{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:55:04Z","timestamp":1790902504619,"version":"4.1.0"},"reference-count":177,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Pathology Informatics"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.jpi.2026.100714","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:30:06Z","timestamp":1788881406000},"page":"100714","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A new era in computational pathology: A survey on foundation and vision-language models"],"prefix":"10.1016","volume":"23","author":[{"given":"Dibaloke","family":"Chanda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milan","family":"Aryal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masoud","family":"Ganji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anil","family":"Parwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasim Yahya","family":"Soltani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jpi.2026.100714_bb0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101813","article-title":"Deep neural network models for computational histopathology: a survey","volume":"67","author":"Srinidhi","year":"2021","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jpi.2026.100714_bb0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2021.103196","article-title":"Artificial intelligence in computational pathology\u2013challenges and future directions","volume":"119","author":"Morales","year":"2021","journal-title":"Digit Signal Process"},{"issue":"4","key":"10.1016\/j.jpi.2026.100714_bb0015","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/s41416-020-01122-x","article-title":"Deep learning in cancer pathology: a new generation of clinical biomarkers","volume":"124","author":"Echle","year":"2021","journal-title":"Br J Cancer"},{"issue":"5","key":"10.1016\/j.jpi.2026.100714_bb0020","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1038\/s41591-021-01343-4","article-title":"Deep learning in histopathology: the path to the clinic","volume":"27","author":"Van der Laak","year":"2021","journal-title":"Nat Med"},{"issue":"6","key":"10.1016\/j.jpi.2026.100714_bb0025","article-title":"A survey on artificial intelligence in histopathology image analysis","volume":"12","author":"Abdelsamea","year":"2022","journal-title":"Wiley Interdisc Rev Data Mining Knowled Discov"},{"issue":"11","key":"10.1016\/j.jpi.2026.100714_bb0030","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.3390\/diagnostics12112794","article-title":"Application of artificial intelligence in pathology: trends and challenges","volume":"12","author":"Kim","year":"2022","journal-title":"Diagnostics"},{"issue":"9","key":"10.1016\/j.jpi.2026.100714_bb0035","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/s43018-022-00436-4","article-title":"Artificial intelligence in histopathology: enhancing cancer research and clinical oncology","volume":"3","author":"Shmatko","year":"2022","journal-title":"Nat Cancer"},{"issue":"11","key":"10.1016\/j.jpi.2026.100714_bb0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.labinv.2023.100255","article-title":"Revolutionizing digital pathology with the power of generative artificial intelligence and foundation models","volume":"103","author":"Waqas","year":"2023","journal-title":"Lab Investig"},{"issue":"5","key":"10.1016\/j.jpi.2026.100714_bb0045","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1002\/path.6168","article-title":"Unleashing the potential of AI for pathology: challenges and recommendations","volume":"260","author":"Asif","year":"2023","journal-title":"J Pathol"},{"issue":"1","key":"10.1016\/j.jpi.2026.100714_bb0050","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1186\/s12938-023-01157-0","article-title":"A survey of transformer applications for histopathological image analysis: new developments and future directions","volume":"22","author":"Atabansi","year":"2023","journal-title":"Biomed Eng Online"},{"issue":"9","key":"10.1016\/j.jpi.2026.100714_bb0055","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1002\/gcc.23177","article-title":"Machine learning in computational histopathology: challenges and opportunities","volume":"62","author":"Cooper","year":"2023","journal-title":"Genes Chromosom Cancer"},{"issue":"12","key":"10.1016\/j.jpi.2026.100714_bb0060","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1038\/s44222-023-00096-8","article-title":"Artificial intelligence for digital and computational pathology","volume":"1","author":"Song","year":"2023","journal-title":"Nat Rev Bioeng"},{"key":"10.1016\/j.jpi.2026.100714_bb0065","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/RBME.2023.3297604","article-title":"Vision transformers for computational histopathology","volume":"17","author":"Xu","year":"2023","journal-title":"IEEE Rev Biomed Eng"},{"issue":"2","key":"10.1016\/j.jpi.2026.100714_bb0070","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1038\/s44287-023-00012-7","article-title":"Artificial intelligence applications in histopathology","volume":"1","author":"Bahadir","year":"2024","journal-title":"Nat Rev Electr Eng"},{"issue":"1","key":"10.1016\/j.jpi.2026.100714_bb0075","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1038\/s41746-024-01106-8","article-title":"Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy","volume":"7","author":"McGenity","year":"2024","journal-title":"npj