{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:13:26Z","timestamp":1774041206642,"version":"3.50.1"},"reference-count":103,"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\/501100007933","name":"Liaoning University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007933","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015226","name":"Shengjing Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Liaoning Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2025-BS-0546"],"award-info":[{"award-number":["2025-BS-0546"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.131921","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T17:03:03Z","timestamp":1772557383000},"page":"131921","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Sparsity-guided multimodal self-supervised learning for expert-level multi-task chest X-ray diagnosis"],"prefix":"10.1016","volume":"318","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7132-0755","authenticated-orcid":false,"given":"Si-Qi","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1701-8557","authenticated-orcid":false,"given":"Cheng","family":"Zhen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4685-8427","authenticated-orcid":false,"given":"Bai-Qiang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0556-2263","authenticated-orcid":false,"given":"Jun-Gang","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1977-303X","authenticated-orcid":false,"given":"Jing-Shan","family":"Huang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131921_bib0001","doi-asserted-by":"crossref","unstructured":"Ahmad, M., Usman, S., Batyrshin, I., Muzammil, M., Sajid, K., Hasnain, M., Jalal, M., & Sidorov, G. (2025). Automated diagnosis of lung diseases using vision transformer: A comparative study on chest X-ray classification. arXiv preprint arXiv: 2503.18973.","DOI":"10.53555\/26ef5855"},{"key":"10.1016\/j.eswa.2026.131921_bib0002","doi-asserted-by":"crossref","first-page":"26626","DOI":"10.1109\/ACCESS.2024.3367360","article-title":"CNX-B2: A novel CNN-transformer approach for chest X-ray medical report generation","volume":"12","author":"Alqahtani","year":"2024","journal-title":"Ieee Access"},{"key":"10.1016\/j.eswa.2026.131921_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105408","article-title":"An automated chest X-ray analysis for COVID-19, tuberculosis, and pneumonia employing ensemble learning approach","volume":"87","author":"Amin","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.eswa.2026.131921_bib0004","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J. et al. (2025). Qwen2. 5-VL technical report. arXiv preprint arXiv: 2502.13923."},{"key":"10.1016\/j.eswa.2026.131921_bib0005","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.eswa.2026.131921_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15016","article-title":"Learning to exploit temporal structure for biomedical vision-language processing","author":"Bannur","year":"2023"},{"key":"10.1016\/j.eswa.2026.131921_bib0007","doi-asserted-by":"crossref","first-page":"42949","DOI":"10.1109\/ACCESS.2025.3546131","article-title":"Knowledge distillation and transformer based framework for automatic spine CT report generation","volume":"13","author":"Batool","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131921_bib0008","series-title":"European conference on computer vision","first-page":"1","article-title":"Making the most of text semantics to improve biomedical vision\u2013language processing","author":"Boecking","year":"2022"},{"key":"10.1016\/j.eswa.2026.131921_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101797","article-title":"PadChest: A large chest X-ray image dataset with multi-label annotated reports","volume":"66","author":"Bustos","year":"2020","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.131921_bib0010","unstructured":"Cai, Y., Zhang, J., He, H., He, X., Tong, A., Gan, Z., Wang, C., Xue, Z., Liu, Y., & Bai, X. (2024). LLaVA-KD: A framework of distilling multimodal large language models. arXiv preprint arXiv: 2410.16236."},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0011","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1038\/s41746-024-01260-z","article-title":"Improving prognostic accuracy in lung transplantation using unique features of isolated human lung radiographs","volume":"7","author":"Chao","year":"2024","journal-title":"NPJ Digital Medicine"},{"key":"10.1016\/j.eswa.2026.131921_bib0012","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"9494","article-title":"Fine-grained image-text alignment in medical imaging enables explainable cyclic image-report generation","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.131921_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.131084","article-title":"A knowledge-guided feature selection method for lung cancer immunotherapy response prediction via pathology image analysis","volume":"307","author":"Chen","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0014","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.