The DOI matches its Crossref record; 79 of the 80 references it cites were found in a registry or an index.
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Open accessAbstract
Self-supervised learning in vision-language processing (VLP) 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 (SOTA) 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Comparison to previous imaging studies is crucial for tracking the development of disease or impact of treatment, and references to prior studies are frequent in radiology reporting. 16,17”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [17]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Such references can be removed to reduce hallucinations when prior studies are not available, 9,14,18 or used in conjunction with prior images to enable descriptions of change.17,19,20”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“Comparison to previous imaging studies is crucial for tracking the development of disease or impact of treatment, and references to prior studies are frequent in radiology reporting. 16,17”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“It is not possible to quantitatively compare to models trained to generate other sections, such as Impression 17 or both Findings and Impression together.15,58”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“It is not possible to quantitatively compare to models trained to generate other sections, such as Impression 17 or both Findings and Impression together.15,58”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [58]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Empirically, in the MIMIC-CXR dataset, when the Comparison section is equivalent to 'No comparison available', references to prior studies are rarely observed, in contrast to the background rate of 40% in the full MIMIC-CXR dataset.17”
From MAIRA-2: Grounded Radiology Report Generation (2024) · cites this paper as [17]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., & Stanley, H. E. (2000) · Circulation · doi:10.1161/01.cir.101.23.e215 · Cited by 14,809
Layer NormalizationPreprint
Ba, J., Kiros, J., & Hinton, G. E. (2016) · arXiv.org · doi:10.48550/arxiv.1607.06450 · Cited by 13,762
Research works printed but not linked: 6
- brown, 2020, Language models are few-shot learners Advances in neural information processing systems, 33, 1877
- boecking, 2022, MS-CXR: Making the most of text semantics to improve biomedical vision-language processing (version 0.1), PhysioNet
- 2020, American College of Radiology (ACR), ACR practice guideline for communication of diagnostic imaging findings
- johnson, 2019, MIMIC-CXR database (version 2 0 0) PhysioNet
- wu, 2021, Chest imagenome dataset (version 1.0.0), PhysioNet
- endo, 2021, Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model, Machine Learning for Health, 209
Cited by
Sorted by citations
Advances in medical image analysis with vision Transformers: A comprehensive review
Azad, R., Kazerouni, A., Heidari, M., Aghdam, E. K., Molaei, A., Jia, Y., Jose, A., Roy, R., & Merhof, D. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.103000 · Cited by 557
Towards Generalist Biomedical AI
Tu, T., Azizi, S., Driess, D., Schaekermann, M., Amin, M., Chang, P.-C., Carroll, A., Lau, C., Tanno, R., Ktena, I., et al. (2024) · NEJM AI · doi:10.1056/aioa2300138 · Cited by 483
The current and future state of AI interpretation of medical images
Rajpurkar, P., & Lungren, M. P. (2023) · New England Journal of Medicine · doi:10.1056/nejmra2301725 · Cited by 443
Self-citationVision-language models for medical report generation and visual question answering: a review
Hartsock, I., & Rasool, G. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1430984 · Cited by 298
Collaboration between clinicians and vision–language models in radiology report generation
Tanno, R., Barrett, D. G. T., Sellergren, A., Ghaisas, S., Dathathri, S., See, A., Welbl, J., Lau, C., Tu, T., Azizi, S., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03302-1 · Cited by 186
Metadata
- Authors
- Bannur, S., Hyland, S., Liu, Q., Pérez-García, F., Ilse, M., Castro, D. C., Boecking, B., Sharma, H., Bouzid, K., Thieme, A., Schwaighofer, A., Wetscherek, M., Lungren, M. P., Nori, A., Alvarez-Valle, J., & Oktay, O.
- Affiliations
- Microsoft (United States) (US)
- Microsoft Health Futures
- ORCID
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 15016-15027
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075916
- Cited by
- 227
- References
- 80
- Citations by year
- 2026: 93 · 2025: 85 · 2024: 40 · 2023: 9
- FWCI
- 24.28
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- temporal structure, self-supervised learning, clinical reports, phrase grounding, report generation, chest radiography
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