Digit Med"},{"key":"10.1016\/j.jpi.2026.100714_bb0080","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpi.2023.100357","article-title":"Computational pathology: a survey review and the way forward","volume":"15","author":"Hosseini","year":"2024","journal-title":"J Pathol Inform"},{"key":"10.1016\/j.jpi.2026.100714_bb0085","doi-asserted-by":"crossref","unstructured":"S. Brussee, G. Buzzanca, A. M. Schrader, and J. Kers, \u201cGraph neural networks in histopathology: emerging trends and future directions,\u201d arXiv preprint arXiv:2406.12808, 2024.","DOI":"10.1016\/j.media.2024.103444"},{"key":"10.1016\/j.jpi.2026.100714_bb0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102337","article-title":"Multiple instance learning for digital pathology: a review of the state-of-the-art, limitations & future potential","volume":"112","author":"Gadermayr","year":"2024","journal-title":"Comput Med Imaging Graph"},{"issue":"4","key":"10.1016\/j.jpi.2026.100714_bb0095","doi-asserted-by":"crossref","first-page":"342","DOI":"10.3390\/bioengineering11040342","article-title":"Applications of large language models in pathology","volume":"11","author":"Cheng","year":"2024","journal-title":"Bioengineering"},{"issue":"10","key":"10.1016\/j.jpi.2026.100714_bb0100","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat Genet"},{"key":"10.1016\/j.jpi.2026.100714_bb0105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-021-01466-1","article-title":"Development and operation of a digital platform for sharing pathology image data","volume":"21","author":"Kang","year":"2021","journal-title":"BMC Med Inform Decision Making"},{"key":"10.1016\/j.jpi.2026.100714_bb0110","unstructured":"E. Zimmermann, E. Vorontsov, J. Viret, A. Casson, M. Zelechowski, G. Shaikovski, N. Tenenholtz, J. Hall, T. Fuchs, N. Fusi et al., \u201cVirchow 2: scaling self-supervised mixed magnification models in pathology,\u201d arXiv preprint arXiv:2408.00738, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103289","article-title":"PathoDuet: foundation models for pathological slide analysis of H&E and IHC stains","volume":"97","author":"Hua","year":"2024","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jpi.2026.100714_bb0120","first-page":"1","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","author":"Vorontsov","year":"2024","journal-title":"Nat Med"},{"key":"10.1016\/j.jpi.2026.100714_bb0125","author":"Saillard"},{"key":"10.1016\/j.jpi.2026.100714_bb0130","unstructured":"J. Dippel, B. Feulner, T. Winterhoff, S. Schallenberg, G. Dernbach, A. Kunft, S. Tietz, P. Jurmeister, D. Horst, L. Ruff et al., \u201cRudolfV: a foundation model by pathologists for pathologists,\u201d arXiv preprint arXiv:2401.04079, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0135","unstructured":"D. Nechaev, A. Pchelnikov, and E. Ivanova, \u201cHibou: a family of foundational vision transformers for pathology,\u201d arXiv preprint arXiv:2406.05074, 2024."},{"issue":"1","key":"10.1016\/j.jpi.2026.100714_bb0140","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.1038\/s41467-025-57587-y","article-title":"A foundation model for generalizable cancer diagnosis and survival prediction from histopathological images","volume":"16","author":"Yang","year":"2025","journal-title":"Nat Commun."},{"key":"10.1016\/j.jpi.2026.100714_bb0145","unstructured":"D. Juyal, H. Padigela, C. Shah, D. Shenker, N. Harguindeguy, Y. Liu, B. Martin, Y. Zhang, M. Nercessian, M. Markey et al., \u201cPLUTO: pathology-universal transformer,\u201d arXiv preprint arXiv:2405.07905, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0150","doi-asserted-by":"crossref","unstructured":"X. Zhou, X. Zhang, C. Wu, Y. Zhang, W. Xie, and Y. Wang, \u201cKnowledge-enhanced visual-language pretraining for computational pathology,\u201d arXiv preprint arXiv:2404.09942, 2024.","DOI":"10.1007\/978-3-031-72943-0_20"},{"issue":"3","key":"10.1016\/j.jpi.2026.100714_bb0155","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"10.1016\/j.jpi.2026.100714_bb0160","series-title":"AAAI 2024 Spring Symposium on Clinical Foundation Models","article-title":"Computational pathology at health system scale\u2013self-supervised foundation models from billions of images","author":"Campanella","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0165","article-title":"Scaling self-supervised learning for histopathology with masked image modeling","author":"Filiot","year":"2023","journal-title":"medRxiv"},{"key":"10.1016\/j.jpi.2026.100714_bb0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3344","article-title":"Benchmarking self-supervised learning on diverse pathology datasets","author":"Kang","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102559","article-title":"Transformer-based unsupervised contrastive learning for histopathological image classification","volume":"81","author":"Wang","year":"2022","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jpi.2026.100714_bb0180","unstructured":"J. Ma, Z. Guo, F. Zhou, Y. Wang, Y. Xu, Y. Cai, Z. Zhu, C. Jin, Y. L. X. Jiang, A. Han et al., \u201cTowards a generalizable pathology foundation model via unified knowledge distillation,\u201d arXiv preprint arXiv:2407.18449, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0185","first-page":"1","article-title":"A multimodal generative AI copilot for human pathology","author":"Lu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.jpi.2026.100714_bb0190","first-page":"1","article-title":"A whole-slide foundation model for digital pathology from real-world data","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.jpi.2026.100714_bb0195","unstructured":"G. Shaikovski, A. Casson, K. Severson, E. Zimmermann, Y. K. Wang, J. D. Kunz, J. A. Retamero, G. Oakley, D. Klimstra, C. Kanan et al., \u201cPrism: a multi-modal generative foundation model for slide-level histopathology,\u201d arXiv preprint arXiv:2405.10254, 2024."