{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T13:05:18Z","timestamp":1784898318970,"version":"3.55.0"},"reference-count":102,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.eswa.2026.131946","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:57:49Z","timestamp":1772643469000},"page":"131946","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Automated diagnostic reporting from medical images using deep learning architectures: Methods, challenges, and future directions"],"prefix":"10.1016","volume":"317","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4137-6707","authenticated-orcid":false,"given":"Menatalla","family":"Haggag","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1652-0492","authenticated-orcid":false,"given":"Abbes","family":"Amira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2508-4496","authenticated-orcid":false,"given":"Fatih","family":"Kurugollu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7559-5297","authenticated-orcid":false,"given":"Habib","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8128-5498","authenticated-orcid":false,"given":"Bassel","family":"Soudan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.131946_bib0001","doi-asserted-by":"crossref","first-page":"121880","DOI":"10.1109\/ACCESS.2025.3587988","article-title":"Privacy-aware detection for large language models using a hybrid biLSTM-HMM approach","volume":"13","author":"Abbasalizadeh","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.131946_bib0002","unstructured":"Alkhaldi, A., Alnajim, R., Alabdullatef, L., Alyahya, R., Chen, J., Zhu, D., Alsinan, A., & Elhoseiny, M. (2024). Minigpt-med: Large language model as a general interface for radiology diagnosis. arXiv preprint arXiv: 2407.04106."},{"key":"10.1016\/j.eswa.2026.131946_bib0003","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"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0004","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.232756","article-title":"Chatbots and large language models in radiology: a practical primer for clinical and research applications","volume":"310","author":"Bhayana","year":"2024","journal-title":"Radiology"},{"key":"10.1016\/j.eswa.2026.131946_bib0005","unstructured":"Chambon, P., Delbrouck, J.-B., Sounack, T., Huang, S.-C., Chen, Z., Varma, M., Truong, S. Q. H., Chuong, C. T., & Langlotz, C. P. (2024). Chexpert plus: Augmenting a large chest x-ray dataset with text radiology reports, patient demographics and additional image formats. arXiv preprint arXiv: 2405.19538."},{"key":"10.1016\/j.eswa.2026.131946_bib0006","series-title":"2024 11th international conference on wireless networks and mobile communications (WINCOM)","first-page":"1","article-title":"A multi-modal feature fusion-based approach for chest x-ray report generation","author":"Cheddi","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0007","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., & Zhou, Y. (2021). Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv: 2102.04306."},{"key":"10.1016\/j.eswa.2026.131946_bib0008","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.eswa.2026.131946_bib0009","unstructured":"Codella, N. C. F., Jin, Y., Jain, S., Gu, Y., Lee, H. H., Abacha, A. B., Santamaria-Pang, A., Guyman, W., Sangani, N., Zhang, S., Poon, H., Hyland, S., Bannur, S., Alvarez-Valle, J., Li, X., Garrett, J., McMillan, A., Rajguru, G., Maddi, M., Vijayrania, N., Bhimai, R., Mecklenburg, N., Jain, R., Holstein, D., Gaur, N., Aski, V., Hwang, J.-N., Lin, T., Tarapov, I., Lungren, M., & Wei, M. (2024). Medimageinsight: An open-source embedding model for general domain medical imaging. arXiv preprint arXiv: 2410.06542."},{"issue":"2","key":"10.1016\/j.eswa.2026.131946_bib0010","doi-asserted-by":"crossref","first-page":"39","DOI":"10.3390\/asi8020039","article-title":"Multimodal AI and large language models for orthopantomography radiology report generation and q&a","volume":"8","author":"Dasanayaka","year":"2025","journal-title":"Applied System Innovation"},{"key":"10.1016\/j.eswa.2026.131946_bib0011","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics: system demonstrations","first-page":"23","article-title":"ViLMedic: a framework for research at the intersection of vision and language in medical AI","author":"Delbrouck","year":"2022"},{"key":"10.1016\/j.eswa.2026.131946_bib0012","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19358","article-title":"Eva: exploring the limits of masked visual representation learning at scale","author":"Fang","year":"2023"},{"key":"10.1016\/j.eswa.2026.131946_bib0013","article-title":"Adf-oct: an advanced assistive diagnosis framework for study-level macular optical coherence tomography","volume":"117","author":"Gao","year":"2024","journal-title":"Information Fusion"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0014","article-title":"Automatic medical report generation: methods and applications","volume":"13","author":"Guo","year":"2024","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"10.1016\/j.eswa.2026.131946_bib0015","series-title":"2024\u202fIEEE international conference on bioinformatics and biomedicine (BIBM)","first-page":"4225","article-title":"Automatic radiology report generation: a comprehensive review and innovative framework","author":"Hamma","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0016","unstructured":"Hardy, R., Kim, S. E., Ro, D. H., & Rajpurkar, P. (2024). Rextrust: A model for fine-grained hallucination detection in ai-generated radiology reports. arXiv preprint arXiv: 2412.15264."