-H., & Wan, X. (2020a). Generating radiology reports via memory-driven transformer. arXiv preprint arXiv: 2010.16056.","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"10.1016\/j.eswa.2026.131921_bib0015","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP)","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.131921_bib0016","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"},{"issue":"6","key":"10.1016\/j.eswa.2026.131921_bib0017","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae596","article-title":"Precision DNA methylation typing via hierarchical clustering of nanopore current signals and attention-based neural network","volume":"25","author":"Dai","year":"2024","journal-title":"Briefings in Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131921_bib0018","doi-asserted-by":"crossref","first-page":"159002","DOI":"10.1109\/ACCESS.2025.3607639","article-title":"Improving medical X-ray imaging diagnosis with attention mechanisms and robust transfer learning techniques","volume":"13","author":"Das","year":"2025","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.eswa.2026.131921_bib0019","article-title":"Curation of the candid-ptx dataset with free-text reports","volume":"3","author":"Feng","year":"2021","journal-title":"Radiology: Artificial Intelligence"},{"issue":"2","key":"10.1016\/j.eswa.2026.131921_bib0020","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1109\/TMI.2022.3224660","article-title":"Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: Applications to chest X-ray analysis","volume":"42","author":"Gaggion","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131921_bib0021","doi-asserted-by":"crossref","unstructured":"Gaggion, N., Mosquera, C., Aineseder, M., Mansilla, L., Milone, D., & Ferrante, E. (2024). Chexmask database: A large-scale dataset of anatomical segmentation masks for chest X-ray images. Scientific Data, 11(1), 511.","DOI":"10.1038\/s41597-024-03358-1"},{"key":"10.1016\/j.eswa.2026.131921_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107550","article-title":"Systematic comparison of genome information processing and boundary recognition tools used for genomic island detection","volume":"166","author":"Guo","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"5","key":"10.1016\/j.eswa.2026.131921_bib0023","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1007\/s10489-020-02010-w","article-title":"An automatic approach based on CNN architecture to detect covid-19 disease from chest X-ray images: An automatic approach based on CNN architecture to detect covid-19 disease from chest X-ray images","volume":"51","author":"Hira","year":"2021","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.131921_bib0024","series-title":"Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"8108","article-title":"ORGAN: Observation-guided radiology report generation via tree reasoning","author":"Hou","year":"2023"},{"key":"10.1016\/j.eswa.2026.131921_bib0025","article-title":"MambaGen: Efficient visual representation learning for automatic radiology report generation","volume":"298","author":"Hou","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0026","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3942","article-title":"Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition","author":"Huang","year":"2021"},{"key":"10.1016\/j.eswa.2026.131921_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113233","article-title":"DCSSGA-UNet: Biomedical image segmentation with densenet channel spatial and semantic guidance attention","volume":"314","author":"Hussain","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.131921_bib0028","unstructured":"Jain, S., Agrawal, A., Saporta, A., Truong, S. Q. H., Duong, D. N., Bui, T., Chambon, P., Zhang, Y., Lungren, M. P., Ng, A. Y. et al. (2021). RadGraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv: 2106.14463."},{"key":"10.1016\/j.eswa.2026.131921_bib0029","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2607","article-title":"PromptMRG: Diagnosis-driven prompts for medical report generation","volume":"vol. 38","author":"Jin","year":"2024"},{"issue":"11","key":"10.1016\/j.eswa.2026.131921_bib0030","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad651","article-title":"MedCPT: Contrastive pre-trained transformers with large-scale pubmed search logs for zero-shot biomedical information retrieval","volume":"39","author":"Jin","year":"2023","journal-title":"Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131921_bib0031","doi-asserted-by":"crossref","unstructured":"Johnson, A. E. W., Pollard, T. J., Greenbaum, N. R., Lungren, M. P., Deng, C.-y., Peng, Y., Lu, Z., Mark, R. G., Berkowitz, S. J., & Horng, S. (2019a). MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv: 1901.07042.","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"3","key":"10.1016\/j.eswa.2026.131921_bib0032","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2019","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.eswa.2026.131921_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118942","article-title":"A weakly supervised approach for thoracic diseases detection","volume":"213","author":"Kabir","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11137","article-title":"CARZero: Cross-attention alignment for radiology zero-shot classification","author":"Lai","year":"2024"},{"key":"10.1016\/j.eswa.2026.131921_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125362","article-title":"Hybrid multiple instance learning network for weakly supervised medical image classification and localization","volume":"260","author":"Lai","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0036","unstructured":"Li, B., Huang, W., Shen, Y., Wang, Y., Lin, S., Lin, J., You, L., Zhang, Y., Li, K., Sun, X. et al. (2025a). LlaVA-RadZ: Can multimodal large language models effectively tackle zero-shot radiology recognition?arXiv preprint arXiv: 2503.07487."