},{"issue":"5","key":"10.1016\/j.jpi.2026.100714_bb0200","first-page":"5034","article-title":"PathAsst: a generative foundation AI assistant towards artificial general intelligence of pathology","volume":"38","author":"Sun","year":"2024","journal-title":"Proc AAAI Conf Artif Intel"},{"issue":"3","key":"10.1016\/j.jpi.2026.100714_bb0205","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat Med"},{"issue":"9","key":"10.1016\/j.jpi.2026.100714_bb0210","doi-asserted-by":"crossref","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","article-title":"A visual\u2013language foundation model for pathology image analysis using medical twitter","volume":"29","author":"Huang","year":"2023","journal-title":"Nat Med"},{"issue":"12","key":"10.1016\/j.jpi.2026.100714_bb0215","first-page":"9052","article-title":"A survey on self-supervised learning: algorithms, applications, and future trends","volume":"46","year":"2024","journal-title":"in IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"issue":"8","key":"10.1016\/j.jpi.2026.100714_bb0220","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.jpi.2026.100714_bb0225","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0230","unstructured":"Modella, \u201cPathChat,\u201d https:\/\/www.modella.ai\/pathchat, 2025, accessed: 2025-07-27."},{"key":"10.1016\/j.jpi.2026.100714_bb0235","unstructured":"Modella, \u201cJudith: Foundation Model for Computational Pathology,\u201d https:\/\/www.modella.ai\/judith, 2025, accessed: 2025-07-27."},{"key":"10.1016\/j.jpi.2026.100714_bb0240","unstructured":"S. Zhang, Y. Xu, N. Usuyama, H. Xu, J. Bagga, R. Tinn, S. Preston, R. Rao, M. Wei, N. Valluri et al., \u201cBiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs,\u201d arXiv preprint arXiv:2303.00915, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11579","article-title":"Modeling dense multimodal interactions between biological pathways and histology for survival prediction","author":"Jaume","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2021.102027","article-title":"A survey on graph-based deep learning for computational histopathology","volume":"95","author":"Ahmedt-Aristizabal","year":"2022","journal-title":"Comput Med Imaging Graph"},{"key":"10.1016\/j.jpi.2026.100714_bb0255","doi-asserted-by":"crossref","unstructured":"P. Chen, C. Zhu, S. Zheng, H. Li, and L. Yang, \u201cWSI-VQA: interpreting whole slide images by generative visual question answering,\u201d arXiv preprint arXiv:2407.05603, 2024.","DOI":"10.1007\/978-3-031-72764-1_23"},{"key":"10.1016\/j.jpi.2026.100714_bb0260","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat et al., \u201cGPT-4 technical report,\u201d arXiv preprint arXiv:2303.08774, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0265","unstructured":"Y. Sun, Y. Zhang, Y. Si, C. Zhu, Z. Shui, K. Zhang, J. Li, X. Lyu, T. Lin, and L. Yang, \u201cPathGen-1.6 M: 1.6 million pathology image-text pairs generation through multi-agent collaboration,\u201d arXiv preprint arXiv:2407.00203, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0270","article-title":"Quilt-1M: one million image-text pairs for histopathology","volume":"36","author":"Ikezogwo","year":"2024","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0275","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0280","author":"Chiang"},{"key":"10.1016\/j.jpi.2026.100714_bb0285","series-title":"OpenCLIP","author":"Ilharco","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0290","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13183","article-title":"Quilt-LLaVA: cisual instruction tuning by extracting localized narratives from open-source histopathology videos","author":"Seyfioglu","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0295","doi-asserted-by":"crossref","unstructured":"P. Chen, H. Li, C. Zhu, S. Zheng, and L. Yang, \u201cMI-Gen: multiple instance generation of pathology reports for gigapixel whole-slide images,\u201d arXiv preprint arXiv:2311.16480, 2023.","DOI":"10.1007\/978-3-031-72083-3_51"},{"key":"10.1016\/j.jpi.2026.100714_bb0300","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0305","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0310","author":"OpenAI"},{"key":"10.1016\/j.jpi.2026.100714_bb0315","doi-asserted-by":"crossref","unstructured":"Y. Sun, H. Wu, C. Zhu, S. Zheng, Q. Chen, K. Zhang, Y. Zhang, X. Lan, M. Zheng, J. Li et al., \u201cPathMMU: a massive multimodal expert-level benchmark for understanding and reasoning in pathology,\u201d arXiv preprint arXiv:2401.16355, 2024.","DOI":"10.1007\/978-3-031-73033-7_4"},{"key":"10.1016\/j.jpi.2026.100714_bb0320","unstructured":"C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie et al., \u201cYOLOv6: a single-stage object detection framework for industrial applications,\u201d arXiv preprint arXiv:2209.02976, 2022."