},{"key":"10.1016\/j.eswa.2026.131946_bib0017","series-title":"2022 19th international bhurban conference on applied sciences and technology (IBCAST)","first-page":"337","article-title":"Analysis of multimodal representation learning across medical images and reports using multiple vision and language pre-trained models","author":"Hassan","year":"2022"},{"key":"10.1016\/j.eswa.2026.131946_bib0018","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"7514","article-title":"Clipscore: a reference-free evaluation metric for image captioning","author":"Hessel","year":"2021"},{"key":"10.1016\/j.eswa.2026.131946_bib0019","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 Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0020","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.2026.131946_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2025.108677","article-title":"Pathology report generation from whole slide images with knowledge retrieval and multi-level regional feature selection","volume":"263","author":"Hu","year":"2025","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.1016\/j.eswa.2026.131946_bib0022","series-title":"Proceedings of the 6th clinical natural language processing workshop","first-page":"283","article-title":"Serpent-vlm: self-refining radiology report generation using vision language models","author":"Kapadnis","year":"2024"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0023","article-title":"Deep neural models for automated multi-task diagnostic scan management\u2013quality enhancement, view classification and report generation","volume":"8","author":"Karthik","year":"2021","journal-title":"Biomedical Physics & Engineering Express"},{"key":"10.1016\/j.eswa.2026.131946_bib0024","series-title":"2024 international conference on artificial intelligence in information and communication (ICAIIC)","first-page":"617","article-title":"Ftt: fourier transform based transformer for brain ct report generation","author":"Kim","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0025","series-title":"European conference on computer vision","first-page":"468","article-title":"Improving medical multi-modal contrastive learning with expert annotations","author":"Kumar","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0026","unstructured":"Lai, H., Jiang, Z., Yao, Q., Wang, R., He, Z., Tao, X., Wei, W., Lv, W., & Zhou, S. K. (2024). E3d-GPT: Enhanced 3d visual foundation for medical vision-language model. arXiv preprint arXiv: 2410.14200."},{"issue":"23","key":"10.1016\/j.eswa.2026.131946_bib0027","doi-asserted-by":"crossref","DOI":"10.3390\/jcm13237337","article-title":"Revolutionizing radiology with natural language processing and chatbot technologies: a narrative umbrella review on current trends and future directions","volume":"13","author":"Lastrucci","year":"2024","journal-title":"Journal of Clinical Medicine"},{"key":"10.1016\/j.eswa.2026.131946_bib0028","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.131946_bib0029","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 Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0030","series-title":"International conference on machine learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0031","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TMI.2024.3424978","article-title":"Ultrasound report generation with cross-modality feature alignment via unsupervised guidance","volume":"44","author":"Li","year":"2025","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.131946_bib0032","series-title":"Proceedings of the 32nd ACM international conference on information and knowledge management","first-page":"1308","article-title":"Harnessing the power of pre-trained vision-language models for efficient medical report generation","author":"Li","year":"2023"},{"key":"10.1016\/j.eswa.2026.131946_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128555","article-title":"Ultrasound report generation with fuzzy knowledge and multi-modal large language model","volume":"292","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2023.101273","article-title":"Deep learning approaches to automatic radiology report generation: a systematic review","volume":"39","author":"Liao","year":"2023","journal-title":"Informatics in Medicine Unlocked"},{"key":"10.1016\/j.eswa.2026.131946_bib0035","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.eswa.2026.131946_bib0036","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Medical Image Analysis"},{"issue":"5","key":"10.1016\/j.eswa.2026.131946_bib0037","doi-asserted-by":"crossref","first-page":"3332","DOI":"10.1109\/TPAMI.2025.3534586","article-title":"Aligning, autoencoding and prompting large language models for novel disease reporting","volume":"47","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"10.1016\/j.eswa.2026.131946_bib0038","doi-asserted-by":"crossref","first-page":"3786","DOI":"10.1109\/TNNLS.2021.3099165","article-title":"Medical-vlbert: medical visual language bert for covid-19 ct report generation with alternate learning","volume":"32","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.131946_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2024.102486","article-title":"Automatic