{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:13:24Z","timestamp":1778102004980,"version":"3.51.4"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006248","name":"Anhui University of Technology","doi-asserted-by":"publisher","award":["DT2200000873"],"award-info":[{"award-number":["DT2200000873"]}],"id":[{"id":"10.13039\/501100006248","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114731","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:16:31Z","timestamp":1775816191000},"page":"114731","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["An interpretable multimodal transformer for medical report generation via hierarchical semantics and clinical labeling"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4251-5822","authenticated-orcid":false,"given":"Jia Sheng","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenbo","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114731_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107448","article-title":"Cov-fed: federated learning-based framework for COVID-19 diagnosis using chest X-ray scans","volume":"128","author":"Adjei-Mensah","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114731_bib2","series-title":"Multiple Object Recognition with Visual Attention","author":"Ba","year":"2015"},{"key":"10.1016\/j.engappai.2026.114731_bib3","series-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.engappai.2026.114731_bib4","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e36272","article-title":"Enhancing image caption generation through context-aware attention mechanism","volume":"10","author":"Bhuiyan","year":"2024","journal-title":"Heliyon"},{"key":"10.1016\/j.engappai.2026.114731_bib5","first-page":"3","article-title":"Discrepancy and error in radiology: concepts, causes and consequences","volume":"81","author":"Brady","year":"2012","journal-title":"Ulst. Med. J."},{"key":"10.1016\/j.engappai.2026.114731_bib6","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-020-70479-z","article-title":"Comparing different deep learning architectures for classification of chest radiographs","volume":"10","author":"Bressem","year":"2020","journal-title":"Sci. Rep."},{"key":"10.1016\/j.engappai.2026.114731_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2024.104764","article-title":"Visual-linguistic diagnostic semantic enhancement for medical report generation","volume":"161","author":"Chen","year":"2025","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.engappai.2026.114731_bib8","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106813","article-title":"Multi-modal graph aggregation transformer for image captioning","volume":"181","author":"Chen","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.engappai.2026.114731_bib9","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2025.104363","article-title":"Road surface damage detection based on enhanced YOLOv8","volume":"173","author":"Chen","year":"2025","journal-title":"Comput. Ind."},{"key":"10.1016\/j.engappai.2026.114731_bib10","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1439","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"key":"10.1016\/j.engappai.2026.114731_bib11","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Demner-Fushman","year":"2016","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"10.1016\/j.engappai.2026.114731_bib12","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Presented at the NAACL-HLT 2019","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.engappai.2026.114731_bib13","doi-asserted-by":"crossref","first-page":"157651","DOI":"10.1109\/ACCESS.2025.3606961","article-title":"Chest X-Ray report generation using abnormality guided vision language model","volume":"13","author":"Edirisinghe","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114731_bib14","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.107562","article-title":"Automated generation of chest X-ray imaging diagnostic reports by multimodal and multi granularity features fusion","volume":"105","author":"Fang","year":"2025","journal-title":"Biomed. Signal Process Control"},{"key":"10.1016\/j.engappai.2026.114731_bib15","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/s00330-024-10907-0","article-title":"Deep learning in pulmonary nodule detection and segmentation: a systematic review","volume":"35","author":"Gao","year":"2024","journal-title":"Eur. Radiol."},{"key":"10.1016\/j.engappai.2026.114731_bib16","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113538","article-title":"Abnormal-region-aware Multi-modal feature fusion for medical report generation","volume":"318","author":"Gao","year":"2025","journal-title":"Knowl. Base Syst."},{"key":"10.1016\/j.engappai.2026.114731_bib17","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130082","article-title":"Dynamic feature fusion guiding and multimodal large language model refining for medical image report generation","volume":"299","author":"Han","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib18","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112805","article-title":"A plug-and-play knowledge-enhanced module for medical reports generation","volume":"309","author":"Han","year":"2025","journal-title":"Knowl. Base Syst."},{"key":"10.1016\/j.engappai.2026.114731_bib19","series-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2015"},{"key":"10.1016\/j.engappai.2026.114731_bib20","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","first-page":"293","article-title":"RATCHET: medical transformer for chest X-ray diagnosis and reporting","author":"Hou","year":"2021"},{"key":"10.1016\/j.engappai.2026.114731_bib21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126394","article-title":"Recalibrated cross-modal alignment network for radiology report generation with weakly supervised contrastive learning","volume":"269","author":"Hou","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib22","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104496","article-title":"MKCL: medical knowledge with contrastive learning model for radiology report generation","volume":"146","author":"Hou","year":"2023","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.engappai.2026.114731_bib23","series-title":"AI for Health Equity and Fairness, Studies in Computational Intelligence","first-page":"233","article-title":"Semantic and visual attention-driven Multi-LSTM network for automated clinical report generation","author":"Huang","year":"2024"},{"key":"10.1016\/j.engappai.2026.114731_bib24","series-title":"Densely Connected Convolutional Networks","author":"Huang","year":"2018"},{"key":"10.1016\/j.engappai.2026.114731_bib25","doi-asserted-by":"crossref","first-page":"7620","DOI":"10.1038\/s41467-024-51749-0","article-title":"Enhancing representation in radiography-reports foundation model: a granular alignment