{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:09:14Z","timestamp":1784203754719,"version":"3.55.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22511106000"],"award-info":[{"award-number":["22511106000"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134088","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T15:09:24Z","timestamp":1779721764000},"page":"134088","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MedLAMA: Medical lesion-aware multimodal alignment"],"prefix":"10.1016","volume":"696","author":[{"given":"Zhiyan","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiqin","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134088_bib0005","author":"Shrestha"},{"issue":"2","key":"10.1016\/j.neucom.2026.134088_bib0010","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1148\/rg.2017160130","article-title":"\u201cMachine learning for medical imaging","volume":"37","author":"Erickson","year":"2017","journal-title":"Radiographics"},{"issue":"7639","key":"10.1016\/j.neucom.2026.134088_bib0015","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"\u201cDermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134088_bib0020","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"655","article-title":"\u201cA medical semantic-assisted transformer for radiographic report generation","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3942","article-title":"\u201cGloria: a multimodal global-local representation learning framework for label-efficient medical image recognition","author":"Huang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134088_bib0030","series-title":"Machine Learning for Healthcare Conference","first-page":"2","article-title":"\u201cContrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0035","series-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","first-page":"3876","article-title":"\u201cMedCLIP: contrastive learning from unpaired medical images and text","volume":"vol. 2022","author":"Wang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0040","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"567","article-title":"\u201cPosition-guided prompt learning for anomaly detection in chest x-rays","author":"Sun","year":"2024"},{"key":"10.1016\/j.neucom.2026.134088_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11137","article-title":"\u201cCarzero: cross-attention alignment for radiology zero-shot classification","author":"Lai","year":"2024"},{"key":"10.1016\/j.neucom.2026.134088_bib0050","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21372","article-title":"\u201cMedklip: medical knowledge enhanced language-image pre-training for x-ray diagnosis","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134088_bib0055","doi-asserted-by":"crossref","first-page":"33536","DOI":"10.52202\/068431-2430","article-title":"\u201cMulti-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134088_bib0060","doi-asserted-by":"crossref","first-page":"3755","DOI":"10.1109\/TMI.2024.3398350","article-title":"\u201cChatcad+: towards a universal and reliable interactive CAD using LLMs","volume":"43","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.neucom.2026.134088_bib0065","author":"Lee"},{"key":"10.1016\/j.neucom.2026.134088_bib0070","doi-asserted-by":"crossref","first-page":"28541","DOI":"10.52202\/075280-1240","article-title":"\u201cLlava-med: training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134088_bib0075","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"\u201cMaking the most of text semantics to improve biomedical vision\u2013language processing","author":"Boecking","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0080","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"\u201cFlamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134088_bib0085","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"\u201cVisual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134088_bib0090","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"\u201cLearning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"12","key":"10.1016\/j.neucom.2026.134088_bib0095","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","article-title":"\u201cExpert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning","volume":"6","author":"Tiu","year":"2022","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.neucom.2026.134088_bib0100","series-title":"European Conference on Computer Vision","first-page":"685","article-title":"\u201cJoint learning of localized representations from medical images and reports","author":"Mller","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0105","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12054","article-title":"\u201cAudio-enhanced text-to-video retrieval using text-conditioned feature alignment","author":"Ibrahimi","year":"2023"},{"key":"10.1016\/j.neucom.2026.134088_bib0110","doi-asserted-by":"crossref","first-page":"45666","DOI":"10.52202\/079017-1452","article-title":"\u201cPlip: language-image pre-training for person representation learning","volume":"37","author":"Zuo","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134088_bib0115","series-title":"International Conference on Machine Learning, PMLR","first-page":"25994","article-title":"\u201cMulti-grained vision language pre-training: aligning texts with visual concepts","author":"Zeng","year":"2022"},{"key":"10.1016\/j.neucom.2026.134088_bib0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3060","article-title":"\u201cEnd-to-end semi-supervised object detection with soft teacher","author":"Xu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134088_bib0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.101985","article-title":"\u201cA survey on incorporating domain knowledge into deep learning for medical image analysis","volume":"69","author":"Xie","year":"2021","journal-title":"Med. Image Anal."},{"issue":"1","key":"10.1016\/j.neucom.2026.134088_bib0130","doi-asserted-by":"crossref","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","article-title":"\u201cKnowledge-enhanced visual-language pre-training on chest radiology images","volume":"14","author":"Zhang","year":"2023","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neucom.2026.134088_bib0135","author":"Li"},{"key":"10.1016\/j.neucom.2026.134088_bib0140","author":"Zheng"},{"key":"10.1016\/j.neucom.2026.134088_bib0145","author":"Li"},{"key":"10.1016\/j.neucom.2026.134088_bib0150","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"590","article-title":"\u201cCheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"vol. 33","author":"Irvin","year":"2019"},{"issue":"suppl_1","key":"10.1016\/j.neucom.2026.134088_bib0155","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"\u201cThe unified medical language system (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic acids res."},{"key":"10.1016\/j.neucom.2026.134088_bib0160","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1109\/TMI.2025.3534436","article-title":"\u201cEnhancing medical vision-language contrastive learning via inter-matching relation modelling","volume":"44","author":"Li","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.neucom.2026.134088_bib0165","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part III 24","first-page":"72","article-title":"\u201cAligntransformer: hierarchical alignment of visual regions and disease tags for medical report generation","author":"You","year":"2021"},{"key":"10.1016\/j.neucom.2026.134088_bib0170","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"537","article-title":"\u201cText-guided cross-position attention for segmentation: case of medical image","author":"Lee","year":"2023"},{"key":"10.1016\/j.neucom.2026.134088_bib0175","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2921","article-title":"\u201cLearning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"10.1016\/j.neucom.2026.134088_bib0180","author":"Achiam"},{"key":"10.1016\/j.neucom.2026.134088_bib0185","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"658","article-title":"\u201cAnatomy-guided weakly-supervised abnormality localization in chest x-rays","author":"Yu","year":"2022"},{"issue":"1","key":"10.1016\/j.neucom.2026.134088_bib0190","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"\u201cMIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"10.1016\/j.neucom.2026.134088_bib0195","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2097","article-title":"\u201cChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017"},{"issue":"1","key":"10.1016\/j.neucom.2026.134088_bib0200","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2019180041","article-title":"\u201cAugmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia","volume":"1","author":"Shih","year":"2019","journal-title":"Radiol. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134088_bib0205","author":"Zawacki"},{"issue":"1","key":"10.1016\/j.neucom.2026.134088_bib0210","article-title":"\u201cCOVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest x-ray images","volume":"10","author":"Wang","year":"2020","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.134088_bib0215","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11492","article-title":"\u201cDecomposing disease descriptions for enhanced pathology detection: a multi-aspect vision-language pre-training framework","author":"Phan","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014864?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226014864?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:43:47Z","timestamp":1784202227000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226014864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"alternative-id":["S0925231226014864"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134088","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MedLAMA: Medical lesion-aware multimodal alignment","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134088","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134088"}}