{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T21:24:50Z","timestamp":1787088290575,"version":"build-2736575974"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00240"],"award-info":[{"award-number":["226-2025-00240"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007820","name":"Hangzhou Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007820","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114606","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T06:10:22Z","timestamp":1786342222000},"page":"114606","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PF","title":["Morphology semantics-guided vision language alignment for cervical cell image classification"],"prefix":"10.1016","volume":"180","author":[{"given":"Jiaxin","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunlei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwen","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenming","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6478-9192","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.patcog.2026.114606_b1","first-page":"7","article-title":"Cancer statistics, 2019","volume":"69","author":"Siegel","year":"2019","journal-title":"CA Cancer J. Clin."},{"key":"10.1016\/j.patcog.2026.114606_b2","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.cmpb.2018.05.034","article-title":"A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images","volume":"164","author":"William","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"issue":"18","key":"10.1016\/j.patcog.2026.114606_b3","doi-asserted-by":"crossref","first-page":"6896","DOI":"10.1002\/cam4.3296","article-title":"The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: A population-based cohort study of 0.7 million women","volume":"9","author":"Bao","year":"2020","journal-title":"Cancer Med"},{"issue":"9","key":"10.1016\/j.patcog.2026.114606_b4","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1093\/jnci\/djy225","article-title":"An observational study of deep learning and automated evaluation of cervical images for cancer screening","volume":"111","author":"Hu","year":"2019","journal-title":"J. Natl. Cancer Inst."},{"key":"10.1016\/j.patcog.2026.114606_b5","doi-asserted-by":"crossref","first-page":"38","DOI":"10.4103\/jpi.jpi_53_18","article-title":"Artificial Intelligence and digital pathology: Challenges and opportunities","volume":"9","author":"Tizhoosh","year":"2018","journal-title":"J. Pathol. Inf."},{"key":"10.1016\/j.patcog.2026.114606_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111532","article-title":"EACE: Explain anomaly via counterfactual explanations","volume":"164","author":"Zhou","year":"2025","journal-title":"Pattern Recognit."},{"issue":"7","key":"10.1016\/j.patcog.2026.114606_b7","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"AI for radiographic COVID-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114606_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112406","article-title":"Aegis: A domain generalization framework for medical image segmentation by mitigating feature misalignment","volume":"172","author":"Xu","year":"2026","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.114606_b9","doi-asserted-by":"crossref","first-page":"4423","DOI":"10.1038\/s41467-021-24698-1","article-title":"The impact of site-specific digital histology signatures on deep learning model accuracy and bias","volume":"12","author":"Howard","year":"2021","journal-title":"Nat. Commun."},{"key":"10.1016\/j.patcog.2026.114606_b10","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1038\/s41746-024-01411-2","article-title":"Aligning knowledge concepts to whole slide images for precise histopathology image analysis","volume":"7","author":"Zhao","year":"2024","journal-title":"Npj Digit. Med."},{"issue":"9","key":"10.1016\/j.patcog.2026.114606_b11","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."},{"key":"10.1016\/j.patcog.2026.114606_b12","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"vol. 35","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.114606_b13","unstructured":"A. Radford, J.W. Kim, C. Hallacy, et al., Learning transferable visual models from natural language supervision, in: Proc Int Conf Mach Learn, 2021, pp. 8748\u20138763."},{"key":"10.1016\/j.patcog.2026.114606_b14","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume":"158","author":"Zhang","year":"2022","journal-title":"Proc. Mach. Learn. Res."},{"issue":"1","key":"10.1016\/j.patcog.2026.114606_b15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1002\/cncr.22423","article-title":"The bethesda interobserver reproducibility study (BIRST): A web-based assessment of the bethesda 2001 system for classifying cervical cytology","volume":"111","author":"Sherman","year":"2007","journal-title":"Cancer"},{"issue":"4\u20135","key":"10.1016\/j.patcog.2026.114606_b16","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1159\/000477556","article-title":"The bethesda system for reporting cervical cytology: A historical perspective","volume":"61","author":"Nayar","year":"2017","journal-title":"Acta Cytol."},{"key":"10.1016\/j.patcog.2026.114606_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112486","article-title":"Multi-AD: Cross-domain unsupervised anomaly detection for medical and industrial applications","volume":"172","author":"Rahmaniar","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114606_b18","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, et al., Deep residual learning for image recognition, in: Proc IEEE Conf Comput Vis Pattern Recognit, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.114606_b19","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., An image is worth 16x16 words: Transformers for image recognition at scale, in: Int Conf Learn Represent, 2021."