medical report generation based on deep learning: a state of the art survey","volume":"120","author":"Liu","year":"2025","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"10.1016\/j.eswa.2026.131946_bib0040","doi-asserted-by":"crossref","first-page":"5987","DOI":"10.1109\/TMM.2023.3342691","article-title":"From observation to concept: a flexible multi-view paradigm for medical report generation","volume":"26","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"issue":"24","key":"10.1016\/j.eswa.2026.131946_bib0041","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6560\/ad0a5a","article-title":"Deep learning for fast super-resolution ultrasound microvessel imaging","volume":"68","author":"Luan","year":"2023","journal-title":"Physics in Medicine & Biology"},{"key":"10.1016\/j.eswa.2026.131946_bib0042","unstructured":"Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., & Agarwal, S. (2020). Language models are few-shot learners. arXiv preprint arXiv: 2005.14165, 1, 3."},{"key":"10.1016\/j.eswa.2026.131946_bib0043","series-title":"Proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: Human language technologies","first-page":"5288","article-title":"Improving factual completeness and consistency of image-to-text radiology report generation","author":"Miura","year":"2021"},{"key":"10.1016\/j.eswa.2026.131946_bib0044","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"19589","article-title":"Evaluating the evaluator: measuring llms\u2019 adherence to task evaluation instructions","volume":"vol. 39","author":"Murugadoss","year":"2025"},{"key":"10.1016\/j.eswa.2026.131946_bib0045","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.clinimag.2021.06.033","article-title":"Understanding artificial intelligence based radiology studies: CNN architecture","volume":"80","author":"Mutasa","year":"2021","journal-title":"Clinical Imaging"},{"key":"10.1016\/j.eswa.2026.131946_bib0046","series-title":"Findings of the association for computational linguistics: EMNLP 2024","first-page":"374","article-title":"Green: generative radiology report evaluation and error notation","author":"Ostmeier","year":"2024"},{"issue":"23","key":"10.1016\/j.eswa.2026.131946_bib0047","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.3390\/math12233852","article-title":"Survey of quantum generative adversarial networks (QGAN) to generate images","volume":"12","author":"Pajuhanfard","year":"2024","journal-title":"Mathematics"},{"issue":"2","key":"10.1016\/j.eswa.2026.131946_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2024.100080","article-title":"Opportunities and challenges in the application of large artificial intelligence models in radiology","volume":"2","author":"Pan","year":"2024","journal-title":"Meta-Radiology"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0049","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12938-023-01113-y","article-title":"A survey on automatic generation of medical imaging reports based on deep learning","volume":"22","author":"Pang","year":"2023","journal-title":"Biomedical Engineering Online"},{"key":"10.1016\/j.eswa.2026.131946_bib0050","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":"10","key":"10.1016\/j.eswa.2026.131946_bib0051","doi-asserted-by":"crossref","first-page":"17841","DOI":"10.1109\/TNNLS.2025.3587687","article-title":"M4CXR: Exploring multi-task potentials of multi-modal large language models for chest x-ray interpretation","volume":"36","author":"Park","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.131946_bib0052","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.131946_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103264","article-title":"From vision to text: a comprehensive review of natural image captioning in medical diagnosis and radiology report generation","volume":"97","author":"Reale-Nosei","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.131946_bib0054","unstructured":"Research and Markets (2021). Global medical imaging market report 2021\u20132026: Analysis by x-ray, ultrasound, MRI, CT scan, nuclear imaging. https:\/\/www.businesswire.com\/news\/home\/20210608005582\/en\/Global- Medical-Imaging-Market-Report-2021-2026-Analysis-by-X-Ray-Ultrasound-MRI-CT-Scan-Nuclear-Imaging\u2014ResearchAndMarkets.com. Accessed: 2025-04-20."},{"issue":"6","key":"10.1016\/j.eswa.2026.131946_bib0055","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1067\/j.cpradiol.2024.07.007","article-title":"ChatGPT and assistive AI in structured radiology reporting: a systematic review","volume":"53","author":"Sacoransky","year":"2024","journal-title":"Current Problems in Diagnostic Radiology"},{"key":"10.1016\/j.eswa.2026.131946_bib0056","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"7881","article-title":"Bleurt: learning robust metrics for text generation","author":"Sellam","year":"2020"},{"key":"10.1016\/j.eswa.2026.131946_bib0057","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TNSRE.2023.3346955","article-title":"B2-Vit net: broad vision transformer network with broad attention for seizure prediction","volume":"32","author":"Shi","year":"2024","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"10.1016\/j.eswa.2026.131946_bib0058","article-title":"Miter: medical image\u2013text joint adaptive pretraining with multi-level contrastive learning","volume":"238","author":"Shu","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0059","unstructured":"Shui, Z., Zhang, J., Cao, W., Wang, S., Guo, R., Lu, L., Yang, L., Ye, X., Liang, T., Zhang, Q., & Zhang, L. (2025). Large-scale and fine-grained vision-language pre-training for enhanced CT image understanding. arXiv preprint arXiv: 2501.14548."