},{"key":"10.1016\/j.jpi.2026.100714_bb0325","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"issue":"6","key":"10.1016\/j.jpi.2026.100714_bb0330","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac409","article-title":"BioGPT: generative pre-trained transformer for biomedical text generation and mining","volume":"23","author":"Luo","year":"2022","journal-title":"Brief Bioinform"},{"key":"10.1016\/j.jpi.2026.100714_bb0335","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.52202\/068431-1833","article-title":"Laion-5B: an open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv Neural Inform Process Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0340","series-title":"International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0345","series-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"5214","article-title":"An open-source speaker gender detection framework for monitoring gender equality","author":"Doukhan","year":"2018"},{"key":"10.1016\/j.jpi.2026.100714_bb0350","author":"Nakatani"},{"key":"10.1016\/j.jpi.2026.100714_bb0355","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19764","article-title":"Visual language pretrained multiple instance zero-shot transfer for histopathology images","author":"Lu","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0360","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16549","article-title":"Multiple instance captioning: learning representations from histopathology textbooks and articles","author":"Gamper","year":"2021"},{"issue":"46","key":"10.1016\/j.jpi.2026.100714_bb0365","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.21105\/joss.01979","article-title":"Pubmed parser: a python parser for pubmed open-access xml subset and medline xml dataset xml dataset","volume":"5","author":"Achakulvisut","year":"2020","journal-title":"J Open Source Softw"},{"key":"10.1016\/j.jpi.2026.100714_bb0370","series-title":"Proceedings of the 16th ACM\/IEEE-CS on Joint Conference on Digital Libraries","first-page":"143","article-title":"Pdffigures 2.0: mining figures from research papers","author":"Clark","year":"2016"},{"key":"10.1016\/j.jpi.2026.100714_bb0375","doi-asserted-by":"crossref","unstructured":"X. He, Y. Zhang, L. Mou, E. Xing, and P. Xie, \u201cPathVQA: 30000+ questions for medical visual question answering,\u201d arXiv preprint arXiv:2003.10286, 2020.","DOI":"10.36227\/techrxiv.13127537"},{"key":"10.1016\/j.jpi.2026.100714_bb0380","series-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","first-page":"423","article-title":"Accurate unlexicalized parsing","author":"Klein","year":"2003"},{"key":"10.1016\/j.jpi.2026.100714_bb0385","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0390","series-title":"When Multiple Instance Learning Meets Foundation Models: Advancing Histological Whole Slide Image Analysis","author":"Lu","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0395","doi-asserted-by":"crossref","unstructured":"M. Mallya, A. K. Mirabadi, H. Farahani, and A. Bashashati, \u201cBenchmarking histopathology foundation models for ovarian cancer bevacizumab treatment response prediction from whole slide images,\u201d arXiv preprint arXiv:2407.20596, 2024.","DOI":"10.1007\/s12672-025-01973-x"},{"key":"10.1016\/j.jpi.2026.100714_bb0400","doi-asserted-by":"crossref","unstructured":"J. Lu, F. Yan, X. Zhang, Y. Gao, and S. Zhang, \u201cPathoTune: adapting visual foundation model to pathological specialists,\u201d arXiv preprint arXiv:2403.16497, 2024.","DOI":"10.1007\/978-3-031-72083-3_37"},{"key":"10.1016\/j.jpi.2026.100714_bb0405","doi-asserted-by":"crossref","unstructured":"G. Campanella, S. Chen, R. Verma, J. Zeng, A. Stock, M. Croken, B. Veremis, A. Elmas, K.-l. Huang, R. Kwan et al., \u201cA clinical benchmark of public self-supervised pathology foundation models,\u201d arXiv preprint arXiv:2407.06508, 2024.","DOI":"10.1038\/s41467-025-58796-1"},{"key":"10.1016\/j.jpi.2026.100714_bb0410","first-page":"1","article-title":"Benchmarking PathCLIP for pathology image analysis","author":"Zheng","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"10.1016\/j.jpi.2026.100714_bb0415","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11292","article-title":"Prompting vision foundation models for pathology image analysis","author":"Yin","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0420","series-title":"Medical Imaging with Deep Learning","article-title":"Impact of layer selection in histopathology foundation models on downstream task performance","author":"Aswolinskiy","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0425","unstructured":"N. Aben, E. D. de Jong, I. Gatopoulos, N. K\u00e4nzig, M. Karasikov, A. Lagr\u00e9, R. Moser, J. van Doorn, F. Tang et al., \u201cTowards large-scale training of pathology foundation models,\u201d arXiv preprint arXiv:2404.15217, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0430","doi-asserted-by":"crossref","unstructured":"D. Ferber, G. W\u00f6lflein, I. C. Wiest, M. Ligero, S. Sainath, N. G. Laleh, O. S. El Nahhas, G. M\u00fcller-Franzes, D. J\u00e4ger, D. Truhn et al., \u201cIn-context learning enables multimodal large language models to classify cancer pathology images,\u201d arXiv preprint arXiv:2403.07407, 