The DOI matches its Crossref record; 186 of the 186 references it cites were found in a registry or an index.
Towards a general-purpose foundation model for computational pathology
Open accessAbstract
Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology. Pretrained using over 100,000 diagnostic histopathological slides across 20 major tissue types, a self-supervised model is shown to outperform existing baselines across various clinically relevant computational 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
“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 [9]
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
“we present Virchow, the largest foundation model for computational pathology to date.”
From A foundation model for clinical-grade computational pathology and rare cancers detection (2024) · cites this paper as [41]
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
“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 [32]
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
“UNI [191], Prov-GigaPath [192], and Virchow [193] were pretrained solely on pathology image data to perform cancer classification, diagnosis, and prognosis.”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [191]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The vision module is based on the patch encoder CTransPath17 for the small and medium models, and UNI18 for the large model.”
From Generating dermatopathology reports from gigapixel whole slide images with HistoGPT (2025) · cites this paper as [18]
The cited source says what the claim attributes to it.
In the citing paper
“We found out that the UNI foundation model32, when paired with multi-task AB-MIL, achieved the best predictive performance for the various TME signature prediction tasks.”
From Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images (2024) · cites this paper as [32]
In the citing paper
“In fact GMA is widely used to assess the performance of pathology foundation models23,25,26.”
From A clinical benchmark of public self-supervised pathology foundation models (2025) · cites this paper as [23]
In the citing paper
“Self-supervised learning has become a widely used approach for pretraining foundation models on thousands to tens of thousands of images without annotations or labels, marking an important paradigm shift in the field.20,21”
From Use of artificial intelligence for liver diseases: A survey from the EASL congress 2024 (2024) · cites this paper as [20]
In the citing paper
“An increasing number of published studies show the potential of foundation models20,24; however, they are currently underrepresented in the field of liver diseases.4”
From Use of artificial intelligence for liver diseases: A survey from the EASL congress 2024 (2024) · cites this paper as [20]
In the citing paper
“These works demonstrate that image features produced with self-supervised learning of pathology images outperform image features trained on natural images and that performance improves with scale.”
From A foundation model for clinical-grade computational pathology and rare cancers detection (2024) · cites this paper as [41]
In the citing paper
“Despite the challenges in collecting large-scale datasets in the pathology domain, recent pioneering works have utilized datasets ranging from 30,000 to 400,000 WSIs to train foundation models ranging in size from 28 million to 307 million parameters35–42”
From A foundation model for clinical-grade computational pathology and rare cancers detection (2024) · cites this paper as [41]
In the citing paper
“Built on rich knowledge representations, these models have shown impressive performance across medical fields such as ophthalmology20, radiology21 and pathology22–25.”
From A Multimodal Vision Foundation Model for Clinical Dermatology (2025) · cites this paper as [23]
In the citing paper
“Specialty-specific foundation models20,21,23 typically focus on single imaging modalities”
From A Multimodal Vision Foundation Model for Clinical Dermatology (2025) · cites this paper as [23]
In the citing paper
“The scaling behavior observed in PanDerm’s performance aligns with recent foundation model trends20,22,23,59”
From A Multimodal Vision Foundation Model for Clinical Dermatology (2025) · cites this paper as [23]
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
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Advances in neural information processing systems 7
Cios, K. J., & Shields, M. E. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,093
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
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
Research works printed but not linked: 13
- Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning, 1597–1607 (PMLR, 2020).
- Chen, R. J. & Krishnan, R. G. Self-supervised vision transformers learn visual concepts in histopathology. In Learning Meaningful Representations of Life, NeurIPS 2021 (2022).
- Dosovitskiy, A. et al. An image is worth 16×16 words: transformers for image recognition at scale. In International Conference on Learning Representations (2021).
- Xiang, J. & Zhang, J. Exploring low-rank property in multiple instance learning for whole slide image classification. In The Eleventh International Conference on Learning Representations (2022).
- Wang, X. et al. SCL-WC: cross-slide contrastive learning for weakly-supervised whole-slide image classification. Advances in Neural Information Processing Systems 35, 18009–18021 (2022).
- Zhou, J. et al. iBOT: image BERT pre-training with online tokenizer. In International Conference on Learning Representations (2022).
- Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In 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) (2018).
- Sablayrolles, A., Douze, M., Schmid, C. & Jégou, H. Spreading vectors for similarity search. In International Conference on Learning Representations (2019).
- Touvron, H., Vedaldi, A., Douze, M. & Jegou, H. Fixing the train–test resolution discrepancy. In Advances in Neural Information Processing Systems, Vol. 32 (eds Wallach, H. et al.) (Curran Associates, 2019).
- Dao, T., Fu, D. Y., Ermon, S., Rudra, A. & Ré, C. FlashAttention: fast and memory-efficient exact attention with IO-awareness. In Advances in Neural Information Processing Systems (2022).
- Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In International Conference on Learning Representations (2019).
- Sarıyıldız, M. B., Kalantidis, Y., Alahari, K. & Larlus, D. No reason for no supervision: improved generalization in supervised models. In The Eleventh International Conference on Learning Representations (2023).
- Yang, J., Chen, H., Yan, J., Chen, X. & Yao, J. Towards better understanding and better generalization of low-shot classification in histology images with contrastive learning. In International Conference on Learning Representations (2021).
