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
Items 201–300 of 1,003
Digital pathology in veterinary clinical pathology: A review
Piccione, J., Anderson, S. N., Neal, S. V., & Varvil, M. S. (2025) · Veterinary Pathology · doi:10.1177/03009858251334340 · Cited by 16
“25,61,112 Such foundation models provide an advanced starting point for addressing a wide range of pathology tasks.”
Tarhini, A., & Naqa, I. E. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26168002 · Cited by 13
“UNI is able to carry out vital tasks such as disease subtyping, tissue classification, and disease diagnosis, which not only provide important guidance for pathologists but can also spearhead diagnostic decisions via microscopic analysis [22].”
Cheng, H., & Wong, C. C. (2025) · Journal of Experimental & Clinical Cancer Research · doi:10.1186/s13046-025-03592-4 · Cited by 16
“Despite these challenges, UNI marks a significant step forward toward versatile and practical clinical applications in pathology [58].”
Leveraging multi-modal foundation models for analysing spatial multi-omic and histopathology data
Liu, T., Huang, T., Ding, T., Wu, H., Humphrey, P., Perincheri, S., Schalper, K., Ying, R., Xu, H., Zou, J., et al. (2026) · Nature Biomedical Engineering · doi:10.1038/s41551-025-01602-6 · Cited by 24
“Although it has been shown that training a PFM can enhance the image classification accuracy as well as gene expression prediction performance 3 , the necessity of having an FM trained based on transcriptomics or other omic data is not resolved yet.”
InfluentialSelf-citationKnowledge-enhanced pretraining for vision-language pathology foundation model on cancer diagnosis
Zhou, X., Sun, L., He, D., Guan, W., Wang, G., Wang, R., Wang, L., Yuan, X., Sun, X., Zhang, Y., et al. (2026) · Cancer Cell · doi:10.1016/j.ccell.2026.01.019 · Cited by 38
“We compared state-of-the-art vision-only foundation models (Vir-chow2 and UNI2) with vision–language foundation models (PLIP, QuiltNet, MI-Zero, CONCH, MUSK, and KEEP) using the TransMIL aggregation framework.”
InfluentialFang, Z., Wang, Y., Xie, P., Wang, Z., & Zhang, Y. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3520129 · Cited by 13
“It is worth noting that the permutation test has been widely used to calculate p-values of different performance metrics in computational pathology [42], [43].”
Foundation Models: From Current Developments, Challenges, and Risks to Future Opportunities
Hussain, A., Ali, S., Farwa, U. E., Mozumder, M. A. I., & Kim, H.-C. (2025) · International Conference on Advanced Communications Technology (ICACT) · doi:10.23919/icact63878.2025.10936649 · Cited by 16
“At the same time, GPT applies a different mode of thinking, where it is trained to predict the next token in the next sequence, given the previous tokens [30, 32, 33].”
Generalized cell phenotyping for spatial proteomics with language-informed vision modelsPreprint
Wang, X., Dilip, R., Iqbal, A. R., Bussi, Y., Brown, C., Pradhan, E., Jain, Y., Yu, K., Li, S., Abt, M., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.02.621624 · Cited by 12
“However, a critical question persists: how can these innovative methods be harnessed to transform the vast amounts of data generated by multiplexed imaging into meaningful biological insights?”
Ganguly, A., Chatterjee, D., Huang, W., Zhang, J., Yurovsky, A., Johnson, T. S., & Chen, C. (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/cvpr52734.2025.01455 · Cited by 11
“Given already very powerful image representations [6, 18, 26, 27, 36], it is difficult to This CVPR paper is the Open Access version, provided by the Computer Vision Foundation.”