2024.","DOI":"10.1038\/s41467-024-51465-9"},{"issue":"1","key":"10.1016\/j.jpi.2026.100714_bb0435","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.mcpdig.2024.02.003","article-title":"Foundation models for histopathology\u2014fanfare or flair","volume":"2","author":"Alfasly","year":"2024","journal-title":"Mayo Clinic Proc Digit Health"},{"key":"10.1016\/j.jpi.2026.100714_bb0440","doi-asserted-by":"crossref","unstructured":"B. Roth, V. Koch, S. J. Wagner, J. A. Schnabel, C. Marr, and T. Peng, \u201cLow-resource finetuning of foundation models beats state-of-the-art in histopathology,\u201d arXiv preprint arXiv:2401.04720, 2024.","DOI":"10.1109\/ISBI56570.2024.10635695"},{"key":"10.1016\/j.jpi.2026.100714_bb0445","unstructured":"J. Lai, F. Ahmed, S. Vijay, T. Jaroensri, J. Loo, S. Vyawahare, S. Agarwal, F. Jamil, Y. Matias, G. S. Corrado et al., \u201cDomain-specific optimization and diverse evaluation of self-supervised models for histopathology,\u201d arXiv preprint arXiv:2310.13259, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0450","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly et al., \u201cAn image is worth 16x16 words: transformers for image recognition at scale,\u201d arXiv preprint arXiv:2010.11929, 2020."},{"key":"10.1016\/j.jpi.2026.100714_bb0455","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume":"vol. 139","author":"Touvron","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0460","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12104","article-title":"Scaling vision transformers","author":"Zhai","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0500","unstructured":"Z. Peng, L. Dong, H. Bao, Q. Ye, and F. Wei, \u201cBEiT v2: masked image modeling with vector-quantized visual tokenizers,\u201d arXiv preprint arXiv:2208.06366, 2022."},{"issue":"3","key":"10.1016\/j.jpi.2026.100714_bb0505","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int J Comput Vision (IJCV)"},{"key":"10.1016\/j.jpi.2026.100714_bb0465","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0470","unstructured":"M. Oquab, T. Darcet, T. Moutakanni, H. Vo, M. Szafraniec, V. Khalidov, P. Fernandez, D. Haziza, F. Massa, A. El-Nouby et al., \u201cDINOv2: learning robust visual features without supervision,\u201d arXiv preprint arXiv:2304.07193, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0475","unstructured":"X. Chen, H. Fan, R. Girshick, and K. He, \u201cImproved baselines with momentum contrastive learning,\u201d arXiv preprint arXiv:2003.04297, 2020."},{"key":"10.1016\/j.jpi.2026.100714_bb0480","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0485","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0490","unstructured":"J. Zhou, C. Wei, H. Wang, W. Shen, C. Xie, A. Yuille, and T. Kong, \u201ciBOT: image BERT pre-training with online tokenizer,\u201d arXiv preprint arXiv:2111.07832, 2021."},{"key":"10.1016\/j.jpi.2026.100714_bb0495","unstructured":"J. Yu, Z. Wang, V. Vasudevan, L. Yeung, M. Seyedhosseini, and Y. Wu, \u201cCoCa: contrastive captioners are image-text foundation models,\u201d arXiv preprint arXiv:2205.01917, 2022."},{"key":"10.1016\/j.jpi.2026.100714_bb0510","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14496","article-title":"Flexivit: one model for all patch sizes","author":"Beyer","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0515","doi-asserted-by":"crossref","unstructured":"J. Ding, S. Ma, L. Dong, X. Zhang, S. Huang, W. Wang, N. Zheng, and F. Wei, \u201cLongNet: scaling transformers to 1,000,000,000 tokens,\u201d arXiv preprint arXiv:2307.02486, 2023.","DOI":"10.14218\/JERP.2023.00003"},{"key":"10.1016\/j.jpi.2026.100714_bb0530","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale et al., \u201cLlama 2: open foundation and fine-tuned chat models,\u201d arXiv preprint arXiv:2307.09288, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0535","series-title":"International conference on machine learning","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021"},{"issue":"8","key":"10.1016\/j.jpi.2026.100714_bb0540","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"issue":"4","key":"10.1016\/j.jpi.2026.100714_bb0565","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1109\/JBHI.2022.3163751","article-title":"Vision-language transformer for interpretable pathology visual question answering","volume":"27","author":"Naseem","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"10.1016\/j.jpi.2026.100714_bb0570","series-title":"Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP","first-page":"82","article-title":"Probing biomedical embeddings from language models","author":"Jin","year":"2019"},{"key":"10.1016\/j.jpi.2026.100714_bb0575","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0580","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"10.1016\/j.jpi.2026.100714_bb0585","article-title":"The rise of AI language pathologists: exploring two-level prompt learning for few-shot weakly-supervised whole slide image classification","volume":"36","author":"Qu","year":"2024","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0590","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11248","article-title":"ViLa-MIL: dual-scale vision-language multiple instance learning for whole slide image classification","author":"Shi","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0595","doi-asserted-by":"crossref","unstructured":"Q. Zhou, W. Zhong, Y. Guo, M. Xiao, H. Ma, and