Cited by
Sorted by citations
A whole-slide foundation model for digital pathology from real-world data
Xu, H., Usuyama, N., Bagga, J., Zhang, S., Rao, R., Naumann, T., Wong, C., Gero, Z., González, J., Gu, Y., et al. (2024) · Nature · doi:10.1038/s41586-024-07441-w · Cited by 921
“Existing models often treat each image tile as an independent sample and formulate slide-level modelling as multiple instance learning 4,40–43 , thus limiting their ability to model complex global patterns in gigapixel whole slides.”
A foundation model for clinical-grade computational pathology and rare cancers detection
Vorontsov, E., Bozkurt, A., Casson, A., Shaikovski, G., Zelechowski, M., Severson, K., Zimmermann, E., Hall, J., Tenenholtz, N., Fusi, N., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03141-0 · Cited by 572
“Implementations of other pretrained visual encoders benchmarked in the study were obtained from the following links: UNI (https://huggingface.co/MahmoodLab/UNI), Phikon (https://huggingface.co/owkin/phikon), DINOp=8 (https://github. com/lunit-io/benchmark-ssl-pathology), PLIP (https://huggingface.co/ vinid/plip), CTra…”
InfluentialA 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
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-citationHow to build the virtual cell with artificial intelligence: Priorities and opportunities
Bunne, C., Roohani, Y., Rosen, Y., Gupta, A., Zhang, X., Roed, M., Alexandrov, T., AlQuraishi, M., Brennan, P., Burkhardt, D. B., et al. (2024) · Cell · doi:10.1016/j.cell.2024.11.015 · Cited by 393
“145 Lastly, in live-cell imaging, CNNs are employed to track dynamic changes within cells or even single molecules over time, providing insights into cell migration, responses to treatment, or the movement and interaction of individual molecules within cells, revealing crucial biological processes…”
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
“2a and Supplementary Tables 1 and 2).”
Vision-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
A guide to artificial intelligence for cancer researchers
Pérez-López, R., Laleh, N. G., Mahmood, F., & Kather, J. N. (2024) · Nature reviews. Cancer · doi:10.1038/s41568-024-00694-7 · Cited by 227
“Cross-modality applications refer to AI systems that can process and integrate information from different data types, such as combining radiology images with clinical notes or pathology images with genomic data 98 , or generally, images and text 97 .”
InfluentialSelf-citationA review of deep learning for brain tumor analysis in MRI
Dorfner, F. J., Patel, J., Kalpathy–Cramer, J., Gerstner, E. R., & Bridge, C. P. (2025) · npj Precision Oncology · doi:10.1038/s41698-024-00789-2 · Cited by 265
“Chen et al. recently intro-ducedageneral-purposefoundationmodelforpathologythatwaspretrained onmorethan100millionimagesacquiredfromover100,000diagnostic H&E-stainedWSIsacross20differenttissuetypes 109 .”
A multimodal whole-slide foundation model for pathology
Ding, T., Wagner, S. J., Song, A. H., Chen, R. J., Lu, M. Y., Zhang, A., Vaidya, A. J., Jaume, G., Shaban, M., Kim, A., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03982-3 · Cited by 171
“…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 resolutions 9,10,87 .”
InfluentialSelf-citationLiu, Y., Dai, Y., & Wang, L. (2025) · Cancer Cell · doi:10.1016/j.ccell.2025.12.009 · Cited by 153
“Building on methods that align histological features to refine spatial units, image data from many spatial platforms can be fed into foundation models, such as UNI 80 for H&E images and KRONOS 81 for fluorescence images, to extract representative features.”
A clinical benchmark of public self-supervised pathology foundation models
Campanella, G., Chen, S., Singh, M., Verma, R., Muehlstedt, S., Zeng, J., Stock, A., Croken, M., Veremis, B., Elmas, A., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-58796-1 · Cited by 126
“Chen et al. 23 introduced UNI, a ViT-large model trained on 100,000 proprietary slides using the DINOv2 24 SSL algorithm.”
Demographic bias in misdiagnosis by computational pathology models
Vaidya, A. J., Chen, R. J., Williamson, D. F. K., Song, A. H., Jaume, G., Yang, Y., Hartvigsen, T., Dyer, E., Lu, M. Y., Lipková, J., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-02885-z · Cited by 148
Self-citationFoundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions
He, Y., Huang, F., Jiang, X., Nie, Y., Wang, M., Wang, J., & Chen, H. (2024) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2024.3496744 · Cited by 162
“UNI [121] utilizedtheDINOv2[122]paradigmandintegratedtheMIMand CLtolearnthefoundationmodelforcomputationalpathology.”
Self-citationA visual–omics foundation model to bridge histopathology with spatial transcriptomics
Chen, W., Zhang, P., Tran, T. N., Xiao, Y., Li, S., Shah, V. V., Cheng, H., Brannan, K. W., Youker, K., Lai, L., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02707-1 · Cited by 118
Foundation models for fast, label-free detection of glioma infiltration
Kondepudi, A., Pekmezci, M., Hou, X., Scotford, K., Jiang, C., Rao, A. T., Harake, E. S., Chowdury, A., Al‐Holou, W. N., Wang, L., et al. (2024) · Nature · doi:10.1038/s41586-024-08169-3 · Cited by 128
“Foundation models for medical AI have the potential to solve challenging Article clinical tasks by requiring little to no task-specific annotations to achieve good generalization performance and clinically meaningful results 17–19 .”