},{"key":"10.1016\/j.eswa.2026.131946_bib0060","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.2026.131946_bib0061","doi-asserted-by":"crossref","unstructured":"Smit, A., Jain, S., Rajpurkar, P., Pareek, A., Ng, A. Y., & Lungren, M. P. (2020). Chexbert: combining automatic labelers and expert annotations for accurate radiology report labeling using BERT. arXiv preprint arXiv: 2004.09167.","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"10.1016\/j.eswa.2026.131946_bib0062","article-title":"Sci2txt: automated report generation of low-resolution SPECT bone scintigrams using spatial-position-aware and hierarchical features","volume":"111","author":"Song","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.eswa.2026.131946_bib0063","doi-asserted-by":"crossref","DOI":"10.1109\/TMM.2024.3428349","article-title":"Centerformer: a novel cluster center enhanced transformer for unconstrained dental plaque segmentation","volume":"26","author":"Song","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131946_bib0064","article-title":"Medkit: multi-level feature distillation with knowledge injection for radiology report generation","volume":"296","author":"Su","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128328","article-title":"Hybrid graph-based radiology report generation","volume":"289","author":"Sun","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0066","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of vision transformers and convolutional neural networks in medical image analysis: a systematic review","volume":"48","author":"Takahashi","year":"2024","journal-title":"Journal of Medical Systems"},{"key":"10.1016\/j.eswa.2026.131946_bib0067","article-title":"Work like a doctor: unifying scan localizer and dynamic generator for automated computed tomography report generation","volume":"237","author":"Tang","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0068","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/JTEHM.2025.3536441","article-title":"Cross-modal augmented transformer for automated medical report generation","volume":"13","author":"Tang","year":"2025","journal-title":"IEEE Journal of Translational Engineering in Health and Medicine"},{"key":"10.1016\/j.eswa.2026.131946_bib0069","unstructured":"The Royal College of Radiologists(2023). Clinical radiology UK workforce census 2023. https:\/\/www.rcr.ac.uk\/media\/5befglss\/rcr-census-clinical-radiology-workforce-census-2023.pdf. Accessed: 2025-04-20."},{"key":"10.1016\/j.eswa.2026.131946_bib0070","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"},{"key":"10.1016\/j.eswa.2026.131946_bib0071","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 Systems with Applications"},{"issue":"4","key":"10.1016\/j.eswa.2026.131946_bib0072","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1109\/JBHI.2024.3354712","article-title":"Camanet: class activation map guided attention network for radiology report generation","volume":"28","author":"Wang","year":"2024","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.1016\/j.eswa.2026.131946_bib0073","unstructured":"Wang, L., Wang, H., Yang, H., Mao, J., Yang, Z., Shen, J., & Li, X. (2024b). Interpretable bilingual multimodal large language model for diverse biomedical tasks. arXiv preprint arXiv: 2410.18387."},{"issue":"9","key":"10.1016\/j.eswa.2026.131946_bib0074","article-title":"Flat-lattice-CNN: a model for chinese medical-named-entity recognition","volume":"20","author":"Wang","year":"2025","journal-title":"PloS one"},{"key":"10.1016\/j.eswa.2026.131946_bib0075","unstructured":"Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022). Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv: 2203.11171."},{"key":"10.1016\/j.eswa.2026.131946_bib0076","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127374","article-title":"Trust it or not: confidence-guided automatic radiology report generation","volume":"578","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.131946_bib0077","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"647","article-title":"Trrg: towards truthful radiology report generation with cross-modal disease clue enhanced large language models","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131946_bib0078","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8250","article-title":"Llm-rg4: flexible and factual radiology report generation across diverse input contexts","volume":"vol. 39","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.131946_bib0079","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2433","article-title":"A self-boosting framework for automated radiographic report generation","author":"Wang","year":"2021"},{"issue":"1","key":"10.1016\/j.eswa.2026.131946_bib0080","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.2026.131946_bib0081","series-title":"2024\u202fIEEE international symposium on biomedical imaging (ISBI)","first-page":"1","article-title":"Maken: improving medical report generation with adapter tuning and knowledge enhancement in vision-language foundation