J. Huang, \u201cPathM3: a multimodal multi-task multiple instance learning framework for whole slide image classification and captioning,\u201d arXiv preprint arXiv:2403.08967, 2024.","DOI":"10.1007\/978-3-031-72083-3_35"},{"issue":"70","key":"10.1016\/j.jpi.2026.100714_bb0600","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J Mach Learn Res"},{"key":"10.1016\/j.jpi.2026.100714_bb0605","series-title":"International Conference on Medical Imaging with Deep Learning","first-page":"1235","article-title":"Inference of captions from histopathological patches","author":"Tsuneki","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0610","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"9049","article-title":"TieNet: text-image embedding network for common thorax disease classification and reporting in chest x-rays","author":"Wang","year":"2018"},{"key":"10.1016\/j.jpi.2026.100714_bb0615","doi-asserted-by":"crossref","unstructured":"H. Watawana, K. Ranasinghe, T. Mahmood, M. Naseer, S. Khan, and F. S. Khan, \u201cHierarchical text-to-vision self supervised alignment for improved histopathology representation learning,\u201d arXiv preprint arXiv:2403.14616, 2024.","DOI":"10.1007\/978-3-031-72083-3_16"},{"key":"10.1016\/j.jpi.2026.100714_bb0620","doi-asserted-by":"crossref","first-page":"28502","DOI":"10.52202\/068431-2066","article-title":"OpenSRH: optimizing brain tumor surgery using intraoperative stimulated raman histology","volume":"35","author":"Jiang","year":"2022","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0625","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11398","article-title":"Generalizable whole slide image classification with fine-grained visual-semantic interaction","author":"Li","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0630","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14318","article-title":"Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning","author":"Li","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0635","doi-asserted-by":"crossref","unstructured":"T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, P. Cistac, T. Rault, R. Louf, M. Funtowicz et al., \u201cHuggingface's transformers: state-of-the-art natural language processing,\u201d arXiv preprint arXiv:1910.03771, 2019.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"10.1016\/j.jpi.2026.100714_bb0640","unstructured":"E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, \u201cLoRA: low-rank adaptation of large language models,\u201d arXiv preprint arXiv:2106.09685, 2021."},{"key":"10.1016\/j.jpi.2026.100714_bb0645","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11450","article-title":"CPLIP: zero-shot learning for histopathology with comprehensive vision-language alignment","author":"Javed","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0650","doi-asserted-by":"crossref","unstructured":"Z. Guo, J. Ma, Y. Xu, Y. Wang, L. Wang, and H. Chen, \u201cHistGen: histopathology report generation via local-global feature encoding and cross-modal context interaction,\u201d arXiv preprint arXiv:2403.05396, 2024.","DOI":"10.1007\/978-3-031-72083-3_18"},{"key":"10.1016\/j.jpi.2026.100714_bb0655","article-title":"Machine learning-driven histotype diagnosis of ovarian carcinoma: insights from the ocean ai challenge","author":"Asadi-Aghbolaghi","year":"2024","journal-title":"medRxiv"},{"issue":"12","key":"10.1016\/j.jpi.2026.100714_bb0660","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.1038\/s41379-022-01146-z","article-title":"Deep learning-based histotype diagnosis of ovarian carcinoma whole-slide pathology images","volume":"35","author":"Farahani","year":"2022","journal-title":"Mod Pathol"},{"key":"10.1016\/j.jpi.2026.100714_bb0665","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.media.2019.02.012","article-title":"Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge","volume":"54","author":"Veta","year":"2019","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jpi.2026.100714_bb0670","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2374","article-title":"CLIPath: fine-tune clip with visual feature fusion for pathology image analysis towards minimizing data collection efforts","author":"Lai","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0675","doi-asserted-by":"crossref","unstructured":"E. Alsentzer, J. R. Murphy, W. Boag, W.-H. Weng, D. Jin, T. Naumann, and M. McDermott, \u201cPublicly available clinical BERT embeddings,\u201d arXiv preprint arXiv:1904.03323, 2019.","DOI":"10.18653\/v1\/W19-1909"},{"issue":"1","key":"10.1016\/j.jpi.2026.100714_bb0680","first-page":"1","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans Comput Healthc (HEALTH)"},{"key":"10.1016\/j.jpi.2026.100714_bb0685","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0690","article-title":"Generating clinical-grade pathology reports from gigapixel whole slide images with HistoGPT","author":"Tran","year":"2024","journal-title":"medRxiv"},{"key":"10.1016\/j.jpi.2026.100714_bb0695","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0700","unstructured":"F. Ahmed, A. Sellergren, L. Yang, S. Xu, B. Babenko, A. Ward, N. Olson, A. Mohtashamian, Y. Matias, G. S. Corrado et al., \u201cPathAlign: a vision-language model for whole slide images in histopathology,\u201d arXiv preprint