},{"issue":"Suppl 2","key":"10.1016\/j.patcog.2026.114606_b20","doi-asserted-by":"crossref","first-page":"2687","DOI":"10.1007\/s10462-023-10588-z","article-title":"A systematic review of deep learning-based cervical cytology screening: From cell identification to whole slide image analysis","volume":"56","author":"Jiang","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patcog.2026.114606_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111768","article-title":"GraphMamba: Whole slide image classification meets graph-driven selective state space model","volume":"167","author":"Zheng","year":"2025","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.patcog.2026.114606_b22","doi-asserted-by":"crossref","first-page":"4116","DOI":"10.1109\/TMI.2025.3548872","article-title":"ToPoFM: Topology-guided pathology foundation model for high-resolution pathology image synthesis with cellular-level control","volume":"44","author":"Li","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.114606_b23","unstructured":"R. Geirhos, P. Rubisch, C. Michaelis, et al., ImageNet-trained CNNs are biased towards texture; Increasing shape bias improves accuracy and robustness, in: Int Conf Learn Represent, 2019."},{"key":"10.1016\/j.patcog.2026.114606_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112630","article-title":"Decoupling augmentation bias in prompt learning for vision-language models","volume":"172","author":"Kim","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114606_b25","doi-asserted-by":"crossref","first-page":"447","DOI":"10.59275\/j.melba.2025-8888","article-title":"Preventing shortcut learning in medical image analysis through intermediate layer knowledge distillation from specialist teachers","volume":"3","author":"Boland","year":"2025","journal-title":"Mach. Learn. Biomed. Imaging"},{"key":"10.1016\/j.patcog.2026.114606_b26","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.patcog.2026.114606_b27","doi-asserted-by":"crossref","unstructured":"S.-C. Huang, L. Shen, M.P. Lungren, et al., GLoRIA: A multimodal global-local representation learning framework for label-efficient medical image recognition, in: Proc IEEE\/CVF Int Conf Comput Vis, 2021, pp. 3922\u20133931.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.patcog.2026.114606_b28","first-page":"37995","article-title":"Quilt-1M: one million image-text pairs for histopathology","volume":"vol. 36","author":"Ikezogwo","year":"2023"},{"key":"10.1016\/j.patcog.2026.114606_b29","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."},{"key":"10.1016\/j.patcog.2026.114606_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103912","article-title":"MIRAGE: Medical image-text pre-training for robustness against noisy environments","volume":"109","author":"Cheng","year":"2026","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2026.114606_b31","unstructured":"V. Sobal, M. Ibrahim, R. Balestriero, et al., X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs, in: Int Conf Learn Represent, 2025."},{"key":"10.1016\/j.patcog.2026.114606_b32","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume":"vol. 30","author":"Snell","year":"2017"},{"key":"10.1016\/j.patcog.2026.114606_b33","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114606_b34","doi-asserted-by":"crossref","unstructured":"C. Wang, K. Zhang, Y. Liu, et al., MVP-CBM: Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification, in: Proc Thirty-Fourth Int Joint Conf Artif Intell, 2025, pp. 529\u2013537.","DOI":"10.24963\/ijcai.2025\/60"},{"issue":"1","key":"10.1016\/j.patcog.2026.114606_b35","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s13755-025-00380-4","article-title":"Knowledge-enhanced medical image classification via descriptive priors from large language models","volume":"13","author":"Zhang","year":"2025","journal-title":"Health Inf. Sci. Syst."},{"key":"10.1016\/j.patcog.2026.114606_b36","doi-asserted-by":"crossref","first-page":"4344","DOI":"10.1109\/TMI.2024.3419697","article-title":"Hicervix: An extensive hierarchical dataset and benchmark for cervical cytology classification","volume":"43","author":"Cai","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.patcog.2026.114606_b37","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1038\/s41597-021-00933-8","article-title":"Cric searchable image database as a public platform for conventional pap smear cytology data","volume":"8","author":"Rezende","year":"2021","journal-title":"Sci. Data"},{"key":"10.1016\/j.patcog.2026.114606_b38","first-page":"962","article-title":"PathologyBERT \u2013 pre-trained vs. A new transformer language model for pathology domain","volume":"vol. 2022","author":"Santos","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015700?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326015700?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T20:42:21Z","timestamp":1787085741000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326015700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":38,"alternative-id":["S0031320326015700"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114606","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Morphology semantics-guided vision language alignment for cervical cell image classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114606","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114606"}}