algorithm using masked contrastive learning","volume":"15","author":"Huang","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.engappai.2026.114731_bib26","first-page":"590","article-title":"CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.engappai.2026.114731_bib27","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"6570","article-title":"Show, describe and conclude: on exploiting the structure information of chest X-Ray reports","author":"Jing","year":"2019"},{"key":"10.1016\/j.engappai.2026.114731_bib28","first-page":"2577","article-title":"On the automatic generation of medical imaging reports","volume":"1","author":"Jing","year":"2018"},{"key":"10.1016\/j.engappai.2026.114731_bib29","author":"Johnson"},{"key":"10.1016\/j.engappai.2026.114731_bib30","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103377","article-title":"DACG: dual attention and context guidance model for radiology report generation","volume":"99","author":"Lang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.engappai.2026.114731_bib31","first-page":"6666","article-title":"Knowledge-driven encode, retrieve, paraphrase for medical image report generation","volume":"33","author":"Li","year":"2019"},{"key":"10.1016\/j.engappai.2026.114731_bib32","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103586","article-title":"Report is a mixture of topics: topic-guided radiology report generation","volume":"103","author":"Li","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.engappai.2026.114731_bib33","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127419","article-title":"RRGMambaFormer: a hybrid transformer-mamba architecture for radiology report generation","volume":"279","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112913","article-title":"Context-enhanced framework for medical image report generation using multimodal contexts","volume":"310","author":"Li","year":"2025","journal-title":"Knowl. Base Syst."},{"key":"10.1016\/j.engappai.2026.114731_bib35","series-title":"Advances in Neural Information Processing Systems","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","author":"Li","year":"2018"},{"key":"10.1016\/j.engappai.2026.114731_bib36","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV). Presented at the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"2851","article-title":"Unify, align and refine: multi-level semantic alignment for radiology report generation","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114731_bib37","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.engappai.2026.114731_bib38","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2023.104281","article-title":"Contrastive pre-training and linear interaction attention-based transformer for universal medical reports generation","volume":"138","author":"Lin","year":"2023","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.engappai.2026.114731_bib39","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Presented at the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"13748","article-title":"Exploring and distilling posterior and prior knowledge for radiology report generation","author":"Liu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114731_bib40","author":"Liu"},{"key":"10.1016\/j.engappai.2026.114731_bib41","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108482","article-title":"Label correlated contrastive learning for medical report generation","volume":"258","author":"Liu","year":"2025","journal-title":"Comput. Methods Progr. Biomed."},{"key":"10.1016\/j.engappai.2026.114731_bib42","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2021.108418","article-title":"Learning multi-level structural information for small organ segmentation","volume":"193","author":"Liu","year":"2022","journal-title":"Signal Process."},{"key":"10.1016\/j.engappai.2026.114731_bib43","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV). Presented at the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"9992","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114731_bib44","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112630","article-title":"Automatic medical report generation combining contrastive learning and feature difference","volume":"305","author":"Lyu","year":"2024","journal-title":"Knowl. Base Syst."},{"key":"10.1016\/j.engappai.2026.114731_bib45","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/s13326-017-0128-y","article-title":"NCBO ontology recommender 2.0: an enhanced approach for biomedical ontology recommendation","volume":"8","author":"Mart\u00ednez-Romero","year":"2017","journal-title":"J. Biomed. Semant."},{"key":"10.1016\/j.engappai.2026.114731_bib46","doi-asserted-by":"crossref","first-page":"10748","DOI":"10.1007\/s10489-024-05739-w","article-title":"ETransCap: efficient transformer for image captioning","volume":"54","author":"Mundu","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.engappai.2026.114731_bib47","series-title":"2023 3rd International Conference on Advanced Research in Computing (ICARC). Presented at the 2023 3rd International Conference on Advanced Research in Computing (ICARC)","first-page":"90","article-title":"Automated radiology report generation using transformers","author":"Nimalsiri","year":"2023"},{"key":"10.1016\/j.engappai.2026.114731_bib48","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2022.102281","article-title":"Radiology report generation for proximal femur fractures using deep classification and language generation models","volume":"128","author":"Paalvast","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.engappai.2026.114731_bib49","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106112","article-title":"Image caption generation using a dual attention mechanism","volume":"123","author":"Padate","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114731_bib50","series-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL \u201902. Presented at the the 40th Annual Meeting","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2001"},{"key":"10.1016\/j.engappai.2026.114731_bib51","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-024-69981-5","article-title":"Multi-modal transformer architecture for medical image analysis and automated report generation","volume":"14","author":"Raminedi","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.engappai.2026.114731_bib52","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1016\/j.procs.2025.04.299","article-title":"An experimentation for generating text-based medical report from chest X-Ray images using attention based deep learning models","volume":"258","author":"Rana","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.engappai.2026.114731_bib53","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Presented at the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Honolulu, HI","first-page":"1179","article-title":"Self-critical