arXiv:2406.19578, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0705","series-title":"European Conference on Computer Vision","first-page":"456","article-title":"Masked siamese networks for label-efficient learning","author":"Assran","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0710","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0715","unstructured":"R. Anil, A. M. Dai, O. Firat, M. Johnson, D. Lepikhin, A. Passos, S. Shakeri, E. Taropa, P. Bailey, Z. Chen et al., \u201cPaLM 2 technical report,\u201d arXiv preprint arXiv:2305.10403, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0720","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16144","article-title":"Scaling vision transformers to gigapixel images via hierarchical self-supervised learning","author":"Chen","year":"2022"},{"key":"10.1016\/j.jpi.2026.100714_bb0725","doi-asserted-by":"crossref","unstructured":"Z. Chen, Y. Song, T.-H. Chang, and X. Wan, \u201cGenerating radiology reports via memory-driven transformer,\u201d arXiv preprint arXiv:2010.16056, 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"10.1016\/j.jpi.2026.100714_bb0730","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Show and tell: a neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.jpi.2026.100714_bb0735","series-title":"International Conference on Machine Learning","first-page":"2048","article-title":"Show, attend and tell: neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.jpi.2026.100714_bb0740","series-title":"Medical Imaging with Deep Learning, Short Paper Track","article-title":"Caption generation from histopathology whole-slide images using pre-trained transformers","author":"Guevara","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0745","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0750","series-title":"Proceedings of the 22nd Annual Conference of the European Association for Machine Translation","first-page":"479","article-title":"OPUS-MT\u2013building open translation services for the world","author":"Tiedemann","year":"2020"},{"key":"10.1016\/j.jpi.2026.100714_bb0755","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103163","article-title":"Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval","volume":"95","author":"Hu","year":"2024","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jpi.2026.100714_bb0760","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"issue":"9","key":"10.1016\/j.jpi.2026.100714_bb0765","doi-asserted-by":"crossref","first-page":"2726","DOI":"10.1109\/TMI.2023.3264781","article-title":"Kernel attention transformer for histopathology whole slide image analysis and assistant cancer diagnosis","volume":"42","author":"Zheng","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"key":"10.1016\/j.jpi.2026.100714_bb0770","unstructured":"J. Devlin, \u201cBERT: pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, 2018."},{"key":"10.1016\/j.jpi.2026.100714_bb0775","doi-asserted-by":"crossref","unstructured":"L. Qu, D. Yang, D. Huang, Q. Guo, R. Luo, S. Zhang, and X. Wang, \u201cPathology-knowledge enhanced multi-instance prompt learning for few-shot whole slide image classification,\u201d arXiv preprint arXiv:2407.10814, 2024.","DOI":"10.1007\/978-3-031-73247-8_12"},{"key":"10.1016\/j.jpi.2026.100714_bb0780","doi-asserted-by":"crossref","unstructured":"S. Sengupta and D. E. Brown, \u201cAutomatic report generation for histopathology images using pre-trained vision transformers,\u201d arXiv preprint arXiv:2311.06176, 2023.","DOI":"10.1109\/ISBI56570.2024.10635175"},{"key":"10.1016\/j.jpi.2026.100714_bb0785","series-title":"Machine Learning for Healthcare Conference","first-page":"418","article-title":"Evaluating and interpreting caption prediction for histopathology images","author":"Zhang","year":"2020"},{"issue":"12","key":"10.1016\/j.jpi.2026.100714_bb0790","doi-asserted-by":"crossref","first-page":"36645","DOI":"10.1007\/s11042-023-15884-y","article-title":"Enhanced descriptive captioning model for histopathological patches","volume":"83","author":"Elbedwehy","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"10.1016\/j.jpi.2026.100714_bb0795","unstructured":"K. Simonyan, \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv preprint arXiv:1409.1556, 2014."},{"issue":"3","key":"10.1016\/j.jpi.2026.100714_bb0800","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput Vis Media"},{"key":"10.1016\/j.jpi.2026.100714_bb0805","doi-asserted-by":"crossref","unstructured":"M. Yasunaga, J. Leskovec, and P. Liang, \u201cLinkBERT: pretraining language models with document links,\u201d arXiv preprint arXiv:2203.15827, 2022.","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"10.1016\/j.jpi.2026.100714_bb0810","doi-asserted-by":"crossref","unstructured":"L. Zhang, B. Yun, X. Xie, Q. Li, X. Li, and Y. Wang, \u201cPrompting whole slide image based genetic biomarker prediction,\u201d arXiv preprint arXiv:2407.09540, 2024.","DOI":"10.1007\/978-3-031-72083-3_38"},{"key":"10.1016\/j.jpi.2026.100714_bb0815","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19830","article-title":"Interventional bag multi-instance learning on whole-slide pathological images","author":"Lin","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0820","unstructured":"W. Qin, R. Xu, P. Huang, X. Wu, H. Zhang, and L. Luo, \u201cWhat a whole slide image can tell? Subtype-guided masked transformer for pathological image captioning,\u201d arXiv preprint arXiv:2310.20607, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0825","series-title":"International Conference on Machine Learning","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.jpi.2026.100714_bb0830","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.jpi.2026.100714_bb0520","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"10.1016\/j.jpi.2026.100714_bb0525","series-title":"International Conference on Machine Learning","first-page":"12310","article-title":"Barlow twins: self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021"},{"key":"10.1016\/j.jpi.2026.100714_bb0545","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.jpi.2026.100714_bb0550","unstructured":"Y. Wang, W.