Analysis of 3D pathology samples using weakly supervised AI
Song, A. H., Williams, M., Williamson, D. F. K., Chow, S. S. L., Jaume, G., Gao, G., Zhang, A., Chen, B., Baras, A. S., Serafin, R. J., et al. (2024) · Cell · doi:10.1016/j.cell.2024.03.035 · Cited by 113
Self-citationThe generative era of medical AI
Fahrner, J., Chen, E., Topol, E. J., & Rajpurkar, P. (2025) · Cell · doi:10.1016/j.cell.2025.05.018 · Cited by 120
Swin-UMamba†: Adapting Mamba-Based Vision Foundation Models for Medical Image Segmentation
Liu, J., Yang, H., Zhou, H.-Y., Yu, L., Liang, Y. Q., Yu, Y., Zhang, S., Zheng, H., & Wang, S. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3508698 · Cited by 115
“Recent research has demonstrated vision foundation models [13], [14], [15], [16], [17], [18], [19], [20] can achieve remarkable performance without relying on large-scale high-quality labeled datasets for various medical tasks.”
A Multimodal Vision Foundation Model for Clinical Dermatology
Yan, S., Yu, Z., Primiero, C., Vico-Alonso, C., Wang, Z., Yang, L., Tschandl, P., Hu, M., Ju, L., Tan, G., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03747-y · Cited by 117
“Specialty-specific foundation models 20,21,23 typically focus on single imaging modalities, while general biomedical models, despite their broad scope, struggle with domain-specific data scarcity and integrating heterogeneous modalities for comprehensive clinical analysis.”
Marra, A., Morganti, S., Pareja, F. G., Campanella, G. S. V., Bibeau, F., Fuchs, T. J., Loda, M. F., Parwani, A. V., Scarpa, A., Reis-Filho, J. S., et al. (2025) · Annals of Oncology · doi:10.1016/j.annonc.2025.03.006 · Cited by 114
Yang, Z., Wei, T., Liang, Y., Yuan, X., Gao, R., Xia, Y., Zhou, J., Zhang, Y., & Yu, Z. (2025) · Nature Communications · doi:10.1038/s41467-025-57587-y · Cited by 110
“Subsequently, the foundation models are well fi ne-tuned using small labeled datasets customized for speci fi c tasks and always achieve high performance 16,17 .”
Machine learning methods for histopathological image analysis: updates in 2024
Komura, D., Ochi, M., & Ishikawa, S. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.12.033 · Cited by 76
Artificial intelligence in digital pathology — time for a reality check
Aggarwal, A., Bharadwaj, S., Corredor, G., Pathak, T. B., Badve, S., & Madabhushi, A. (2025) · Nature Reviews Clinical Oncology · doi:10.1038/s41571-025-00991-6 · Cited by 84
“The focus has progressively shifted from basic tasks, such as image classification, segmentation and detection, to more complex applications, including predicting patient prognosis and response to treatment 11,15,21,22,36 .”
Avanzo, M., Stancanello, J., Pirrone, G., Drigo, A., & Retico, A. (2024) · Cancers · doi:10.3390/cancers16213702 · Cited by 87
“ML can also assist in diagnosing conditions from clinical data, such as myocardial infarction [190,191] and in making differential diagnoses among various findings in neonatal radiographs [192].”
BackgroundA multimodal visual–language foundation model for computational ophthalmology
Shi, D., Zhang, W., Yang, J., Huang, S., Chen, X., Xu, P., Jin, K., Lin, S. C., Wei, J., Yusufu, M., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01772-2 · Cited by 129
Has multimodal learning delivered universal intelligence in healthcare? A comprehensive survey
Lin, Q., Zhu, Y., Mei, X., Huang, L., Ma, J., He, K., Peng, Z., Cambria, E., & Feng, M. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102795 · Cited by 86
Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology
Song, A. H., Chen, R. J., Ding, T., Williamson, D. F. K., Jaume, G., & Mahmood, F. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01099 · Cited by 79
“Given a WSI for subject j , we tessellate it into small non-overlapping patches We then employ a feature extractor f enc ( · ) pre-trained on large archives of histopathology images [18], to extract a representative and compressed embedding from each patch.”
BackgroundMethodSelf-citationDigital profiling of gene expression from histology images with linearized attention
Pizurica, M., Zheng, Y., Carrillo‐Pérez, F., Noor, H., Yao, W., Wohlfart, C., Vladimirova, A., Marchal, K., & Gevaert, O. (2024) · Nature Communications · doi:10.1038/s41467-024-54182-5 · Cited by 84
“In addition, we leverage UNI, a foundation model optimized for histological feature extraction 24 .”
Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75
“UNI [191], Prov-GigaPath [192], and Virchow [193] were pretrained solely on pathology image data to perform cancer classification, diagnosis, and prognosis.”
Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection
Campanella, G., Kumar, N., Nanda, S., Singi, S., Fluder, E., Kwan, R., Muehlstedt, S., Pfarr, N., Schüffler, P. J., Häggström, I., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03780-x · Cited by 69
Benchmarking foundation models as feature extractors for weakly supervised computational pathology
Neidlinger, P., El Nahhas, O. S. M., Muti, H. S., Lenz, T., Hoffmeister, M., Brenner, H., van Treeck, M., Langer, R., Dislich, B., Behrens, H. M., et al. (2025) · Nature Biomedical Engineering · doi:10.1038/s41551-025-01516-3 · Cited by 80
“In the first step, feature vectors were extracted from WSIs utilizing the foundational models evaluated in this study.”
InfluentialGrandQC: A comprehensive solution to quality control problem in digital pathology
Weng, Z., Seper, A., Pryalukhin, A., Mairinger, F. D., Wickenhauser, C., Bauer, M., Glamann, L., Bläker, H., Lingscheidt, T., Hulla, W., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-54769-y · Cited by 79
Zhao, Y. S., Xiong, S., Ren, Q., Wang, J., Li, M., Yang, L., Wu, D., Tang, K., Pan, X., Chen, F., et al. (2024) · The Lancet Oncology · doi:10.1016/s1470-2045(24)00599-0 · Cited by 70
Self-citationPantanowitz, L., Pearce, T. M., Abukhiran, I. M., Hanna, M. G., Wheeler, S., Soong, T. R., Tafti, A. P., Pantanowitz, J., Lu, M. Y., Mahmood, F., et al. (2024) · Modern Pathology · doi:10.1016/j.modpat.2024.100680 · Cited by 71
Self-citationHu, B., He, R., Pang, K., Wang, G., Wang, N., Zhu, W., Sui, X., Teng, H., Liu, T., Zhu, J., et al. (2025) · Cell · doi:10.1016/j.cell.2024.12.023 · Cited by 70
SAM-Med3D: A Vision Foundation Model for General-Purpose Segmentation on Volumetric Medical Images
Wang, H., Guo, S., Ye, J., Deng, Z., Cheng, J., Li, T., Chen, J., Su, Y., Huang, Z., Shen, Y., et al. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3586694 · Cited by 67
“…medical VFMs and the adaptation of existing natural image VFMs. Modality-specific models like RETFound [25], MIS-FM [26], SegVol [27], STU-Net [5], USFM [23], and UNI [28] have shown high generalization within their respective domains, partially mitigating the challenge of limited annotated data.”
Artificial intelligence-based biomarkers for treatment decisions in oncology
Ligero, M., Nahhas, O. S. M. E., Aldea, M. D., & Kather, J. N. (2025) · Trends in cancer · doi:10.1016/j.trecan.2024.12.001 · Cited by 74
Domain Generalization in Computational Pathology: Survey and Guidelines
Jahanifar, M., Raza, M., Xu, K., Vuong, T. T. L., Jewsbury, R., Shephard, A., Tajeddin, N. Z., Kwak, J. T., Raza, S. E. A., Minhas, F., et al. (2025) · ACM Computing Surveys · doi:10.1145/3724391 · Cited by 86
“In non-subjective tasks like survival analysis prediction, a posterior shift may indicate a prior shift or sample preparation disparities.”
Combining spatial transcriptomics with tissue morphology
Chelebian, E., Avenel, C., & Wählby, C. (2025) · Nature Communications · doi:10.1038/s41467-025-58989-8 · Cited by 81
“Rapid advancements in 2024 have led to the development of models like CONCH 86 , CTrans-Path 87 , H-optimus-0 88 , Kaiko 89 , Phikon 90 , Prov-GigaPath 91 , UNI 92 , or Virchow 93 , showcasing state-of-the-art representation learning.”
A pathologist–AI collaboration framework for enhancing diagnostic accuracies and efficiencies
Huang, Z., Yang, E., Shen, J., Gratzinger, D. A., Eyerer, F., Liang, B., Nirschl, J., Bingham, D. B., Dussaq, A., Kunder, C. A., et al. (2024) · Nature Biomedical Engineering · doi:10.1038/s41551-024-01223-5 · Cited by 65
“…(AI) and machine learning (ML) algorithms have made substantial achievements in digital pathology, enabling a variety of computer-aided diagnoses; these include cell or tissue segmentation 1,2 , image classification 3–6 , patient prognosis 7,8 , and lymph node (LN) metastasis identification 9,10 .”
A multimodal knowledge-enhanced whole-slide pathology foundation model
Xu, Y., Wang, Y., Zhou, F., Ma, J., Jin, C., Yang, S., Li, J., Zhang, Z., Zhao, C., Zhou, H., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-66220-x · Cited by 118
“In the realm of prior investigations into pathology foundation models, two prominent categories have emerged: vision-only models 2,4,46 and vision-language models 1,3 .”
InfluentialSelf-citationA Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model
Xu, Y., Wang, Y., Zhou, F., Ma, J., Jin, C., Yang, S., Li, J., Zhang, Z., Zhao, C., Zhou, H., et al. (2024) · arXiv · doi:10.48550/arxiv.2407.15362 · Cited by 60
“In the realm of prior investigations into pathology foundation models, two prominent categories have emerged: vision-only models 2,4,46 and vision-language models 1,3 .”