Das, A., Tomita, N., Syme, K. J., Ma, W., O’Connor, P., Corbett, K. N., Ren, B., Liu, X., & Hassanpour, S. (2025) · American Journal Of Pathology · doi:10.1016/j.ajpath.2025.08.014 · Cited by 11
Xiang, Y., Liu, B., & Rantalainen, M. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01974-w · Cited by 10
Path2Omics Enhances Transcriptomic and Methylation Prediction Accuracy from Tumor Histopathology
Hoang, D.-T., Shulman, E. D., Dhruba, S. R., Nair, N. U., Barman, R. K., Cantore, T., Biswas, S., Lalchungnunga, H., Singh, O., Chung, Y., et al. (2025) · Cancer Research · doi:10.1158/0008-5472.can-25-4350 · Cited by 14
Cellular architecture and neighborhood-informed virtual spatial tumor profiling from histopathology
Li, Y. J., Li, Z., Quinton, R. J., Ji, Y., Zhang, X., Xiang, J., Wang, X., Yang, S., Eweje, F. R., Chen, Y. M., et al. (2026) · Cell · doi:10.1016/j.cell.2026.05.031 · Cited by 12
Chang, J., & Hatfield, B. S. (2024) · Advances in cancer research · doi:10.1016/bs.acr.2024.05.006 · Cited by 13
Computational modeling for medical data: From data collection to knowledge discovery
Yin, Y., Xu, S., Hong, Y., Cai, Y., Tang, W., Wang, J., Shen, B., Zong, H., & Yu, G. (2024) · The Innovation Life · doi:10.59717/j.xinn-life.2024.100079 · Cited by 11
Self-citationAdachi, M., Taki, T., Kojima, M., Sakamoto, N., Matsuura, K., Hayashi, R., Tabuchi, K., Ishikawa, S., Ishii, G., & Sakashita, S. (2024) · The Journal of Pathology Clinical Research · doi:10.1002/2056-4538.12392 · Cited by 12
“In recent years, methods for feature extraction from pathological images using vision transformer technology have also been reported [45,46].”
MethodDissecting AI-based mutation prediction in lung adenocarcinoma: A comprehensive real-world study
Dernbach, G., Kazdal, D. N., Ruff, L., Alber, M., Romanovsky, E., Schallenberg, S., Christopoulos, P., Weis, C., Muley, T., Schneider, M. A., et al. (2024) · European Journal of Cancer · doi:10.1016/j.ejca.2024.114292 · Cited by 13
Wang, R., Gunesli, G. N., Skingen, V. E., Valen, K.-A. F., Lyng, H., Young, L. S., & Rajpoot, N. (2025) · npj Precision Oncology · doi:10.1038/s41698-024-00778-5 · Cited by 11
Hieromnimon, H. M., Trzcinska, A., Wen, F. T., Howard, F. M., Dolezal, J. M., Dyer, E., Kochanny, S. E., Schulte, J. J., Wang, C., Chen, H., et al. (2025) · Oral Oncology · doi:10.1016/j.oraloncology.2025.107207 · Cited by 12
Zerdes, I., Matikas, A., Mezheyeuski, A., Manikis, G. C., Ács, B., Johansson, H., Boyacı, C., Boman, C., Poncet, C., Ignatiadis, M., et al. (2025) · npj Breast Cancer · doi:10.1038/s41523-025-00730-1 · Cited by 11
“…perspectives towards potential clinicalimplementationincludethere fi nementofexistingordesignofnext-generation AI models (i.e., foundation models) 23 , validation in prospective clinical studies and integration of computational image-based tools to other multi-omic data types for generation of…”
Wu, X., Li, Y., Chen, J., Chen, J., Zhang, W., Lu, X., Zhong, X., Zhu, M., Yi, Y., & Bu, H. (2025) · Breast Cancer Research · doi:10.1186/s13058-025-01968-0 · Cited by 12
“…images and biomedical texts) [10], REMEDIS (combining large-scale supervised transfer learning with natural images and intermediate contrastive self-supervised learning for medical images) [11], UNI (an SSL algorithm based on DINOv2) [12], and Virchow (also an SSL algorithm based on DINOv2) [13].”
How artificial intelligence is transforming pathology
Kwon, D. (2025) · Nature · doi:10.1038/d41586-025-01576-0 · Cited by 14
NCT-CRC-HE: Not All Histopathological Datasets are Equally Useful
Ignatov, A., & Malivenko, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91721-9_19 · Cited by 13
Mulliqi, N., Blilie, A., Ji, X., Szolnoky, K., Olsson, H., Titus, M., Gonzalez, G. M., Boman, S. E., Valkonen, M., Gudlaugsson, E. G., et al. (2025) · BMJ Open · doi:10.1136/bmjopen-2024-097591 · Cited by 12
“49 We aim to compare our end- to-end trained prostate cancer-specific model to transfer- learning-based models relying on state- of- the-art foundation models for histopathology.”
