The DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
A visual-language foundation model for computational pathology
Open accessAbstract
The accelerated adoption of digital pathology and advances in deep learning have enabled the development of robust models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain, and a model’s usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text and, notably, over 1.17 million image–caption pairs through task-agnostic pretraining. Evaluated on a suite of 14 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving histopathology images and/or text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, and text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning. Developed using diverse sources of histopathology images, biomedical text and over 1.17 million image–caption pairs, evaluated on a suite of 14 diverse benchmarks, a visual-language foundation model achieves state-of-the-art performance on a wide array of clinically relevant pathology tasks.
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
“Similarly, given a diagnostically challenging WSI, retrieving a similar WSI via slide search5,46–53 or pathology reports through cross-modal report search10,54–56 typically requires specialized algorithms to bridge the gap between fine-grained patch embeddings and slide-level information, introducing hurdles to clinical adoption.”
From A multimodal whole-slide foundation model for pathology (2025) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The choice of CONCHv1.5 for feature extraction was due to the fact that the model was pretrained on histology regions with diverse stains and tissue types, including FFPE, frozen tissue and IHC, thereby yielding region features that are robust against diverse tissue processing protocols.”
From A multimodal whole-slide foundation model for pathology (2025) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“By increasing the patch size from the widely used 256 × 256 pixels, we effectively reduce the sequence length by four without impacting the representation quality due to higher resolution patch input, leveraging the robustness of the patch-level foundation models in generalizing to higher resolutions9,10,87.”
From A multimodal whole-slide foundation model for pathology (2025) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“enabling it to create effective representations for non–H&E (hematoxylin and eosin)-stained images, such as immunohistochemistry and special stains, without relying on large public histology slide collections such as The Cancer Genome Atlas, Pancreatic Cancer AI Platform, and Genotype-Tissue Expression.”
From Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook. (2024) · cites this paper as [141]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“CONCH is a vision-language M-LLM specifically designed for computational histopathology.”
From Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook. (2024) · cites this paper as [141]
Experimental — accuracy not yet measured
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
“To overcome these limitations, several research groups have alternatively proposed the use of weakly-supervised deep learning models, which can be trained to perform various downstream computational pathology tasks such as tumor subtyping and prognosis32–37 without any region or pixel-level annotations.”
From Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images (2024) · cites this paper as [34]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Following the success of previous studies10, we use CoCa95, a state-of-the-art visual-language foundation model pretraining method, for both stages of vision-language alignment.”
From A multimodal whole-slide foundation model for pathology (2025) · cites this paper as [10]
The cited source says what the claim attributes to it.
In the citing paper
“Contrastive vision language models in pathology, such as PLIP12 and CONCH13, align text and images at the patch-level.”
From Generating dermatopathology reports from gigapixel whole slide images with HistoGPT (2025) · cites this paper as [13]
The cited source says what the claim attributes to it.
In the citing paper
“They are zero-shot learners, i.e., they can solve downstream tasks for which they have not been trained (e.g., cancer subtyping).”
From Generating dermatopathology reports from gigapixel whole slide images with HistoGPT (2025) · cites this paper as [13]
The cited source says what the claim attributes to it.
In the citing paper
“It is pretrained on the largest histopathology-specific vision-language data set”
From Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook. (2024) · cites this paper as [141]
The cited source says what the claim attributes to it.
In the citing paper
“PLIP [194] and CONCH [195] were pretrained on paired pathology images and text descriptions using contrastive learning methods.”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [195]
In the citing paper
“Several studies have developed visual–language foundation models using paired histopathology images and captions11,12.”
From A visual–omics foundation model to bridge histopathology with spatial transcriptomics (2025) · cites this paper as [11]
In the citing paper
“Existing dual-modality foundation models in computational biology11,12 primarily combine images with textual descriptions, proving their utility in histopathology annotation and analysis.”
From A visual–omics foundation model to bridge histopathology with spatial transcriptomics (2025) · cites this paper as [11]
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
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
Measures of the Amount of Ecologic Association Between Species
Dice, L. R. (1945) · Ecology · doi:10.2307/1932409 · Cited by 12,187
Learning to Prompt for Vision-Language Models
Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01653-1 · Cited by 3,304
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293
Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyö, D., Moreira, A. L., Razavian, N., & Tsirigos, A. (2018) · Nature Medicine · doi:10.1038/s41591-018-0177-5 · Cited by 2,930
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019) · Nature Medicine · doi:10.1038/s41591-019-0508-1 · Cited by 2,799
Data-efficient and weakly supervised computational pathology on whole-slide images
Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Chen, R. J., Barbieri, M., & Mahmood, F. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00682-w · Cited by 2,282
Self-citation
Research works printed but not linked: 13
- Li, J., Li, D., Xiong, C. & Hoi, S. BLIP: bootstrapping language–image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning (eds Chaudhur, K. et al.) 12888–12900 (PMLR, 2022).
- Maleki, D. & Tizhoosh, H. R. LILE: look in-depth before looking elsewhere—a dual attention network using transformers for cross-modal information retrieval in histopathology archives. In International Conference on Medical Imaging with Deep Learning (eds Konukoglu, E. et al.) 879–894 (PMLR, 2022).
- Zhang, Y., Jiang, H., Miura, Y., Manning, C. D. & Langlotz, C. P. Contrastive learning of medical visual representations from paired images and text. In Machine Learning for Healthcare Conference (eds Lipton, Z. et al.) 2–25 (PMLR, 2022).
