted novelty 7.0

    MedSyn2 generates controllable high-resolution 3D CT volumes using optional text prompts and partial semantic segmentation masks via a modified diffusion transformer with gated attention.

  2. BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation

    cs.CV 2026-05 unverdicted novelty 5.0

    BiomedAP improves robustness of biomedical VLMs to prompt variations using gated cross-modal fusion and dual-anchor constraints, outperforming baselines on 11 benchmarks.