Panacea: A foundation model for clinical trial search, summarization, design, and recruitmentPreprint
Lin, J., Xu, H., Wang, Z., Wang, S., & Sun, J. (2024) · medRxiv · doi:10.1101/2024.06.26.24309548 · Cited by 15
Jesinghaus, M., Schmitt, M. P., Foersch, S., & Konukiewitz, B. (2025) · Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin · doi:10.1007/s00428-025-04241-z · Cited by 10
Zhang, X., Zhou, H., Chen, Q., Wang, X., Fu, Y., Jin, C., Zhou, F., Wang, J.-P., Cai, Q.-Y., Wang, J., et al. (2025) · EClinicalMedicine · doi:10.1016/j.eclinm.2025.103557 · Cited by 11
Self-citationAI-Driven Digital Pathology: Deep Learning and Multimodal Integration for Precision Oncology
Jang, H., & Lee, S. H. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms27010379 · Cited by 13
“For the pathology foundation model, UNI2 [5] was employed to extract patch-level feature embeddings, which were subsequently aggregated and classified using a clustering-constrained-attention multiple-instance learning approach [4].”
Large-scale self-supervised video foundation model for intelligent surgery
Yang, S., Zhou, F., Mayer, L., Huang, F., Chen, Y., Wang, Y., He, S., Nie, Y., Wang, X., Sümer, Ö., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02403-0 · Cited by 23
“as radiology 11,13 and pathology 12,15 , its application within the surgical fi eld remains nascent and underexplored.”
Generalist biological artificial intelligence in modeling the language of life
Rao, V. M., Zhang, S., Plosky, B. S., Hsu, P. D., Wang, B., Zou, J., Žitnik, M., Topol, E. J., & Rajpurkar, P. (2026) · Nature Biotechnology · doi:10.1038/s41587-026-03064-w · Cited by 14
“UNI similarly uses a vision transformer backbone and can perform nuclei segmentation, cancer detection and grading, organ transplant assessment and more 101 .”
Deep learning model with pathological knowledge for detection of colorectal neuroendocrine tumor
Zheng, K., Duan, J., Wang, R., Chen, H., He, H., Zheng, X., Zhao, Z., Jing, B., Zhang, Y., Liu, S., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101785 · Cited by 13
Integrated multicenter deep learning system for prognostic prediction in bladder cancer
He, Q., Xiao, B., Tan, Y., Wang, J., Tan, H. Y., Peng, C., Liang, B., Cao, Y., & Xiao, M. (2024) · npj Precision Oncology · doi:10.1038/s41698-024-00731-6 · Cited by 15
“Meanwhile,wecomparedseveralself-supervised histopathologynetworksonthedownstreamtaskofBcaprognosis, includingCTransPath,Virchow,Uni,andProv-Gigapath 32 – 35 .”
Self-citationWang, C., Wan, Y., Li, S., Qu, K., Zhou, X., He, J., Ke, J., Yu, Y., Wang, T., & Shen, Y. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3501352 · Cited by 13
“To provide more comprehensive insights into patient diagnoses and treatment plans, models like PRISM [30] and TANGLE [31] have introduced multimodal capabilities, integrating pathology images with genomic and transcriptomic data [32].”
High-Resolution Spatial Transcriptomics from Histology Images using HisToSGE
Shi, Z., Xue, S., Zhu, F., & Min, W. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822048 · Cited by 10
“The feature extraction module, utilizing the UNI [17] model trained on one hundred million histological images, generates multimodal feature maps that include RGB, positional, and histological features.”
Transforming Physiology and Healthcare through Foundation Models
Godwin, R. C., Tung, A., Berkowitz, D. E., & Melvin, R. L. (2025) · Physiology · doi:10.1152/physiol.00048.2024 · Cited by 11
Yuan, H. (2025) · Medicine Advances · doi:10.1002/med4.70001 · Cited by 10
“…traditional DL approaches that require large datasets for training, recent advancements in foundation models across various medical domains, such as radiology [8], pathology [9], and ophthalmology [10], have demonstrated the capability to address tasks effectively with limited fine‐tuning samples.”