InfluentialSelf-citationMultimodal AI generates virtual population for tumor microenvironment modeling
Valanarasu, J. M. J., Xu, H., Usuyama, N., Kim, C., Wong, C., Argaw, P., Shimol, R. B., Crabtree, A., Matlock, K., Bartlett, A. Q., et al. (2025) · Cell · doi:10.1016/j.cell.2025.11.016 · Cited by 58
An eyecare foundation model for clinical assistance: a randomized controlled trial
Wu, Y.-L., Qian, B., Li, T., Qin, Y., Guan, Z., Chen, T., Jia, Y., Zhang, P., Zeng, D., Moroi, S. E., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03900-7 · Cited by 67
Self-citationLi, Z., Li, Y., Xiang, J., Wang, X., Yang, S., Zhang, X., Eweje, F. R., Chen, Y. M., Luo, X., Li, Y., et al. (2026) · Nature Medicine · doi:10.1038/s41591-025-04060-4 · Cited by 73
“25).”
New horizons at the interface of artificial intelligence and translational cancer research
Yates, J., & Allen, E. M. V. (2025) · Cancer Cell · doi:10.1016/j.ccell.2025.03.018 · Cited by 58
Arango-Argoty, G., Bikiel, D. E., Sun, G. J., Kipkogei, E., Smith, K. M., Pro, S. C., Choe, E. Y., & Jacob, E. (2025) · Cancer Cell · doi:10.1016/j.ccell.2025.03.029 · Cited by 61
Transcriptomics-Guided Slide Representation Learning in Computational Pathology
Jaume, G., Oldenburg, L., Vaidya, A., Chen, R. J., Williamson, D. F. K., Peeters, T., Song, A. H., & Mahmood, F. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00920 · Cited by 51
“Encoding histology patches: Most works applying SSL to CPath focus on building embeddings from image patches (typically 256 × 256-pixel regions) [4, 12, 13, 21, 40, 43, 55, 81, 83, 85].”
MethodSelf-citationGenerative Artificial Intelligence in Anatomic Pathology
Brodsky, V., Ullah, E., Bychkov, A., Song, A. H., Walk, E. E., Louis, P., Rasool, G., Singh, R. S., Mahmood, F., Bui, M. M., et al. (2025) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2024-0215-ra · Cited by 48
Self-citationROSIE: AI generation of multiplex immunofluorescence staining from histopathology images
Wu, E., Bieniosek, M. F., Wu, Z., Thakkar, N., Charville, G. W., Makky, A., Schürch, C. M., Huyghe, J. R., Peters, U., Li, C. I., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-62346-0 · Cited by 58
“Recent advances in Transformer architecture-based foundation models trained on histopathology images 10,12,39 show promise when adapted and fi ne-tuned on a wide range of clinical downstream tasks.”
Breen, J., Allen, K., Zucker, K., Godson, L., Orsi, N. M., & Ravikumar, N. (2025) · npj Precision Oncology · doi:10.1038/s41698-025-00799-8 · Cited by 61
Bian, Y., Li, J., Ye, C., Jia, X., & Yang, Q. (2025) · Chinese Medical Journal · doi:10.1097/cm9.0000000000003489 · Cited by 58
“[81,82] Based on pretrained dataset modalities and clinical scenarios, foundation models are typically classified into three categories: general vision foundation models, modality-specific vision foundation models, and vision-language foundation models [Table 2].”
An Electrocardiogram Foundation Model Built on over 10 Million Recordings
Li, J., Aguirre, A. D., Junior, V. F. M., Jin, J., Liu, C., Zhong, L., Sun, C., Clifford, G. D., Westover, M. B., & Hong, S. (2025) · NEJM AI · doi:10.1056/aioa2401033 · Cited by 116
Redlich, J.-P., Feuerhake, F., Weis, J., Schaadt, N. S., Teuber‐Hanselmann, S., Buck, C., Luttmann, S., Eberle, A., Nikolin, S., Appenzeller, A., et al. (2024) · npj Imaging · doi:10.1038/s44303-024-00020-8 · Cited by 49
“The emergence of foundationmodelsforcomputationalpathology 123,124 ,developedusinglarge amountsofhistopathologicaldata,maybeanimprovementoverthecurrent relianceontheResNetCNNarchitectureandtheImageNetdatasetforpre-training.”
Mahlein, A., Barbedo, J. G. A., Chiang, K., Ponte, E. M. D., & Bock, C. H. (2024) · Phytopathology · doi:10.1094/phyto-01-24-0009-per · Cited by 53
DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
Koch, V., Wagner, S. J., Kazeminia, S., Sancar, E., Hehr, M., Schnabel, J. A., Peng, T., & Marr, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72390-2_49 · Cited by 61
Zhang, J., Nguyen, A. T., Xi, H., Trinh, V. Q., Qin, H., Samaras, D., & Hosseini, M. S. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00339 · Cited by 54
Ma, J., Guo, Z., Zhou, F., Wang, Y., Xu, Y., Li, J., Yan, F., Cai, Y., Zhu, Z., Jin, C., et al. (2025) · Nature Biomedical Engineering · doi:10.1038/s41551-025-01488-4 · Cited by 94
Self-citationKhosravi, P., Fuchs, T. J., & Ho, D. J. (2025) · Cancer Research · doi:10.1158/0008-5472.can-24-3630 · Cited by 41
Mi, H., Sivagnanam, S., Ho, W. J., Zhang, S., Bergman, D. R., Deshpande, A. M., Baras, A. S., Jaffee, E. M., Coussens, L. M., Fertig, E. J., et al. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae421 · Cited by 38
“…of robust, general-purpose foundation models has been successful in a wide range of downstream tasks involving histopathology images and/or text,with state-of-the-art performance on image classification [246–248], segmentation [71, 237], and text-to-image and image-to-text retrieval [249, 250].”