},{"key":"10.1016\/j.eswa.2026.131921_bib0037","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":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131921_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiolchem.2025.108483","article-title":"scDGG: Dynamic gene graphs for enhancing spatial and temporal analysis of single-cell RNA sequencing data","volume":"118","author":"Li","year":"2025","journal-title":"Computational Biology and Chemistry"},{"key":"10.1016\/j.eswa.2026.131921_bib0039","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3334","article-title":"Dynamic graph enhanced contrastive learning for chest x-ray report generation","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.131921_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122964","article-title":"BioDynGrap: Biomedical event prediction via interpretable learning framework for heterogeneous dynamic graphs","volume":"244","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"12","key":"10.1016\/j.eswa.2026.131921_bib0041","doi-asserted-by":"crossref","first-page":"4253","DOI":"10.1109\/TMI.2024.3421599","article-title":"An organ-aware diagnosis framework for radiology report generation","volume":"43","author":"Li","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131921_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.131076","article-title":"KA-DDI: A knowledge-adaptive contrastive learning framework for drug-drug interaction prediction","volume":"308","author":"Li","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0043","series-title":"Text summarization branches out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"issue":"7","key":"10.1016\/j.eswa.2026.131921_bib0044","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.1109\/TMI.2024.3372638","article-title":"Multi-grained radiology report generation with sentence-level image-language contrastive learning","volume":"43","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0045","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-024-01339-7","article-title":"A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosis","volume":"8","author":"Liu","year":"2025","journal-title":"npj Digital Medicine"},{"key":"10.1016\/j.eswa.2026.131921_bib0046","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"8721","article-title":"In-context learning for zero-shot medical report generation","author":"Liu","year":"2024"},{"issue":"12","key":"10.1016\/j.eswa.2026.131921_bib0047","doi-asserted-by":"crossref","first-page":"5848","DOI":"10.1109\/JBHI.2023.3313886","article-title":"Attention-guided partial domain adaptation for automated pneumonia diagnosis from chest x-ray images","volume":"27","author":"Liu","year":"2023","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.1016\/j.eswa.2026.131921_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108243","article-title":"Multi-task driven explainable diagnosis of COVID-19 using chest X-ray images","volume":"122","author":"Malhotra","year":"2022","journal-title":"Pattern recognition"},{"key":"10.1016\/j.eswa.2026.131921_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122029","article-title":"Applications of machine learning algorithms to support COVID-19 diagnosis using X-rays data information","volume":"238","author":"Medeiros","year":"2024","journal-title":"Expert Systems With Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0050","unstructured":"Miao, Q., Liu, K., Ma, Z., Li, Y., Kang, X., Liu, R., Liu, T., Xie, K., & Jiao, Z. (2025). EVOKE: Elevating chest X-ray report generation via multi-view contrastive learning and patient-specific knowledge. https:\/\/arxiv.org\/abs\/2411.10224."},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0051","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232085","article-title":"Weakly supervised deep learning in radiology","volume":"312","author":"Misera","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.eswa.2026.131921_bib0052","doi-asserted-by":"crossref","unstructured":"Mohamed, Y., Mohamed, N., Abouhashad, K., Tang, F., Atito, S., Jameel, S., Razzak, I., & Zaky, A. B. (2025). DeepChest: Dynamic gradient-free task weighting for effective multi-task learning in chest X-ray classification. arXiv preprint arXiv: 2505.23595.","DOI":"10.1109\/BigData66926.2025.11401482"},{"key":"10.1016\/j.eswa.2026.131921_bib0053","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1109\/ACCESS.2022.3232719","article-title":"Vision transformer and language model based radiology report generation","volume":"11","author":"Mohsan","year":"2022","journal-title":"IEEE Access"},{"issue":"12","key":"10.1016\/j.eswa.2026.131921_bib0054","doi-asserted-by":"crossref","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","article-title":"Multi-modal understanding and generation for medical images and text via vision-language pre-training","volume":"26","author":"Moon","year":"2022","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0055","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":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.131921_bib0056","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2022.107141","article-title":"IEViT: An enhanced vision transformer architecture for chest X-ray image classification","volume":"226","author":"Okolo","year":"2022","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.1016\/j.eswa.2026.131921_bib0057","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128162","article-title":"CLN: A multi-task deep neural network for chest X-ray image localisation and classification","volume":"288","author":"Okolo","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0058","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0059","doi-asserted-by":"crossref","first-page":"3848","DOI":"10.1038\/s41467-022-31514-x","article-title":"Self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation","volume":"13","author":"Park","year":"2022","journal-title":"Nature Communications"},{"key":"10.1016\/j.eswa.2026.131921_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107238","article-title":"Automated detection of covid-19 from chest X-ray scans using an optimized CNN architecture","volume":"104","author":"Pathan","year":"2021","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.131921_bib0061","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102774","article-title":"Generalized pancreatic cancer diagnosis via multiple instance learning and anatomically-guided shape