Ferlay, J. et al. Most cancers statistics for the yr 2020: an outline. Int. J. Most cancers 149, 778–789 (2021).
Google Scholar
Benediktsson, H., Whitelaw, J. & Roy, I. Pathology companies in growing international locations: a problem. Arch. Pathol. Lab. Med. 131, 1636–1639 (2007).
Google Scholar
Metter, D. M., Colgan, T. J., Leung, S. T., Timmons, C. F. & Park, J. Y. Developments within the US and Canadian pathologist workforces from 2007 to 2017. JAMA Netw. Open 2, e194337 (2019).
Google Scholar
Märkl, B., Füzesi, L., Huss, R., Bauer, S. & Schaller, T. Variety of pathologists in Germany: comparability with European international locations, USA, and Canada. Virchows Arch. 478, 335–341 (2021).
Google Scholar
Bera, Ok., Schalper, Ok. A., Rimm, D. L., Velcheti, V. & Madabhushi, A. Synthetic intelligence in digital pathology—new instruments for analysis and precision oncology. Nat. Rev. Clin. Oncol. 16, 703–715 (2019).
Google Scholar
Tune, A. H. et al. Synthetic intelligence for digital and computational pathology. Nat. Rev. Bioeng. 1, 930–949 (2023).
Google Scholar
Campanella, G. et al. Scientific-grade computational pathology utilizing weakly supervised deep studying on complete slide photographs. Nat. Med. 25, 1301–1309 (2019).
Google Scholar
Huang, S.-C. et al. Deep neural community skilled on gigapixel photographs improves lymph node metastasis detection in scientific settings. Nat. Commun. 13, 3347 (2022).
Google Scholar
Kundra, R. et al. OncoTree: a most cancers classification system for precision oncology. JCO Clin. Most cancers Inform. 5, 221–230 (2021).
Google Scholar
Lu, M. Y. et al. Information-efficient and weakly supervised computational pathology on whole-slide photographs. Nat. Biomed. Eng. 5, 555–570 (2021).
Google Scholar
Lu, M. Y. et al. A visible-language basis mannequin for computational pathology. Nat. Med. 30, 863–874 (2024).
Google Scholar
Wang, X. et al. A pathology basis mannequin for most cancers analysis and prognosis prediction. Nature 634, 970–978 (2024).
Google Scholar
Xu, H. et al. A complete-slide basis mannequin for digital pathology from real-world information. Nature 630, 181–188 (2024).
Google Scholar
Arslan, S. et al. A scientific pan-cancer examine on deep learning-based prediction of multi-omic biomarkers from routine pathology photographs. Commun. Med. 4, 48 (2024).
Google Scholar
Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J. & Zou, J. A visible–language basis mannequin for pathology picture evaluation utilizing medical Twitter. Nat. Med. 29, 2307–2316 (2023).
Google Scholar
Chen, R. J. et al. In direction of a general-purpose basis mannequin for computational pathology. Nat. Med. 30, 850–862 (2024).
Google Scholar
Kang, M., Tune, H., Park, S., Yoo, D. & Pereira, S. Benchmarking self-supervised studying on numerous pathology datasets. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Brown, M. S. et al.) 3344–3354 (IEEE, 2023).
Ilse, M., Tomczak, J. & Welling, M. Consideration-based deep a number of occasion studying. In Proc. thirty fifth Worldwide Convention on Machine Studying (eds Dy, J. & Krause, A.) 2127–2136 (PMLR, 2018).
Chen, R. J. et al. Scaling imaginative and prescient transformers to gigapixel photographs by way of hierarchical self-supervised studying. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Chellappa, R. et al.) 16144–16155 (IEEE, 2022).
Snell, J., Swersky, Ok. & Zemel, R. Prototypical networks for few-shot studying. In Proc. thirty first Worldwide Convention on Neural Data Processing Programs (eds von Luxburg, U. et al.) 4080–4090 (ACM, 2017).
Wang, Y., Chao, W.-L., Weinberger, Ok. Q. & van der Maaten, L. SimpleShot: revisiting nearest-neighbor classification for few-shot studying. Preprint at (2019).
Brown, T. et al. Language fashions are few-shot learners. In Proc. thirty fourth Worldwide Convention on Neural Data Processing Programs (eds Larochelle, H. et al.) 1877–1901 (Curran Associates, Inc., 2020).
Wang, X., Wang, W., Cao, Y., Shen, C. & Huang, T. Photos communicate in photographs: a generalist painter for in-context visible studying. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Brown, M. S. et al.) 6830–6839 (IEEE, 2023).
Zhang, J., Wang, B., Li, L., Nakashima, Y. & Nagahara, H. Instruct me extra! Random prompting for visible in-context studying. In Proc. IEEE/CVF Winter Convention on Functions of Pc Imaginative and prescient (eds Memento, R. et al.) 2585–2594 (IEEE, 2024).
Sheng, D. et al. In direction of extra unified in-context visible understanding. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Camps, O. et al.) 13362–13372 (IEEE, 2024).
Zhao, H. et al. MMICL: empowering vision-language mannequin with multi-modal in-context studying. In Proc. twelfth Worldwide Convention on Studying Representations (ed. Kim, B.) (ICLR, 2024).
Ferber, D. et al. In-context studying permits multimodal giant language fashions to categorise most cancers pathology photographs. Nat. Commun. 15, 10104 (2024).
Google Scholar
Bejnordi, B. E. et al. Diagnostic evaluation of deep studying algorithms for detection of lymph node metastases in ladies with breast most cancers. JAMA 318, 2199–2210 (2017).
Google Scholar
Qu, L. et al. The rise of AI language pathologists: exploring two-level immediate studying for few-shot weakly-supervised complete slide picture classification. In Proc. thirty seventh Worldwide Convention on Neural Data Processing Programs (eds Oh, A. et al.) 67551–67564 (Curran Associates, Inc., 2023).
