{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T01:09:43Z","timestamp":1789088983116,"version":"build-2803163510"},"reference-count":75,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100023542","name":"The Chinese University of Hong Kong Centre for Perceptual and Interactive Intelligence Ltd","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Med"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.medj.2026.101223","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:03:19Z","timestamp":1783695799000},"page":"101223","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["A unified multi-task framework enables interpretable chest radiograph analysis"],"prefix":"10.1016","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6632-4011","authenticated-orcid":false,"given":"Lijian","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinglong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaosong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.medj.2026.101223_bib1","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1016\/j.radi.2021.03.006","article-title":"Radiographers reporting chest x-ray images: Identifying the service enablers and challenges in england, uk","volume":"27","author":"Stevens","year":"2021","journal-title":"Radiography"},{"key":"10.1016\/j.medj.2026.101223_bib2","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102125","article-title":"Deep learning for chest x-ray analysis: A survey","volume":"72","author":"\u00c7all\u0131","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.medj.2026.101223_bib3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib4","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib7","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.medj.2026.101223_bib8","first-page":"5547","article-title":"Glam: Efficient scaling of language models with mixture-of-experts","volume":"162","author":"Du","year":"2022","journal-title":"ICML"},{"key":"10.1016\/j.medj.2026.101223_bib9","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib10","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib11","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.medj.2026.101223_bib12","article-title":"One leaf reveals the season: Occlusion-based contrastive learning with semantic-aware views for efficient visual representation","author":"Yang","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib13","article-title":"Fewer tokens, greater scaling: Self-adaptive visual bases for efficient and expansive representation learning","author":"Young","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib14","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib15","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.medj.2026.101223_bib16","first-page":"49250","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113203","article-title":"Scalar: Spatial-concept alignment for robust vision in harsh open world","volume":"176","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.medj.2026.101223_bib18","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib19","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","article-title":"Med-bert: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction","volume":"4","author":"Rasmy","year":"2021","journal-title":"npj Digit. Med."},{"key":"10.1016\/j.medj.2026.101223_bib20","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.medj.2026.101223_bib21","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.medj.2026.101223_bib22","doi-asserted-by":"crossref","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","article-title":"A generalist vision\u2013language foundation model for diverse biomedical tasks","volume":"30","author":"Zhang","year":"2024","journal-title":"Nat. Med."},{"key":"10.1016\/j.medj.2026.101223_bib23","article-title":"Medvilam: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib24","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib25","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"Mimic-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.medj.2026.101223_bib26","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","article-title":"Vindr-cxr: An open dataset of chest x-rays with radiologist\u2019s annotations","volume":"9","author":"Nguyen","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.medj.2026.101223_bib27","doi-asserted-by":"crossref","first-page":"2042","DOI":"10.1109\/TMI.2021.3070847","article-title":"A structure-aware relation network for thoracic diseases detection and segmentation","volume":"40","author":"Lian","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.medj.2026.101223_bib28","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1038\/s41597-024-03358-1","article-title":"Chexmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images","volume":"11","author":"Gaggion","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.medj.2026.101223_bib29","unstructured":"Zawacki, A., Wu, C., Shih, G., Elliott, J., Fomitchev, M., Hussain, M., Culliton, P., and Bao, S. (2019). Siim-acr pneumothorax segmentation. Kaggle competition."},{"key":"10.1016\/j.medj.2026.101223_bib30","first-page":"2097","article-title":"Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib31","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","article-title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019","journal-title":"AAAI"},{"key":"10.1016\/j.medj.2026.101223_bib32","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2019180041","article-title":"Augmenting 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.medj.2026.101223_bib33","doi-asserted-by":"crossref","first-page":"71","DOI":"10.2214\/ajr.174.1.1740071","article-title":"Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists\u2019 detection of pulmonary nodules","volume":"174","author":"Shiraishi","year":"2000","journal-title":"AJR Am. J. Roentgenol."