normalization","volume":"86","author":"Qu","year":"2023","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.131921_bib0062","series-title":"Machine learning for healthcare conference","first-page":"650","article-title":"Retrieval augmented chest X-ray report generation using openai GPT models","author":"Ranjit","year":"2023"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0063","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1038\/s41597-022-01608-8","article-title":"Brax, brazilian labeled chest X-ray dataset","volume":"9","author":"Reis","year":"2022","journal-title":"Scientific Data"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0064","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0262209","article-title":"Attention based automated radiology report generation using CNN and LSTM","volume":"17","author":"Sirshar","year":"2022","journal-title":"Plos one"},{"key":"10.1016\/j.eswa.2026.131921_bib0065","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1109\/RBME.2024.3408456","article-title":"Automated radiology report generation: A review of recent advances","volume":"18","author":"Sloan","year":"2024","journal-title":"IEEE Reviews in Biomedical Engineering"},{"key":"10.1016\/j.eswa.2026.131921_bib0066","series-title":"Proceedings of the 2025 conference of the nations of the americas chapter of the association for computational linguistics: Human language technologies (volume 1: Long papers)","first-page":"643","article-title":"Fact-aware multimodal retrieval augmentation for accurate medical radiology report generation","author":"Sun","year":"2025"},{"key":"10.1016\/j.eswa.2026.131921_bib0067","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113166","article-title":"SCA-InceptionUNeXt: A lightweight spatial-channel-attention-based network for efficient medical image segmentation","volume":"311","author":"Tagnamas","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.131921_bib0068","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2021.102920","article-title":"X-ray and CT-scan-based automated detection and classification of covid-19 using convolutional neural networks (CNN)","volume":"69","author":"Thakur","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"issue":"8","key":"10.1016\/j.eswa.2026.131921_bib0069","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nature medicine"},{"issue":"12","key":"10.1016\/j.eswa.2026.131921_bib0070","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","article-title":"Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning","volume":"6","author":"Tiu","year":"2022","journal-title":"Nature Biomedical Engineering"},{"key":"10.1016\/j.eswa.2026.131921_bib0071","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119475","article-title":"MTSS-AAE: Multi-task semi-supervised adversarial autoencoding for covid-19 detection based on chest X-ray images","volume":"216","author":"Ullah","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0072","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124464","article-title":"Iterative enhancement fusion-based cascaded model for detection and localization of multiple disease from CXR-images","volume":"255","author":"Vats","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0073","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4566","article-title":"CIDEr: Consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0074","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1186\/s12880-022-00904-4","article-title":"Computer-aided diagnostic for classifying chest X-ray images using deep ensemble learning","volume":"22","author":"Visu\u00f1a","year":"2022","journal-title":"BMC Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131921_bib0075","series-title":"Computer vision - ECCV 2022: 17th european conference, tel aviv, israel, october 23-27, 2022, proceedings, part XXXV","first-page":"563-579","article-title":"Cross-modal prototype driven network for radiology report generation","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131921_bib0076","article-title":"A multi-label chest x-ray image classification agorithm based on multi-scale and attribute-aware semantic graph","volume":"298","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0077","unstructured":"Wang, X., Li, Y., Wang, F., Wang, S., Li, C., & Jiang, B. (2024a). R2genCSR: Retrieving context samples for large language model based X-ray medical report generation. arXiv preprint arXiv: 2408.09743."},{"key":"10.1016\/j.eswa.2026.131921_bib0078","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, F., Li, Y., Ma, Q., Wang, S., Jiang, B., Li, C., & Tang, J. (2024b). CXPMRG-Bench: Pre-training and benchmarking for X-ray medical report generation on chexpert plus dataset. arXiv preprint arXiv: 2410.00379.","DOI":"10.1109\/CVPR52734.2025.00483"},{"key":"10.1016\/j.eswa.2026.131921_bib0079","unstructured":"Wang, X., Wang, F., Wang, H., Jiang, B., Li, C., Wang, Y., Tian, Y., & Tang, J. (2025b). Activating associative disease-aware vision token memory for LLM-based X-ray report generation. arXiv preprint arXiv: 2501.03458."