BackgroundWang, X., Jiang, Y., Yang, S., Wang, F., Zhang, X., Wang, W., Chen, Y. M., Wu, X., Xiang, J., Li, Y., et al. (2025) · Journal of Clinical Oncology · doi:10.1200/jco-24-01501 · Cited by 52
Patkar, S., Chen, A., Basnet, A., Bixby, A., Rajendran, R., Chernet, R., Faso, S., Kumar, P. A., Desai, D., El-Zammar, O., et al. (2024) · npj Precision Oncology · doi:10.1038/s41698-024-00765-w · Cited by 41
“Overall, to develop HistoTME we experiment with three open-source foundation models — CTransPath, RetCCL, and UNI 21,22,26 — and two con fi gurations of AB-MIL: single task AB-MIL, where the predictions of each signature are optimized separately, and multi-task AB-MIL, where predictions of functionally related signatur…”
InfluentialAdvancing biological understanding of cellular senescence with computational multiomics
Li, S., Agudelo Garcia, P. A., Aliferis, C., Becich, M. J., Calyeca, J., Cosgrove, B. D., Elisseeff, J., Farzad, N., Fertig, E. J., Glass, C., et al. (2025) · Nature Genetics · doi:10.1038/s41588-025-02314-y · Cited by 40
Self-citationA review on federated learning in computational pathology
Schoenpflug, L. A., Nie, Y., Sheikhzadeh, F., & Koelzer, V. H. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.10.037 · Cited by 41
Generating dermatopathology reports from gigapixel whole slide images with HistoGPT
Tran, M., Schmidle, P., Guo, R. R., Wagner, S. J., Koch, V., Lupperger, V., Novotny, B., Murphree, D. H., Hardway, H. D., D’Amato, M., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-60014-x · Cited by 36
“The vision module is based on thepatchencoder CTransPath 17 for thesmall and medium models,and UNI 18 for the large model.”
InfluentialGe, Y., Leng, J., Tang, Z., Wang, K., Kaicheng, U., Zhang, S. M., Han, S., Zhang, Y., Xiang, J., Yang, S., et al. (2024) · Research · doi:10.34133/research.0568 · Cited by 35
“Afterward, UNI [ 37 ], directly training on 100 million tiles using DINOv2 [ 40 ] architecture, was successfully validated by 33 pathology analytical tasks.”
Comiter, C. S., Chen, X., Vaishnav, E. D., Kobayashi-Kirschvink, K. J., Ciampricotti, M., Zhang, K., Murray, J., Monticolo, F., Qi, J., Tanaka, R., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.03.21.533680 · Cited by 34
Cai, L., Huang, S., Zhang, Y., Lu, J., & Zhang, Y. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103631 · Cited by 33
Cohort-Individual Cooperative Learning for Multimodal Cancer Survival Analysis
Zhou, H., Zhou, F., & Chen, H. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3455931 · Cited by 39
“To prove the robustness of our framework, we compare the proposed framework with main competitors, including MCAT [29], SurvPath [30], MOTCat [32], and CMTA [33] by using latest pathology foundation models, including HIPT [16], PLIP [52], UNI [54], and CONCH [53].”
Howard, F. M., Hieromnimon, H. M., Ramesh, S., Dolezal, J. M., Kochanny, S. E., Zhang, Q., Feiger, B., Peterson, J., Fan, C., Perou, C. M., et al. (2024) · Science Advances · doi:10.1126/sciadv.adq0856 · Cited by 33
Yuan, B., Hu, Y., Liang, Y. C., Zhu, Y., Zhang, L., Cai, S., Peng, R., Wang, X., Yang, Z., & Hu, J. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1606336 · Cited by 39
Use of artificial intelligence for liver diseases: A survey from the EASL congress 2024
Žigutytė, L., Sorz-Nechay, T., Clusmann, J., & Kather, J. N. (2024) · JHEP Reports · doi:10.1016/j.jhepr.2024.101209 · Cited by 33
Artificial intelligence for medicine 2025: Navigating the endless frontier
Dai, J., Xu, H., Chen, T., Huang, T., Liang, W., Zhang, R., Xu, G.-X., Zhang, Z., Xue, L., Gao, Y. Q., et al. (2025) · The Innovation Medicine · doi:10.59717/j.xinn-med.2025.100120 · Cited by 35
Hou, J., Zhang, R., Xie, Y., Li, C., & Qin, W. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02257-y · Cited by 38
“In medicine, various foundation models handle different data modalities,suchasscFoundationforgenesequencingdata 45 ,UNIforwhole-slide images 46 , CONCH 24 and MUSK 47 for image-text pairs.”