URFM: A general Ultrasound Representation Foundation Model for advancing ultrasound image diagnosis
Kang, Q., Lao, Q., Gao, J. Y., Bao, W., He, Z., Du, C., Lu, Q., & Li, K. (2025) · iScience · doi:10.1016/j.isci.2025.112917 · Cited by 18
Xu, J., An, H., & Chi, M. (2024) · Bioengineering · doi:10.3390/bioengineering11080814 · Cited by 9
“Studies have demonstrated their effectiveness in tumor metastasis diagnosis [4], tumor subtyping [5], mutation prediction [5], and analyzing gigapixel pathology slides [6].”
BackgroundChandramohan, D., Garapati, H. N., Nangia, U., Simhadri, P. K., Lapsiwala, B. J., Jena, N. K., & Singh, P. K. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1447057 · Cited by 14
Scaling data toward pan-cancer foundation models
Khalili, N., & Ciompi, F. (2024) · Trends in cancer · doi:10.1016/j.trecan.2024.08.008 · Cited by 9
Re-identification from histopathology images
Ganz, J., Ammeling, J., Jabari, S., Breininger, K., & Aubreville, M. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103335 · Cited by 14
Prediction of molecular subtypes for endometrial cancer based on hierarchical foundation model
Cui, H., Guo, Q., Xu, J., Wu, X., Cai, C., Jiao, Y., Ming, W., Wen, H., & Wang, X. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf059 · Cited by 12
“Recently, UNI, a pathology-oriented foundation model (Chen et al. 2024) was developed to solve the problem of self-supervised learning.”
Wang, Y., Liu, Z., & Ma, X. (2025) · Genome Medicine · doi:10.1186/s13073-025-01449-1 · Cited by 12
“Recently, three typical histology-specific models, such as Virchow [79], UNI [80], and Prov-GigaPath [81], are proposed to establish general-purpose foundation models for computational pathology.”
Ullah, E., Baig, M. M., Waqas, A., Rasool, G., Singh, R. P., Shandilya, A., GholamHossieni, H., & Parwani, A. V. (2025) · Advances in Anatomic Pathology · doi:10.1097/pap.0000000000000498 · Cited by 9
Hasan, K. R., Kim, S., Cho, J., & Han, H. S. (2025) · IEEE Access · doi:10.1109/access.2025.3570673 · Cited by 9
“We adopted this widely used protocol from prior literatures [17], [18], [37], [40], and [49].”
InfluentialDing, R.-W., Luong, K.-D., Rodriguez, E., da Silva, A. C. A. L., & Hsu, W. (2024) · Scientific Reports · doi:10.1038/s41598-025-99042-4 · Cited by 13
“[24].”
Advances and challenges in pathomics for liver cancer: From diagnosis to prognostic stratification
Peng, M.-H., Zhang, K., Guan, S.-W., Lin, Q. D., & Yu, H. (2025) · World Journal of Clinical Oncology · doi:10.5306/wjco.v16.i6.107646 · Cited by 9
Integrating images and genomics for multi-modal cancer survival analysis via mixture of experts
Zhang, W., Xu, W., Chen, T., Sakal, C., & Li, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103521 · Cited by 12
ZoomLDM: Latent Diffusion Model for multi-scale image generation
Yellapragada, S., Graikos, A., Triaridis, K., Prasanna, P., Gupta, R., Saltz, J., & Samaras, D. (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/cvpr52734.2025.02184 · Cited by 14
Multi-modal image analysis for large-scale cancer tissue studies within IMMUcan
Eling, N., Dorier, J., Rusakiewicz, S., Liechti, R., Devanand, P., Daniel, M., Windhager, J., Fernandez, B. P., Déglise, S., Despland, L., et al. (2025) · Cell Reports Methods · doi:10.1016/j.crmeth.2025.101170 · Cited by 14
“These include extracting tile embeddings from consecutive H&E sections using foundation models (e.g., UNI 58 ), followed by clustering and proportional sampling, or training deep learning classifiers on expert annotations.”