},{"issue":"10","key":"10.1016\/j.eswa.2026.131921_bib0080","doi-asserted-by":"crossref","first-page":"2803","DOI":"10.1109\/TMI.2022.3171661","article-title":"Automated radiographic report generation purely on transformer: A multicriteria supervised approach","volume":"41","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131921_bib0081","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11558","article-title":"MetransFormer: Radiology report generation by transformer with multiple learnable expert tokens","author":"Wang","year":"2023"},{"issue":"3","key":"10.1016\/j.eswa.2026.131921_bib0082","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"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0083","doi-asserted-by":"crossref","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data","volume":"16","author":"Wu","year":"2025","journal-title":"Nature Communications"},{"key":"10.1016\/j.eswa.2026.131921_bib0084","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"21372","article-title":"MedKLIP: Medical knowledge enhanced language-image pre-training for X-ray diagnosis","author":"Wu","year":"2023"},{"issue":"4","key":"10.1016\/j.eswa.2026.131921_bib0085","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1109\/TCBB.2023.3258455","article-title":"CDT-CAD: Context-aware deformable transformers for end-to-end chest abnormality detection on X-ray images","volume":"21","author":"Wu","year":"2023","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"key":"10.1016\/j.eswa.2026.131921_bib0086","unstructured":"Wu, Z., Chen, X., Pan, Z., Liu, X., Liu, W., Dai, D., Gao, H., Ma, Y., Wu, C., Wang, B. et al. (2024). DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv: 2412.10302."},{"key":"10.1016\/j.eswa.2026.131921_bib0087","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126531","article-title":"An assessment framework of higher-order thinking skills based on fine-tuned large language models","volume":"272","author":"Xiao","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0088","series-title":"Proceedings of the Thirteenth International Conference on Learning Representations","article-title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine","author":"Xie","year":"2025"},{"issue":"18","key":"10.1016\/j.eswa.2026.131921_bib0089","doi-asserted-by":"crossref","first-page":"9800","DOI":"10.1021\/acs.jcim.5c01773","article-title":"MGRL-DDI: Multiview graph representation learning for accurate drug\u2013drug interaction prediction","volume":"65","author":"Xiong","year":"2025","journal-title":"Journal of Chemical Information and Modeling"},{"key":"10.1016\/j.eswa.2026.131921_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127474","article-title":"Super-resolution 3D reconstruction from low-dose biomedical images based on expertized multi-layer refining","volume":"281","author":"Xu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0091","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127582","article-title":"STAF-LLM: A scalable and task-adaptive fine-tuning framework for large language models in medical domain","volume":"281","author":"Xu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0092","unstructured":"Xu, W., Chan, H. P., Li, L., Aljunied, M., Yuan, R., Wang, J., Xiao, C., Chen, G., Liu, C., Li, Z. et al. (2025c). Lingshu: A generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv: 2506.07044."},{"key":"10.1016\/j.eswa.2026.131921_bib0093","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121260","article-title":"Generating radiology reports via auxiliary signal guidance and a memory-driven network","volume":"237","author":"Xue","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"11","key":"10.1016\/j.eswa.2026.131921_bib0094","doi-asserted-by":"crossref","first-page":"4017","DOI":"10.1109\/TMI.2024.3412402","article-title":"Token-mixer: Bind image and text in one embedding space for medical image reporting","volume":"43","author":"Yang","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131921_bib0095","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baac018","article-title":"HPVMD-C: A disease-based mutation database of human papillomavirus in china","volume":"2022","author":"Yang","year":"2022","journal-title":"Database"},{"key":"10.1016\/j.eswa.2026.131921_bib0096","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125355","article-title":"BSD: A multi-task framework for pulmonary disease classification using deep learning","volume":"259","author":"Yi","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131921_bib0097","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 Systems with Applications"},{"issue":"10","key":"10.1016\/j.eswa.2026.131921_bib0098","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","article-title":"Top-down neural attention by excitation backprop","volume":"126","author":"Zhang","year":"2018","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.131921_bib0099","doi-asserted-by":"crossref","first-page":"1","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":"Nature Medicine"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0100","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":"Nature Communications"},{"key":"10.1016\/j.eswa.2026.131921_bib0101","series-title":"Machine learning for healthcare conference","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022"},{"key":"10.1016\/j.eswa.2026.131921_bib0102","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124826","article-title":"LW-XNet for segmentation and classification of skin lesions from dermoscopy images","volume":"255","author":"Zheng","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.1016\/j.eswa.2026.131921_bib0103","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1038\/s41746-025-01807-8","article-title":"Vision-language model for report generation and outcome prediction in CT pulmonary angiogram","volume":"8","author":"Zhong","year":"2025","journal-title":"NPJ Digital Medicine"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426008341?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426008341?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:28:22Z","timestamp":1774034902000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426008341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":103,"alternative-id":["S0957417426008341"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131921","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sparsity-guided multimodal self-supervised learning for expert-level multi-task chest X-ray diagnosis","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131921","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":"131921"}}