},{"key":"10.1016\/j.medj.2026.101223_bib34","article-title":"Making the most of text semantics to improve biomedical vision\u2013language processing","author":"Boecking","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib35","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","author":"Chen","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib36","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib37","first-page":"3942","article-title":"Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition","author":"Huang","year":"2021","journal-title":"ICCV"},{"key":"10.1016\/j.medj.2026.101223_bib38","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s42256-021-00425-9","article-title":"Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports","volume":"4","author":"Zhou","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.medj.2026.101223_bib39","article-title":"Multimodal masked autoencoders learn transferable representations","author":"Geng","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib40","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib41","article-title":"Medklip: Medical knowledge enhanced language-image pre-training for x-ray diagnosis","author":"Wu","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib42","article-title":"Delving into masked autoencoders for multi-label thorax disease classification","author":"Xiao","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib43","article-title":"Advancing radiograph representation learning with masked record modeling","author":"Zhou","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib44","series-title":"ICME","first-page":"1","article-title":"Visual grounding with transformers","author":"Du","year":"2022"},{"key":"10.1016\/j.medj.2026.101223_bib45","article-title":"Seqtr: A simple yet universal network for visual grounding","author":"Zhu","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib46","article-title":"Transvg: End-to-end visual grounding with transformers","author":"Deng","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib47","article-title":"Medical phrase grounding with region-phrase context contrastive alignment","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib48","article-title":"Chex: Interactive localization and region description in chest x-rays","author":"M\u00fcller","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib49","doi-asserted-by":"crossref","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","article-title":"Knowledge-enhanced visual-language pre-training on chest radiology images","volume":"14","author":"Zhang","year":"2023","journal-title":"Nat. Commun."},{"key":"10.1016\/j.medj.2026.101223_bib50","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.medj.2026.101223_bib51","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018","journal-title":"CVPR"},{"key":"10.1016\/j.medj.2026.101223_bib52","article-title":"Self-critical sequence training for image captioning","author":"Rennie","year":"2017","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib53","article-title":"Cross-modal memory networks for radiology report generation","author":"Chen","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib54","article-title":"Contrastive attention for automatic chest x-ray report generation","author":"Liu","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib55","article-title":"Interactive and explainable region-guided radiology report generation","author":"Tanida","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib56","article-title":"Multimodal image-text matching improves retrieval-based chest x-ray report generation","author":"Jeong","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib57","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1038\/s41467-024-45599-z","article-title":"A deep-learning-based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest x-ray","volume":"15","author":"Fan","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.medj.2026.101223_bib58","article-title":"Maira-2: Grounded radiology report generation","author":"Bannur","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib59","series-title":"LLaVA-Rad MIMIC-CXR Annotations","author":"Chaves","year":"2025"},{"key":"10.1016\/j.medj.2026.101223_bib60","doi-asserted-by":"crossref","first-page":"4374","DOI":"10.1007\/s00330-024-11339-6","article-title":"Cxr-llava: a multimodal large language model for interpreting chest x-ray images","volume":"35","author":"Lee","year":"2025","journal-title":"Eur. Radiol."},{"key":"10.1016\/j.medj.2026.101223_bib61","series-title":"AAAI 2024 Spring Symposium on Clinical Foundation Models","article-title":"Chexagent: Towards a foundation model for chest x-ray interpretation","author":"Chen","year":"2024"},{"key":"10.1016\/j.medj.2026.101223_bib62","article-title":"A deepseek-powered ai system for automated chest radiograph interpretation in clinical practice","author":"Bai","year":"2026","journal-title":"Nat. Commun."},{"key":"10.1016\/j.medj.2026.101223_bib63","article-title":"Medversa: A generalist foundation model for medical image interpretation","author":"Zhou","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib64","article-title":"Xrayclaw: Cooperative-competitive multi-agent alignment for trustworthy chest x-ray diagnosis","author":"Young","year":"2026","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib65","article-title":"Tc-ssa: Token compression via semantic slot aggregation for gigapixel pathology reasoning","author":"Chen","year":"2026","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib66","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume":"162","author":"Wang","year":"2022","journal-title":"ICML"},{"key":"10.1016\/j.medj.2026.101223_bib67","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib68","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib69","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib70","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI technical report"},{"key":"10.1016\/j.medj.2026.101223_bib71","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"10.1016\/j.medj.2026.101223_bib72","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.medj.2026.101223_bib73","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2023.100802","article-title":"Evaluating progress in automatic chest x-ray radiology report generation","volume":"4","author":"Yu","year":"2023","journal-title":"Patterns"},{"key":"10.1016\/j.medj.2026.101223_bib74","article-title":"Elixr: Towards a general purpose x-ray artificial intelligence system through alignment of large language models and radiology vision encoders","author":"Xu","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.medj.2026.101223_bib75","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"}],"container-title":["Med"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666634026002266?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666634026002266?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:50:12Z","timestamp":1789087812000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666634026002266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":75,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["S2666634026002266"],"URL":"https:\/\/doi.org\/10.1016\/j.medj.2026.101223","relation":{},"ISSN":["2666-6340"],"issn-type":[{"value":"2666-6340","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A unified multi-task framework enables interpretable chest radiograph analysis","name":"articletitle","label":"Article Title"},{"value":"Med","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.medj.2026.101223","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"101223"}}