MorphoITH: a framework for deconvolving intra-tumor heterogeneity using tissue morphology
Nielsen, A. W., Manoochehri, H. E., Zhong, H., Panwar, V., Jarmale, V. N., Jasti, J., Nourani, M., Rakheja, D., Brugarolas, J., Kapur, P., et al. (2025) · Genome Medicine · doi:10.1186/s13073-025-01504-x · Cited by 9
“From several models evaluated (UNI [35], Virchow [36], GigaPath [37], CONCH [38], RetCCL [39]), UNI (v1) was selected due to its strong performance on the pretext task and its computational manageability (Additional file 1: Fig.”
Wang, Y., Gu, Y., Zhang, X., Wang, B., Wang, R., Li, X., Liu, Y., Qu, F., Ren, F., Yan, R., et al. (2025) · Chinese Medical Journal · doi:10.1097/cm9.0000000000003790 · Cited by 9
“[45] UNI is trained using the self-supervised learning algorithm DINO-V2.”
Schuiveling, M., van Duin, I. A. J., ter Maat, L. S., van der Weerd, J. C., Verheijden, R. J., van den Berkmortel, F. W. P. J., Blank, C. U., Breimer, G. E., Burgers, F. H., Boers‐Sonderen, M. J., et al. (2025) · JAMA Oncology · doi:10.1001/jamaoncol.2025.4072 · Cited by 11
Frascarelli, C., Venetis, K., Marra, A., Concardi, A., D’Ercole, M., Mangione, E., Negrelli, M., Porta, F. M., Keswani, S., Curigliano, G., et al. (2025) · npj Breast Cancer · doi:10.1038/s41523-025-00857-1 · Cited by 12
“In response to the limitations of large-scale foundation models, a new generationofoptimizedAImodelsisgainingmomentum 53,54 .”
Foundation Models Meet Medical Image Interpretation
Jiao, L., Hao, J., Li, R., Li, L., Liu, X., Liu, F., Ma, W., Chen, P., Huang, Z., Yang, J., et al. (2026) · Research · doi:10.34133/research.1024 · Cited by 12
Generating clinical-grade pathology reports from gigapixel whole slide images with HistoGPTPreprint
Tran, M., Schmidle, P., Wagner, S. J., Koch, V., Novotny, B. C., Lupperger, V., Feuchtinger, A., Böhner, A., Kaczmarczyk, R., Biedermann, T., et al. (2024) · medRxiv · doi:10.1101/2024.03.15.24304211 · Cited by 9
Triage of 3D pathology data via 2.5D multiple-instance learning to guide pathologist assessments
Gao, G., Song, A. H., Wang, F., Brenes, D., Wang, R., Chow, S. S. L., Bishop, K. W., True, L. D., Mahmood, F., & Liu, J. T. C. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00689 · Cited by 7
“…approach, as opposed to a full 3D approach, is that it is able to evaluate 3D pathology data at high resolution along the depth axis, and also takes advantage of the emerging family of 2D feature extraction models for 2D pathology images [12, 25, 36, 54], which are lacking in 3D feature extraction.”
BackgroundMethodSelf-citationUsing artificial intelligence to prioritize pathology samples: report of a test drive
Rienda, I., Vale, J., Pinto, J. C., Polónia, A., & Eloy, C. (2024) · Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin · doi:10.1007/s00428-024-03988-1 · Cited by 8
“Different efforts have been made recently to bring foundation model-based tools to pathology, with a successful multi-task performance [5, 6].”
Tissue concepts: Supervised foundation models in computational pathology
Nicke, T., Schäfer, J. R., Höfener, H., Feuerhake, F., Merhof, D., Kiessling, F. M., & Lotz, J. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109621 · Cited by 17
“[15] present a general purpose foundation model that leverages over 100 million patches from 100.000 WSI slides across 20 major cancer types.”
InfluentialUnlocking the potential of digital pathology: Novel baselines for compression
Fischer, M., Neher, P., Schüffler, P. J., Ziegler, S., Xiao, S., Peretzke, R., Clunie, D., Ulrich, C., Baumgartner, M., Muckenhuber, A., et al. (2025) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2025.100421 · Cited by 10
“51 Evaluating compression in the context of dl work fl ows ensures that automated systems maintain robust performance and avoids unanticipated failures during real-world deployment.”