-L. Chao, K. Q. Weinberger, and L. Van Der Maaten, \u201cSimpleshot: revisiting nearest-neighbor classification for few-shot learning,\u201d arXiv preprint arXiv:1911.04623, 2019."},{"key":"10.1016\/j.jpi.2026.100714_bb0555","series-title":"Medical Imaging with Deep Learning","article-title":"eva: evaluation framework for pathology foundation models","author":"Gatopoulos","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0560","doi-asserted-by":"crossref","unstructured":"Y. Xu, Y. Wang, F. Zhou, J. Ma, S. Yang, H. Lin, X. Wang, J. Wang, L. Liang, A. Han et al., \u201cA multimodal knowledge-enhanced whole-slide pathology foundation model,\u201d arXiv preprint arXiv:2407.15362, 2024.","DOI":"10.1038\/s41467-025-66220-x"},{"key":"10.1016\/j.jpi.2026.100714_bb0835","doi-asserted-by":"crossref","unstructured":"D. Dai, Y. Zhang, L. Xu, Q. Yang, X. Shen, S. Xia, and G. Wang, \u201cPA-LLaVA: a large language-vision assistant for human pathology image understanding,\u201d arXiv preprint arXiv:2408.09530, 2024.","DOI":"10.1109\/BIBM62325.2024.10821785"},{"key":"10.1016\/j.jpi.2026.100714_bb0840","unstructured":"X. Wu, R. Xu, P. Wei, W. Qin, P. Huang, Z. Li, and L. Luo, \u201cPathinsight: instruction tuning of multimodal datasets and models for intelligence assisted diagnosis in histopathology,\u201d arXiv preprint arXiv:2408.07037, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0845","doi-asserted-by":"crossref","unstructured":"K. Chen, M. Liu, F. Yan, L. Ma, X. Shi, L. Wang, X. Wang, L. Zhu, Z. Wang, M. Zhou et al., \u201cCost-effective instruction learning for pathology vision and language analysis,\u201d arXiv preprint arXiv:2407.17734, 2024.","DOI":"10.1038\/s43588-025-00818-5"},{"key":"10.1016\/j.jpi.2026.100714_bb0850","unstructured":"A. Grattafiori, A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten et al., \u201cThe llama 3 herd of models,\u201d arXiv preprint arXiv:2407.21783, 2024."},{"key":"10.1016\/j.jpi.2026.100714_bb0855","unstructured":"J. Bai, S. Bai, S. Yang, S. Wang, S. Tan, P. Wang, J. Lin, C. Zhou, and J. Zhou, \u201cQwen-VL: a frontier large vision-language model with versatile abilities,\u201d arXiv preprint arXiv:2308.12966, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0860","unstructured":"P. Zhang, X. D. B. Wang, Y. Cao, C. Xu, L. Ouyang, Z. Zhao, S. Ding, S. Zhang, H. Duan, H. Yan et al., \u201cInternlm-xcomposer: a vision-language large model for advanced text-image comprehension and composition,\u201d arXiv preprint arXiv:2309.15112, 2023."},{"key":"10.1016\/j.jpi.2026.100714_bb0865","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19358","article-title":"Eva: exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"key":"10.1016\/j.jpi.2026.100714_bb0870","series-title":"21st IEEE International Symposium on Biomedical Imaging (ISBI 2024)","article-title":"Demonstration of an adversarial attack against a multimodal vision language model for pathology imaging","author":"Thota","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0875","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2018"},{"key":"10.1016\/j.jpi.2026.100714_bb0880","series-title":"MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL)","article-title":"Preprocessing pathology reports for vision-language model development","author":"Lucassen","year":"2024"},{"key":"10.1016\/j.jpi.2026.100714_bb0885","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5182","article-title":"PathLDM: text conditioned latent diffusion model for histopathology","author":"Yellapragada","year":"2024"}],"container-title":["Journal of Pathology Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2153353926001768?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2153353926001768?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:18:32Z","timestamp":1790900312000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2153353926001768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":177,"alternative-id":["S2153353926001768"],"URL":"https:\/\/doi.org\/10.1016\/j.jpi.2026.100714","relation":{},"ISSN":["2153-3539"],"issn-type":[{"value":"2153-3539","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A new era in computational pathology: A survey on foundation and vision-language models","name":"articletitle","label":"Article Title"},{"value":"Journal of Pathology Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jpi.2026.100714","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc. on behalf of Association for Pathology Informatics.","name":"copyright","label":"Copyright"}],"article-number":"100714"}}