The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Open accessAbstract
The development of decision support systems for pathology and their deployment in clinical practice have been hindered by the need for large manually annotated datasets. To overcome this problem, we present a multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations. We evaluated this framework at scale on a dataset of 44,732 whole slide images from 15,187 patients without any form of data curation. Tests on prostate cancer, basal cell carcinoma and breast cancer metastases to axillary lymph nodes resulted in areas under the curve above 0.98 for all cancer types. Its clinical application would allow pathologists to exclude 65-75% of slides while retaining 100% sensitivity. Our results show that this system has the ability to train accurate classification models at unprecedented scale, laying the foundation for the deployment of computational decision support systems in clinical practice.
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
“Prognostic and risk stratification systems estimate outcomes such as mortality, deterioration, readmission, or complications, supporting early intervention and clinical prioritisation [15,33].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [33]
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
“Large-scale experiments have shown that, although dependent on the tissue type and specific task, at least 10,000 WSIs are necessary for clinical-grade classification performance (Campanella et al, 2019), which is very difficult to achieve for rare diseases, such as MF.”
From Deep Learning–Based Classification of Early-Stage Mycosis Fungoides and Benign Inflammatory Dermatoses on H&E-Stained Whole-Slide Images: A Retrospective, Proof-of-Concept Study (2025) · cites this paper as Campanella et al, 2019
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
“However, most importantly, the performance of DL-based models significantly improves with increasing numbers of patients included in the training dataset.”
From Deep Learning–Based Classification of Early-Stage Mycosis Fungoides and Benign Inflammatory Dermatoses on H&E-Stained Whole-Slide Images: A Retrospective, Proof-of-Concept Study (2025) · cites this paper as Campanella et al, 2019
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
“AI and machine learning techniques are indispensable for handling the high-dimensional data generated by digital pathology, multi-omics analyses, and clinical information [23].”
From A perspective on integrating digital pathology, proteomics, clinical data and AI analytics in cancer research (2025) · cites this paper as [23]
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
“Digital pathology systems analyse whole-slide images to detect tumours and grade malignancies with reported high sensitivity in selected study settings [33,16].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [33]
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
“Paige.ai has received breakthrough status from FDA for an AI-based algorithm that is capable of diagnose cancer in computational histopathology with great accuracy, allowing pathologist to gain time to focus on important slides (44).”
From Artificial Intelligence in Medicine: Today and Tomorrow (2020) · cites this paper as [44]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Advances in artificial intelligence (AI) are driving a revolution across science, enabling exciting new results across chemistry,80–82 biology,83,84 and medicine.85–88”
From Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review (2021) · cites this paper as [86]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Forecasting capabilities enable planning for seasonal demand, public health emergencies, and fluctuations in elective procedures [33].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [33]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“AI is also used to automate radiotherapy contouring and optimise dose distribution, improving consistency in treatment delivery [33,36].”
From Artificial Intelligence in Clinical Decision-Making: A Comprehensive Review of Diagnostic, Prognostic, and Therapeutic Applications, Validation Gaps, Bias, and Deployment Challenges (2026) · cites this paper as [33]
Experimental — accuracy not yet measuredIn the citing paper
“However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles.”
From Swarm learning for decentralized artificial intelligence in cancer histopathology (2022) · cites this paper as [19]
In the citing paper
“Previous work has shown that when the sample size is increased to approximately 10,000 patients, classifier performance will increase 19,20 .”
From Swarm learning for decentralized artificial intelligence in cancer histopathology (2022) · cites this paper as [19]
In the citing paper
“Using multiple-instance learning14,49,55 with labels at the level of groups of slides has enabled clinically relevant diagnostics by scaling to training datasets on the order of 10,000 WSIs10–14.”
From A foundation model for clinical-grade computational pathology and rare cancers detection (2024) · cites this paper as [14]
In the citing paper
“Campanella et al. (2019) train a weakly supervised segmentation model for whole slide histopathology images using only slide-level labels.”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Campanella et al. (2019)
In the citing paper
“They achieve a 1% increase in AUC when using the RNN classifier over just using the MIL approach directly.”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Campanella et al. (2019)
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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
Wickham, H. (2016) · Use R! · doi:10.1007/978-3-319-24277-4 · Cited by 34,218
(2008) · Journal of Machine Learning Research · Cited by 33,051
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649
Siegel, R. L., Miller, K. D., & Jemal, A. (2016) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21332 · Cited by 16,003
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Research works printed but not linked: 3
- Ball, C. S. The early history of the compound microscope. Bios 37, 51–60 (1966).