Shi, J., Sun, D., Jiang, Z., Du, J., Wang, W., Zheng, Y., & Wu, H. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102502 · Cited by 8
Du, R. F., Carbonell, E. L., Huang, J., Liu, S., Wang, X., Shen, D. G., & Ke, J. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3551913 · Cited by 10
Augmented reality microscopy to bridge trust between AI and pathologists
Badve, S., Kumar, G. L., Lang, T., Peigin, E., Pratt, J., Anders, R. A., Chatterjee, D., González, R. S., Graham, R. P., Krasinskas, A. M., et al. (2025) · npj Precision Oncology · doi:10.1038/s41698-025-00899-5 · Cited by 9
“Following the general research trend of large language models, AI foundation models are currently dominating the computational pathology research space 12,15,43 – 47 .”
Albahri, M., Sauter, D., Nensa, F., Lodde, G. C., Livingstone, E., Schadendorf, D., & Kukuk, M. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.06.017 · Cited by 9
“This approach compensates for slides that do not have the target resolution (mpp = 0.5) directly [27].”
InfluentialMulti-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation
Albastaki, S., Sohail, A., Ganapathi, I. I., Alawode, B., Khan, A. A., Javed, S., Werghi, N., Bennamoun, M., & Mahmood, A. (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/cvpr52734.2025.02413 · Cited by 8
“Our zero-shot evaluation was conducted using the testing split for each dataset, while for linear and full-fine-tuning evaluations (see supplementary material), we used both the training and testing splits of each dataset as suggested in UNI [26].”
InfluentialCytoFM: The First Cytology Foundation Model
Ivezić, V., Radhachandran, A., Redekop, E., Athreya, S., Lee, D., Sant, V. R., Arnold, C. W., & Speier, W. F. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00461 · Cited by 8
“Unlike previous approaches which rely on explicit annotations, self-supervised learning learns the inherent structure in unlabeled data through pretext tasks, resulting in meaningful representations generalizable to unseen domains.”
InfluentialMultimodal AI-based risk stratification for distant metastasis in nasopharyngeal carcinoma
Zhou, J., Wibawa, M. S., Wang, R., Deng, Y., Huang, H., Luo, Z.-X., Xia, Y., Guo, X., Young, L. S., Lo, K. W., et al. (2025) · ESMO Open · doi:10.1016/j.esmoop.2025.105809 · Cited by 9
Artificial intelligence-assisted prostate cancer diagnosis for reduced use of immunohistochemistry
Blilie, A., Mulliqi, N., Ji, X., Szolnoky, K., Boman, S. E., Titus, M., Gonzalez, G. M., Asenjo, J., Gambacorta, M., Libretti, P., et al. (2025) · Communications Medicine · doi:10.1038/s43856-025-01185-y · Cited by 10
“UNI 25 and Virchow2 34 foundation models were used within the same training pipeline; however, the weights of the encoders were kept frozen, and only the ABMIL and subsequent classi fi cation layers were trained identically to the task-speci fi c model.”
Lightweight self supervised learning framework for domain generalization in histopathology
Shafique, A., Dy, A., Qin, X., Alshamlan, N., Androutsos, D., Done, S. J., & Khademi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-20411-0 · Cited by 10
Guo, Q., Cui, H., Zhang, Y., Tang, S., Yan, W., Zhou, X., Ding, H., Zhou, J., Ju, X., Feng, Z., et al. (2026) · npj Precision Oncology · doi:10.1038/s41698-026-01280-w · Cited by 11
“Forfaircomparison,allmodelsused patch-level features extracted from the UNI pathology foundation model, which provides pathology-speci fi c representations with improved consistency across cohorts 21 .”
Hist2Cell: Deciphering fine-grained cellular architectures from histology images
Zhao, W., Liang, Z., Huang, X., Huang, Y., & Yu, L. (2026) · Cell Genomics · doi:10.1016/j.xgen.2025.101137 · Cited by 8
“6,43 Additionally, we compared with UNI, 44 a pathology foundation model pre-trained on over 100,000 diagnostic WSIs from 20 major tissue types.”