Gao, P., Xiao, Q., Tan, H. J. J., Song, J., Fu, Y., Xu, J., Zhao, J., Miao, Y., Li, X., Yi, J., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101848 · Cited by 30
“All tiles underwent color normalization using Macenko’s 47,48 technique to mitigate color bias and streamline model training and assessment.”
Spatial omics enters the microscopic realm: opportunities and challenges
Si, Y., Lee, J. S., Jun, G., Kang, H. M., & Lee, J. H. (2025) · Trends in Genetics · doi:10.1016/j.tig.2025.05.002 · Cited by 31
Kludt, C., Wang, Y., Ahmad, W., Bychkov, A., Fukuoka, J., Gaisa, N. T., Kühnel, M., Jonigk, D. D., Pryalukhin, A., Mairinger, F. D., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101697 · Cited by 42
Ma, Y., Jamdade, S., Konduri, L., & Sailem, H. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01524-2 · Cited by 32
Gao, Y., Wen, P., Liu, Y., Sun, Y., Qian, H., Zhang, X., Peng, H., Gao, Y., Li, C., Gu, Z., et al. (2025) · Journal of Translational Medicine · doi:10.1186/s12967-025-06428-z · Cited by 32
“PathChat was constructed by combining a specially trained pathological image visual encoder [61] with a pre-trained large language model (such as Llama 2), and fine-tuned on over 450,000 diverse image-text instructions (containing 999,202 rounds of Q&A).”
Application of artificial intelligence and digital tools in cancer pathology
Shaktah, L., Carrero, Z. I., Hewitt, K. J., Gustav, M., Cecchini, M. J., Foersch, S., Berezowska, S., & Kather, J. N. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100933 · Cited by 33
A foundation model for continuous glucose monitoring data
Lutsker, G., Sapir, G., Shilo, S., Merino, J., Godneva, A., Greenfield, J. R., Samocha‐Bonet, D., Dhir, R., Gude, F., Mannor, S., et al. (2026) · Nature · doi:10.1038/s41586-025-09925-9 · Cited by 64
“11–16).”
Xue, S., Zhu, F., Chen, J., & Min, W. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae630 · Cited by 30
“Moreover,scstGCN has exhibited its capability in enhancing spatial patterns of significant genes, discovering more biologically meaningful pathways and high-resolution annotation of tissue architecture.”
Xu, H., Wang, M., Shi, D., Qin, H., Zhang, Y., Liu, Z., Madabhushi, A., Gao, P., Cong, F., & Lu, C. Y. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103456 · Cited by 41
“After that, we identified ImageNet pre-trained ResNet50 [23] and five recent histological foundation models: CTransPath [10], PathoDuet [11], PLIP [12], CONCH [13], and UNI [14], for conduct-163 ing patch-level embedding (see Fig.”
InfluentialMultimodal foundation model and benchmark for comprehensive retinal OCT image analysis
Morano, J., Fazekas, B., Sükei, E., Fecso, R., Emre, T., Gumpinger, M., Faustmann, G., Oghbaie, M., Schmidt-Erfurth, U. M., & Bogunović, H. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01852-3 · Cited by 39
“Similar to previous work on FMs 27,32,42,44,79,80 , all models were evaluated using linear probing on the target datasets.”
Multistain Pretraining for Slide Representation Learning in Pathology
Jaume, G., Vaidya, A., Zhang, A., H. Song, A., J. Chen, R., Sahai, S., Mo, D., Madrigal, E., Phi Le, L., & Mahmood, F. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-73414-4_2 · Cited by 27
Self-citationA comprehensive AI model development framework for consistent Gleason grading
Huo, X., Ong, K. H., Lau, K. W., Golé, L., Young, D. M., Tan, C. L., Zhu, X., Zhang, C., Zhang, Y., Li, L., et al. (2024) · Communications Medicine · doi:10.1038/s43856-024-00502-1 · Cited by 27
“Addressing these limitations and designing comprehensive AI diagnostic model development framework that encompass diverse datasets 29 , ef fi cient annotation schemes, and consideration of model updateability are crucial steps towards advancing AI-assisted pathology diagnostic models and…”
InfluentialSelf-citationMahbod, A., Saeidi, N., Hatamikia, S., & Woitek, R. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110571 · Cited by 38
“(pathology) Vision/Language 512 UNI [31] Med.”
STPath: a generative foundation model for integrating spatial transcriptomics and whole-slide images
Huang, T., Liu, T., Babadi, M., Ying, R., & Jin, W. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02020-3 · Cited by 33
“STPath also enhances pathology foundation models in weakly supervised settings, improving survival prediction by 6.1% for UNI and 5.6% for Gigapath, and gene mutation prediction by 5.6% for UNI and 5.0% for Gigapath among eight datasetsandninebiomarkers.”
InfluentialSchuiveling, M., Liu, H., Eek, D., Breimer, G. E., Suijkerbuijk, K. P. M., Blokx, W. A. M., & Veta, M. (2025) · GigaScience · doi:10.1093/gigascience/giaf011 · Cited by 26
A multimodal dataset for precision oncology in head and neck cancer
Dörrich, M., Balk, M., Heusinger, T., Beyer, S., Mirbagheri, H., Fischer, D. J., Kanso, H., Matek, C., Hartmann, A., Iro, H., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-62386-6 · Cited by 28
“The resulting image-like embeddings were used to train a Convolutional Neural Network (CNN, see Figure 4) to the same task as in Figure 3.”