- Hajdu, S. I. Microscopic contributions of pioneer pathologists. Ann. Clin. Lab. Sci. 41, 201–206 (2011).
- LeBoit, P. E. et al. Pathology and Genetics of Skin Tumours (IARC Press, 2006).
Cited by
Sorted by citations
Items 101–111 of 111
Fair Machine Learning in Healthcare: A Survey
Feng, Q., Du, M., Zou, N., & Hu, X. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3361836 · Cited by 12
Guedes, J., Woldmar, N., Szasz, A. M., Wieslander, E., Pawłowski, K., Horvatovich, P., Malm, J., Szadai, L., Németh, I. B., Marko-Varga, G., et al. (2025) · Journal of Proteomics · doi:10.1016/j.jprot.2025.105493 · Cited by 16
Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images
Liu, Y., He, Q., Duan, H., Shi, H., Han, A., & He, Y. (2022) · Sensors · doi:10.3390/s22166053 · Cited by 10
Integrating context for superior cancer prognosis
Jaume, G., Song, A. H., & Mahmood, F. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00924-z · Cited by 8
Xie, C., Vanderbilt, C., Feng, C., Ho, D., Campanella, G., Egger, J., Plodkowski, A., Girshman, J., Sawan, P., Arbour, K., et al. (2022) · doi:10.21203/rs.3.rs-1251762/v1 · Cited by 8
Self-citationCross-Attention-Based Saliency Inference for Predicting Cancer Metastasis on Whole Slide Images
Su, Z., Rezapour, M., Sajjad, U., Niu, S., Gurcan, M. N., & Niazi, M. K. K. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3439499 · Cited by 10
Doeleman, T., Brussee, S., Hondelink, L. M., Westerbeek, D. W. F., Sequeira, A. M., Valkema, P. A., Jansen, P. M., He, J., Vermeer, M. H., Quint, K. D., et al. (2025) · Journal of Investigative Dermatology · doi:10.1016/j.jid.2024.07.036 · Cited by 7
Current Pathology Foundation Models are unrobust to Medical Center Differences
de Jong, E. D., Marcus, E., & Teuwen, J. (2025) · arXiv · doi:10.48550/arxiv.2501.18055 · Cited by 7
Li, X., Yu, X., Tian, D., Liu, Y., & Li, D. (2023) · Medical Physics · doi:10.1002/mp.16748 · Cited by 6
The role of multimodality in clinical disease diagnosis: advances, challenges, and opportunities
Nawaz, A., Edinat, A., Rana, M. R. R., Ali, T., Mustafa, G., Tahir, S., & Lee, S. W. (2026) · Frontiers in public health · doi:10.3389/fpubh.2026.1788454 · Cited by 3
Patil, S. S., Jha, G. K., Mohsin, N., Patel, P., Ralte, L., & Shukla, A. K. (2026) · Cureus · doi:10.7759/cureus.109905
“Prognostic and risk stratification systems estimate outcomes such as mortality, deterioration, readmission, or complications, supporting early intervention and clinical prioritisation [15,33].”
Influential
Metadata
- Authors
- 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.
- Affiliations
- Memorial Sloan Kettering Cancer Center (US)
- Corresponding author
- Fuchs, Thomas J.
- ORCID
- Venue
- Nature Medicine
- Published
- 2019-07-15
- Volume
- 25
- Issue
- 8
- Pages
- 1301-1309
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- PMC
- PMC7418463
- OpenAlex
- W2956228567
- Cited by
- 2,799
- References
- 44
- Citations by year
- 2026: 585 · 2025: 457 · 2024: 435 · 2023: 400 · 2022: 366 · 2021: 304 · 2020: 216 · 2019: 29
- FWCI
- 104.81
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Nature Medicine (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Cancer Institute (P30CA008748)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- computational pathology, weakly supervised learning, multiple instance learning, whole slide images, cancer diagnosis, prostate cancer, basal cell carcinoma, breast cancer metastasis, axillary lymph nodes, decision support system, annotation-free training, clinical implementation
- MeSH terms
- Deep Learning, Breast Neoplasms, Carcinoma, Basal Cell, Basal Cell Carcinoma, Female, Humans, Male, Prostatic Neoplasms, Decision Support Systems, Clinical, Neoplasm Grading
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