Lee, Y., Liu, X., Hao, M., Liu, T., & Regev, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.10.627865 · Cited by 8
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
Precision oncology in patients with breast cancer: towards a ‘screen and characterize’ approach
Rassy, E., Mosele, M. F., Meglio, A. D., Pistilli, B., & André, F. (2024) · ESMO Open · doi:10.1016/j.esmoop.2024.103716 · Cited by 7
Generalized domain prompt learning for accessible scientific vision-language models
Cao, Q., Chen, Y., Lu, L., Sun, H., Zeng, Z., Yang, X., & Zhang, D. (2025) · Nexus · doi:10.1016/j.ynexs.2025.100069 · Cited by 7
Plattner, C., Sturm, G., Kühl, A. A., Atreya, R. N., Carollo, S., Rieder, D., Gronauer, R., Günther, M., Ormanns, S., Manzl, C., et al. (2025) · Gastroenterology · doi:10.1053/j.gastro.2026.05.023 · Cited by 8
Utility of synthetic musculoskeletal gaits for generalizable healthcare applications
Yamada, Y., Kobayashi, M., Shinkawa, K., Bilal, E., Liao, J., Nemoto, M., Ota, M., Nemoto, K., & Arai, T. (2025) · Nature Communications · doi:10.1038/s41467-025-61292-1 · Cited by 8
Chanchal, A. K., Lal, S., & Suresh, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-10712-9 · Cited by 7
“In previous works, deep learning approaches for the classification of histopathology images were focused on transfer learning 5,8,10,15,16,38 techniques.”
Artificial Intelligence in Pathology: Advancing Large Models for Scalable Applications
Xiao, Z., Feng, B., Yang, J., Sun, G., Shen, Y., Xu, S., Yang, L., Xu, H., Zhang, M., & Wang, S. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095814 · Cited by 9
Ayhan, M. S., Ong, A. Y., Ruffell, E., Wagner, S. K., Merle, D. A., & Keane, P. A. (2026) · Ophthalmology Science · doi:10.1016/j.xops.2025.100934 · Cited by 7
The Rise of AI-Assisted Diagnosis: Will Pathologists Be Partners or Bystanders?
El‐Khoury, R., & Zaatari, G. S. (2025) · Diagnostics · doi:10.3390/diagnostics15182308 · Cited by 10
“In pathology, foundation models are being developed and include vision encoders such as UNI [72], CTransPath [73], and Virchow [74], vision–language encoders such as PLIP [71], Prov-GigaPath [75], and CONCH [76], and, as we write this review, THREAD, a molecular-driven foundation model for…”
Xu, X., Kapse, S., & Prasanna, P. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103808 · Cited by 16
Jo, Y., Baek, S.-J., Baek, D., Oh, C., Lee, D., & Hong, B. (2025) · Anesthesia and Pain Medicine · doi:10.17085/apm.25354 · Cited by 7
“The development of foundation models and associated technologies may enhance the efficiency and versatility of AI models in medical imaging [25].”
Self-supervised learning for data augmentation in histopathology image segmentation
Almubarak, H. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-23280-9 · Cited by 8
NuLite - lightweight and fast model for nuclei instance segmentation and classification
Tommasino, C., Russo, C., & Rinaldi, A. M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109333 · Cited by 7
Bilal, M., Gulzar, M. A., Jaffar, N., Alabduljabbar, A., Altherwy, Y. N., Alsuhaibani, A., & Almarshad, F. A. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102680 · Cited by 11
Adaptive compression framework for giga-pixel whole slide images
Lee, J., Takemaru, L., Bappy, D. M., Jeong, Y. S., Jeong, W., Oldridge, D. A., Kim, D., Ahn, S., & Lee, S. H. (2025) · Nature Communications · doi:10.1038/s41467-025-66889-0 · Cited by 10
“For our analysis, we adopted the approachoutlined in the UNI 19 , selecting only samples with a single ground-truth label.”
Artificial intelligence in genitourinary pathology
Patel, A., Parwani, A. V., & Satturwar, S. P. (2025) · Histopathology · doi:10.1111/his.70020 · Cited by 10
“164,165 Foundation models offer practical advantages for GU pathologists, including increased robustness to variations in staining protocols or scanner technologies, reducing frequent revalidation needs.”