Litjens, G. et al. 1399 H&E-stained sentinel lymph node sections of breast most cancers sufferers: the CAMELYON dataset. Gigascience 7, giy065 (2018).
Google Scholar
Zhang, Y. et al. Benchmarking the robustness of deep neural networks to widespread corruptions in digital pathology. In Proc. twenty fifth Worldwide Convention on Medical Picture Computing and Pc-Assisted Intervention (eds Wang, L. et al.) 242–252 (Springer, 2022).
He, Ok., Zhang, X., Ren, S. & Solar, J. Deep residual studying for picture recognition. In Proc. IEEE Convention on Pc Imaginative and prescient and Sample Recognition (eds Tuytelaars, T. et al.) 770–778 (IEEE, 2016).
Deng, J. et al. ImageNet: a large-scale hierarchical picture database. In Proc. IEEE Convention on Pc Imaginative and prescient and Sample Recognition (eds Huttenlocher, D. et al.) 248–255 (IEEE, 2009).
Vorontsov, E. et al. A basis mannequin for clinical-grade computational pathology and uncommon cancers detection. Nat. Med. 30, 2924–2935 (2024).
Google Scholar
Ma, J. et al. A generalizable pathology basis mannequin utilizing a unified information distillation pretraining framework. Nat. Biomed. Eng. (2025).
Ding, T. et al. A multimodal whole-slide basis mannequin for pathology. Nat. Med. 31, 3749–3761 (2025).
Google Scholar
Shao, Z. et al. TransMIL: transformer based mostly correlated a number of occasion studying for complete slide picture classification. In Proc. thirty fifth Worldwide Convention on Neural Data Processing Programs (eds Ranzato, M. et al.) 2136–2147 (Curran Associates, Inc., 2021).
Li, H. et al. Job-specific fine-tuning by way of variational data bottleneck for weakly-supervised pathology complete slide picture classification. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Brown, M. S. et al.) 7454–7463 (IEEE, 2023).
Tang, W. et al. A number of occasion studying framework with masked arduous occasion mining for complete slide picture classification. In Proc. IEEE/CVF Convention on Pc Imaginative and prescient and Sample Recognition (eds Brown, M. S. et al.) 4078–4087 (IEEE, 2023).
Chen, Y. et al. dMIL-Transformer: a number of occasion studying by way of integrating morphological and spatial data for lymph node metastasis classification. IEEE J. Biomed. Well being Inform. 27, 4433–4443 (2023).
Google Scholar
Xiang, J. et al. A vision-language basis mannequin for precision oncology. Nature 638, 769–778 (2025).
Google Scholar
Coudray, N. et al. Classification and mutation prediction from non-small cell lung most cancers histopathology photographs utilizing deep studying. Nat. Med. 24, 1559–1567 (2018).
Google Scholar
Liang, J. et al. Deep studying supported discovery of biomarkers for scientific prognosis of liver most cancers. Nat. Mach. Intell. 5, 408–420 (2023).
Google Scholar
Zhou, Y., Li, X., Wang, Q. & Shen, J. Visible in-context studying for big vision-language fashions. In Findings of the Affiliation for Computational Linguistics (eds Ku, L.-W. et al.) 15890–15902 (ACL, 2024).
Li, C. et al. LLaVA-med: coaching a big language-and-vision assistant for biomedicine in in the future. In Proc. thirty seventh Worldwide Convention on Neural Data Processing Programs (eds Oh, A. et al.) 28541–28564 (Curran Associates, Inc., 2023).
Li, Y. et al. Few-shot lymph node metastasis classification meets excessive efficiency on complete slide photographs by way of the informative non-parametric classifier. In Proc. twenty fifth Worldwide Convention on Medical Picture Computing and Pc-Assisted Intervention (eds Linguraru, M. G. et al.) 109–119 (Springer, 2024).
Caron, M. et al. Rising properties in self-supervised imaginative and prescient transformers. In Proc. IEEE/CVF Worldwide Convention on Pc Imaginative and prescient (eds Berg, T. et al.) 9650–9660 (IEEE, 2021).
Dosovitskiy, A. et al. A picture is value 16×16 phrases: Transformers for picture recognition at scale. In Proc. ninth Worldwide Convention on Studying Representations (ed. Mohamed, S.) (ICLR, 2021).
Xu, Y. et al. A multimodal knowledge-enhanced whole-slide pathology basis mannequin. Nat. Commun. 16, 11406 (2025).
Google Scholar
Wang, X. et al. Transformer-based unsupervised contrastive studying for histopathological picture classification. Med. Picture Anal. 81, 102559 (2022).
Google Scholar
Oquab, M. et al. DINOv2: Studying strong visible options with out supervision. Trans. Mach. Study. Res. (2024).
Radford, A. et al. Studying transferable visible fashions from pure language supervision. In Proc. Worldwide Convention on Machine Studying (eds Meila, M. & Zhang, T.) 8748–8763 (PMLR, 2021).
Ding, J. et al. LongNet: scaling transformers to 1,000,000,000 tokens. In Proc. tenth Worldwide Convention on Studying Representations (eds Hofmann, Ok. & Rush, A.) (ICLR, 2023).
Komura, D. et al. Common encoding of pan-cancer histology by deep texture representations. Cell Rep. 38, 110424 (2022).
Google Scholar
Riasatian, A. et al. Effective-tuning and coaching of DenseNet for histopathology picture illustration utilizing tcga diagnostic slides. Med. Picture Anal. 70, 102032 (2021).
Google Scholar
Lu, M. Y. et al. AI-based pathology predicts origins for cancers of unknown major. Nature 594, 106–110 (2021).
Google Scholar