- Tsuneki, M. & Kanavati, F. Inference of captions from histopathological patches. In International Conference on Medical Imaging with Deep Learning (eds Konukoglu, E. et al.) 1235–1250 (PMLR, 2022).
- Zhang, R., Weber, C., Grossman, R. & Khan, A. A. Evaluating and interpreting caption prediction for histopathology images. In Machine Learning for Healthcare Conference (eds Doshi-Velez, F. et al.) 418–435 (PMLR, 2020).
- Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. In International Conference on Machine Learning (eds Dy, J. & Krause, A.) 2127–2136 (PMLR, 2018).
- Perez, E., Kiela, D. & Cho, K. True few-shot learning with language models. Adv. Neural Inf. Process. Syst. 34, 11054–11070 (2021).
- Dosovitskiy, A. et al. An image is worth 16×16 words: transformers for image recognition at scale. In 9th International Conference on Learning Representations https://openreview.net/forum?id=YicbFdNTTy (OpenReview.net, 2021).
- Zhou, J. et al. Image BERT pre-training with online tokenizer. In 10th International Conference on Learning Representations https://openreview.net/forum?id=ydopy-e6Dg (OpenReview.net, 2022).
- Li, J., Li, D., Savarese, S. & Hoi, S. BLIP-2: bootstrapping language–image pre-training with frozen image encoders and large language models. In Proc. 40th International Conference on Machine Learning (eds Krause, A. et al.) 19730–19742 (PMLR, 2023).
- Banerjee, S. & Lavie, A. METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In Proc. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization 65–72 (Association for Computational Linguistics, 2005).
- Lin, C.-Y. ROUGE: a package for automatic evaluation of summaries. In Text Summarization Branches Out 74–81 (Association for Computational Linguistics, 2004).
- Lewis, M., Dauphin, Y. & Fan, A. Hierarchical neural story generation. In Proc. 56th Annual Meeting of the Association for Computational Linguistics (eds Gurevych, I. & Miyao, Y.) 889–898 (Association for Computational Linguistics, 2018).
Cited by
Sorted by citations
A pathology foundation model for cancer diagnosis and prognosis prediction
Wang, X., Zhao, J., Marostica, E., Yuan, W., Jin, J., Zhang, J., Li, R., Tang, H., Wang, K., Li, Y., et al. (2024) · Nature · doi:10.1038/s41586-024-07894-z · Cited by 580
The TRIPOD-LLM reporting guideline for studies using large language models
Gallifant, J., Afshar, M., Ameen, S., Aphinyanaphongs, Y., Chen, S., Cacciamani, G., Demner-Fushman, D., Dligach, D., Daneshjou, R., Fernandes, C., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03425-5 · Cited by 615
“Of note, this guideline was developed with text-only LLMs in mind; however, advances in multimodal models incorporating LLMs, such as vision-language models 47 , are now rapidly emerging — illustrating the need for rapid, nimble approaches for reporting guidelines.”
A multimodal generative AI copilot for human pathology
Lu, M. Y., Chen, B., Williamson, D. F. K., Chen, R. J., Zhao, M., Chow, A. K., Ikemura, K., Kim, A., Pouli, D., Patel, A., et al. (2024) · Nature · doi:10.1038/s41586-024-07618-3 · Cited by 461
Self-citationMultimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349
“In this section, we present a use case that demonstrates the practical application of M-LLMs in health care using the Contrastive Learning From Captions for Histopathology (CONCH) model [141].”
A Vision-Language Foundation Model for Precision Oncology
Xiang, J., Wang, X., Zhang, X., Xi, Y., Eweje, F., Chen, Y., Li, Y., Bergstrom, C., Gopaulchan, M., Kim, T., et al. (2025) · Nature · doi:10.1038/s41586-024-08378-w · Cited by 256
“A key feature of a foundation model is its ability to perform downstream tasks without further training, that is, zero-shot learning capability 15,16 .”
Influential
Metadata
- Authors
- Lu, M. Y., Chen, B., Williamson, D. F. K., Chen, R. J., Liang, I., Ding, T., Jaume, G., Odintsov, I., Le, L. P., Gerber, G., Parwani, A. V., Zhang, A., & Mahmood, F.
- Affiliations
- Broad Institute (US)
- Brigham and Women's Hospital (US)
- Harvard University (US)
- The Ohio State University Wexner Medical Center (US)
- Corresponding author
- Mahmood, Faisal
- ORCID
- Venue
- Nature Medicine
- Published
- 2024-03
- Volume
- 30
- Issue
- 3
- Pages
- 863-874
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- PMC
- PMC11384335
- OpenAlex
- W4392947532
- Semantic Scholar
- 0746410e1250576cc1b9621ef602e4bceb1c07ca
- Cited by
- 966
- References
- 79
- Citations by year
- 2026: 491 · 2025: 388 · 2024: 87
- FWCI
- 135.39
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- Locations
- Nature Medicine (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Human Genome Research Institute (T32HG002295)
- National Cancer Institute (T32CA251062)
- National Institute of General Medical Sciences (R35GM149270, R35GM138216)
- National Institute of Diabetes and Digestive and Kidney Diseases (P30DK034854)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- histopathology, digital pathology, contrastive learning, image-caption pairs, biomedical text, histology image classification, image captioning, text-to-image retrieval, image-to-text retrieval, transfer learning, limited labeled data
- MeSH terms
- Machine Learning, Humans, Language, Workflow
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