sequence training for image captioning","author":"Rennie","year":"2017"},{"key":"10.1016\/j.engappai.2026.114731_bib54","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.107805","article-title":"A spatiotemporal feature-based early-stage cervical cancer diagnostic report generation method using bimodal image","volume":"107","author":"Su","year":"2025","journal-title":"Biomed. Signal Process Control"},{"key":"10.1016\/j.engappai.2026.114731_bib55","author":"Su"},{"key":"10.1016\/j.engappai.2026.114731_bib56","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102823","article-title":"A label information fused medical image report generation framework","volume":"150","author":"Sun","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.engappai.2026.114731_bib57","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2024.100648","article-title":"A comprehensive review on transformer network for natural and medical image analysis","volume":"53","author":"Thirunavukarasu","year":"2024","journal-title":"Computer Science Review"},{"key":"10.1016\/j.engappai.2026.114731_bib58","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1007\/s10278-022-00666-z","article-title":"Analyzing transfer learning of vision transformers for interpreting chest radiography","volume":"35","author":"Usman","year":"2022","journal-title":"J. Digit. Imag."},{"key":"10.1016\/j.engappai.2026.114731_bib59","series-title":"Attention Is all You Need","author":"Vaswani","year":"2023"},{"key":"10.1016\/j.engappai.2026.114731_bib60","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Presented at the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4566","article-title":"CIDEr: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.engappai.2026.114731_bib61","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126622","article-title":"HKRG: hierarchical knowledge integration for radiology report generation","volume":"271","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib62","author":"Wang"},{"key":"10.1016\/j.engappai.2026.114731_bib63","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100033","article-title":"R2GenGPT: Radiology report generation with frozen LLMs","volume":"1","author":"Wang","year":"2023","journal-title":"Meta-Radiology"},{"key":"10.1016\/j.engappai.2026.114731_bib64","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101817","article-title":"Vision-knowledge fusion model for multi-domain medical report generation","volume":"97","author":"Xu","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.engappai.2026.114731_bib65","series-title":"International Conference on Machine Learning. Presented at the 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.engappai.2026.114731_bib66","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","first-page":"457","article-title":"Multimodal recurrent model with attention for automated radiology report generation","author":"Xue","year":"2018"},{"key":"10.1016\/j.engappai.2026.114731_bib67","doi-asserted-by":"crossref","first-page":"3541","DOI":"10.1007\/s40747-023-01341-8","article-title":"Exploring better image captioning with grid features","volume":"10","author":"Yan","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.engappai.2026.114731_bib68","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2025.116781","article-title":"Explainable deep learning method for power system stability evaluation with incomplete voltage data based on transfer learning","volume":"247","author":"Yang","year":"2025","journal-title":"Measurement"},{"key":"10.1016\/j.engappai.2026.114731_bib69","article-title":"Explainable ensemble learning method for OCT detection with transfer learning","volume":"19","author":"Yang","year":"2024","journal-title":"PLoS One"},{"key":"10.1016\/j.engappai.2026.114731_bib70","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129784","article-title":"CG-TRAN: a novel multi-label retinal disease classification model with partially known pathologies","volume":"298","author":"Yang","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib71","doi-asserted-by":"crossref","DOI":"10.1002\/mp.18003","article-title":"Multi\u2010class brain tumor diagnosis using MRI: a dynamic reinforcement ensemble learning approach","volume":"52","author":"Yang","year":"2025","journal-title":"Med. Phys."},{"key":"10.1016\/j.engappai.2026.114731_bib72","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.109247","article-title":"Adaptive reinforcement ensemble transfer learning for robust lung tumor detection","volume":"114","author":"Yang","year":"2026","journal-title":"Biomed. Signal Process Control"},{"key":"10.1016\/j.engappai.2026.114731_bib73","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1109\/JBHI.2024.3350077","article-title":"TSGET: Two-stage global enhanced transformer for automatic radiology report generation","volume":"28","author":"Yi","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.engappai.2026.114731_bib74","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","first-page":"72","article-title":"AlignTransformer: hierarchical alignment of visual regions and disease tags for medical report generation","author":"You","year":"2021"},{"key":"10.1016\/j.engappai.2026.114731_bib75","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124644","article-title":"CheXReport: a transformer-based architecture to generate chest X-ray reports suggestions","volume":"255","author":"Zeiser","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.engappai.2026.114731_bib76","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2023.107979","article-title":"AERMNet: attention-enhanced relational memory network for medical image report generation","volume":"244","author":"Zeng","year":"2024","journal-title":"Comput. Methods Progr. Biomed."},{"key":"10.1016\/j.engappai.2026.114731_bib77","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.patrec.2025.04.036","article-title":"Integrating clinical knowledge and imaging for medical report generation","volume":"195","author":"Zhao","year":"2025","journal-title":"Pattern Recognit. Lett."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010134?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010134?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T20:31:33Z","timestamp":1778099493000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626010134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":77,"alternative-id":["S0952197626010134"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114731","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An interpretable multimodal transformer for medical report generation via hierarchical semantics and clinical labeling","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114731","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":"114731"}}