Contrastive learning enhances fairness in pathology artificial intelligence systems
Lin, S.-Y., Tsai, P.-C., Su, F.-Y., Chen, C.-Y., Li, F., Zhao, J., Ho, Y. Y., Lee, M. T., Healey, E., Lin, P.-J., et al. (2025) · Cell Reports Medicine · doi:10.1016/j.xcrm.2025.102527 · Cited by 13
“Several studies have demonstrated AI’s capabilities in detecting tumors, 2–4 classifying cancer subtypes, 5–7 predicting cancer-related genomic profiles, 8–10 and estimating patient survival outcomes.”
Chang, L., Li, H., Wu, W., Liu, X., Yan, J., Chen, Z., Wu, H., & Song, S. (2025) · Journal of Translational Medicine · doi:10.1186/s12967-025-07591-z · Cited by 10
“Self supervised and weakly supervised objectives, including masked modeling and contrastive pairing of image, omics, and text, reduce labeling burden and improve transfer across institutions [20].”
InfluentialGenerating crossmodal gene expression from cancer histopathology improves multimodal AI predictions
Dey, S., Banerji, C. R. S., Basuchowdhuri, P., Saha, S. K., Parashar, D., & Chakraborti, T. (2025) · Nature Communications · doi:10.1038/s41467-025-66961-9 · Cited by 11
“Our work builds on preliminary studies in crossmodal prediction 8,17,18 , to provide a road map for sustainable, safe and cost-effective translation of multimodal AI models supporting cancer diagnostics/prognostics, to the clinic.”
Khan, M. S., Dambandkhameneh, F., Shaikh, N., Nie, Y., Venugopal, R., & Li, X. (2026) · Scientific Reports · doi:10.1038/s41598-025-34367-8 · Cited by 7
“Node features are extracted using embeddings from a pretrained UNI [2] model and are further enriched with N -dimensional sinusoidal positional encodings to preserve spatial context.”
Hanif, F., Raza, A., & Mohammed, H. A. (2026) · Scientific Reports · doi:10.1038/s41598-026-35119-y · Cited by 8
Artificial intelligence in clinical oncology: Multimodal integration and translational development
Lin, R., Zhao, Z., Liu, Z., Kang, J., Zhang, K., Huang, X., & Yu, Y. (2026) · Cancer Letters · doi:10.1016/j.canlet.2026.218493 · Cited by 7
Codebook VQ-VAE Approach for Prostate Cancer Diagnosis using Multiparametric MRI
Redekop, E., Pleasure, M., Wang, Z., Sarma, K. V., Kinnaird, A. S., Speier, W. F., & Arnold, C. W. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00242 · Cited by 7
“Given the benefit of foundational models for small datasets and their expressive power to learn a useful latent representation of the domain [8], we believe training a foundational model for the three radiology modalities could help in instances where data is missing.”
Self-supervised learning using diverse cell images for cervical cancer classification
Hemalatha, K., & Vetriselvi, V. (2024) · Measurement · doi:10.1016/j.measurement.2024.116413 · Cited by 8
Bareja, R., Carrillo‐Pérez, F., Zheng, Y., Pizurica, M., Nandi, T., Shen, J., Madduri, R., & Gevaert, O. (2025) · medRxiv · doi:10.1101/2025.05.08.25327250 · Cited by 13
“25,26 Therefore there has been a large effort in developing general purpose pathology foundation models that are trained on millions of whole slide images 26–28 , and can be adapted to tumor classification, segmentation, grading tasks with smaller amounts of labeled data.”
TAD-Graph: Enhancing Whole Slide Image Analysis via Task-Aware Subgraph Disentanglement
Wang, F., Xin, J., Zhao, W., Jiang, Y., Yeung, M. C. F., Wang, L., & Yu, L. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3545680 · Cited by 6
“As detailed in Table VIII, UNI [60] achieved the best results in 5 out of 6 settings, underscoring the importance of selecting a stable and robust patch feature extractor.”
Macaulay, D. O., Han, W., Zarella, M. D., Garcia, C., & Tavolara, T. E. (2025) · The Journal of Pathology Clinical Research · doi:10.1002/2056-4538.70024 · Cited by 7
How can artificial intelligence models advance placental biology?
Chou, T., & Goldstein, J. A. (2025) · Placenta · doi:10.1016/j.placenta.2025.03.010 · Cited by 6
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