HONeYBEE: enabling scalable multimodal AI in oncology through foundation model-driven embeddings
Tripathi, A. G., Waqas, A., Schabath, M. B., Yılmaz, Y., & Rasool, G. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02003-4 · Cited by 37
“For WSIs embedding generation, HONeYBEE supports UNI (ViT-L/ 16, 307M parameters), UNI2-h (ViT-g/14, 632M parameters), and Virchow2(DINOv2, 1.1B parameters) 16,27 .”
Loeffler, C. M. L., Nahhas, O. S. M. E., Muti, H. S., Carrero, Z. I., Seibel, T., van Treeck, M., Çifçi, D., Gustav, M., Bretz, K., Gaisa, N. T., et al. (2024) · BMC Biology · doi:10.1186/s12915-024-02022-9 · Cited by 39
“To ensure the robustness of our findings, we also performed the same experiments using another pretrained vision transformers encoder called UNI [47], https:// github. com/ mahmo odlab/ UNI), followed by a transformer-based multi-head self-attention DL-model as previously already published [48]…”
MethodHuang, Q., Wu, S., Ou, Z., & Gao, Y. (2025) · Intelligent Oncology · doi:10.1016/j.intonc.2025.03.004 · Cited by 29
Pan‐cancer analysis shapes the understanding of cancer biology and medicine
Cen, X., Lan, Y., Zou, J., Chen, R., Hu, C., Tong, Y., Zhang, C., Chen, J., Wang, Y., Zhou, R., et al. (2025) · 癌症：英文版 · doi:10.1002/cac2.70008 · Cited by 30
“Similar examples include recently developed foundation models for histopathology imaging [57, 58].”
Self-citationTiwari, A., Ghose, A., Hasanova, M., Faria, S. S., Mohapatra, S., Adeleke, S. M., & Boussios, S. (2025) · Discover Oncology · doi:10.1007/s12672-025-02212-z · Cited by 32
“Chen et al. [88] introduced a general-purpose foundation model trained on 100 million images from over 100,000 diagnostic H&E-stained WSIs across 20 major tissue types.”
A large model for non-invasive and personalized management of breast cancer from multiparametric MRI
Luo, L., Wu, M., Li, M., Xin, Y., Wang, Q., Vardhanabhuti, V., Chu, C. W., Li, Z., Zhou, J., Rajpurkar, P., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-58798-z · Cited by 29
“The model was developed and extensively evaluated based on a large-scale multiparametric breast MRI dataset collected from three hospitals in China, achieving comparable malignancy differentiating performance with National Health Commission (NHC)-qualified radiologists.”
Training a high-performance retinal foundation model with half-the-data and 400 times less compute
Engelmann, J., & Bernabéu, M. O. (2025) · Nature Communications · doi:10.1038/s41467-025-62123-z · Cited by 31
“First, they train models from scratch using randomly initialised weights, which is particularly challenging and computationally expensive for modern vision transformer architectures 27 that do not have strong inductive biases like traditional convolutional neural networks.”
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding
Chen, Y., Wang, G., Ji, Y., Li, Y., Ye, J., Li, T., Hu, M., Yu, R., Qiao, Y., & He, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00484 · Cited by 50
“SlideChat can generate comprehensive descriptions of whole-slide images and provide contextually relevant responses across various applications. momentum, mainly driven by breakthroughs in the visual foundation model [9, 28, 31].”
High-parameter spatial multi-omics through histology-anchored integration
Liu, Y., Wang, C., Wang, Z., Chen, L., Li, Z., Song, J., Zou, Q., Gao, R., Qian, B., Feng, X., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02926-6 · Cited by 30
“The model processes input H&E images through cell segmentation 45 and cropping to generate single-cell morphology images, which are then transformed into high-dimensional feature representations using a pretrained H&E foundation model 46 (Fig.”
Metadata
- Authors
- Chen, R. J., Ding, T., Lu, M. Y., Williamson, D. F. K., Jaume, G., Song, A. H., Chen, B., Zhang, A., Shao, D., Shaban, M., Williams, M., Oldenburg, L., Weishaupt, L. L., Wang, J. J., Vaidya, A., Le, L. P., Gerber, G., Sahai, S., Williams, W., & Mahmood, F.
- Affiliations
- Broad Institute (US)
- Brigham and Women's Hospital (US)
- Harvard University (US)
- Corresponding author
- Mahmood, Faisal
- ORCID
- Venue
- Nature Medicine
- Published
- 2024-03
- Volume
- 30
- Issue
- 3
- Pages
- 850-862
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- PMC
- PMC11403354
- OpenAlex
- W4392947521
- Semantic Scholar
- cac496ddebbff6bbba78242780cde01bd962bfc9
- Cited by
- 1,560
- References
- 170
- Citations by year
- 2026: 789 · 2025: 613 · 2024: 154
- FWCI
- 229.15
- 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)
- 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
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- computational pathology, whole slide images, self-supervised learning, foundation models, unsupervised feature learning, tissue classification, few-shot learning, cancer subtyping, histopathology, transfer learning
- MeSH terms
- Artificial Intelligence, 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