models","author":"Wu","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0082","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126839","article-title":"Multichannel feature fusion network-based technique for heart sound signal classification and recognition","volume":"273","author":"Xiong","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.131946_bib0083","doi-asserted-by":"crossref","first-page":"5647","DOI":"10.1109\/TIFS.2025.3574959","article-title":"Anonymity-enhanced sequential multi-signer ring signature for secure medical data sharing in ioMT","volume":"20","author":"Xu","year":"2025","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.1016\/j.eswa.2026.131946_bib0084","unstructured":"Xu, L., Sun, H., Ni, Z., Li, H., & Zhang, S. (2024). Medvilam: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation. arXiv preprint arXiv: 2409.19684."},{"key":"10.1016\/j.eswa.2026.131946_bib0085","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"},{"key":"10.1016\/j.eswa.2026.131946_bib0086","series-title":"2024 43rd chinese control conference (CCC)","first-page":"8637","article-title":"Cross-modal network of mining text-knowledge for radiology report generation","author":"Yan","year":"2024"},{"key":"10.1016\/j.eswa.2026.131946_bib0087","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102798","article-title":"Radiology report generation with a learned knowledge base and multi-modal alignment","volume":"86","author":"Yang","year":"2023","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.131946_bib0088","doi-asserted-by":"crossref","DOI":"10.1016\/j.bios.2025.117408","article-title":"A hybrid bioelectronic retina-probe interface for object recognition","volume":"279","author":"Ye","year":"2025","journal-title":"Biosensors and Bioelectronics"},{"key":"10.1016\/j.eswa.2026.131946_bib0089","series-title":"2024\u202fIEEE international conference on bioinformatics and biomedicine (BIBM)","first-page":"2780","article-title":"C2RG: Parameter-efficient adaptation of 3d vision and language foundation model for coronary CTA report generation","author":"Ye","year":"2024"},{"issue":"23","key":"10.1016\/j.eswa.2026.131946_bib0090","doi-asserted-by":"crossref","DOI":"10.3390\/jcm13237092","article-title":"Auto-rad: end-to-end report generation from lumber spine MRI using vision\u2013language model","volume":"13","author":"Yeasin","year":"2024","journal-title":"Journal of Clinical Medicine"},{"issue":"9","key":"10.1016\/j.eswa.2026.131946_bib0091","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"},{"issue":"7","key":"10.1016\/j.eswa.2026.131946_bib0092","doi-asserted-by":"crossref","first-page":"5303","DOI":"10.1109\/JBHI.2025.3535699","article-title":"Adapter-enhanced hierarchical cross-modal pre-training for lightweight medical report generation","volume":"29","author":"Yu","year":"2025","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"20","key":"10.1016\/j.eswa.2026.131946_bib0093","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6560\/acf98f","article-title":"Deep learning for fast denoising filtering in ultrasound localization microscopy","volume":"68","author":"Yu","year":"2023","journal-title":"Physics in Medicine & Biology"},{"key":"10.1016\/j.eswa.2026.131946_bib0094","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"},{"key":"10.1016\/j.eswa.2026.131946_bib0095","doi-asserted-by":"crossref","first-page":"9736","DOI":"10.1109\/TMM.2024.3397191","article-title":"Unidcp: unifying multiple medical vision-language tasks via dynamic cross-modal learnable prompts","volume":"26","author":"Zhan","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131946_bib0096","doi-asserted-by":"crossref","first-page":"4706","DOI":"10.1109\/TMM.2023.3325965","article-title":"Multi-task paired masking with alignment modeling for medical vision-language pre-training","volume":"26","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.131946_bib0097","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019). Bertscore: Evaluating text generation with bert. arXiv preprint arXiv: 1904.09675."},{"issue":"4","key":"10.1016\/j.eswa.2026.131946_bib0098","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2024.100103","article-title":"Potential of multimodal large language models for data mining of medical images and free-text reports","volume":"2","author":"Zhang","year":"2024","journal-title":"Meta-Radiology"},{"key":"10.1016\/j.eswa.2026.131946_bib0099","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.ins.2023.01.020","article-title":"Secure internet of things (iot) using a novel brooks iyengar quantum byzantine agreement-centered blockchain networking (BIQBA-BCN) model in smart healthcare","volume":"629","author":"Zhao","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.eswa.2026.131946_bib0100","series-title":"Findings of the association for computational linguistics: EMNLP 2024","first-page":"16542","article-title":"See detail say clear: towards brain CT report generation via pathological clue-driven representation learning","author":"Zheng","year":"2024"},{"issue":"5","key":"10.1016\/j.eswa.2026.131946_bib0101","doi-asserted-by":"crossref","first-page":"3293","DOI":"10.1109\/JBHI.2024.3417849","article-title":"Multi-modality regional alignment network for covid x-ray survival prediction and report generation","volume":"29","author":"Zhong","year":"2024","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.1016\/j.eswa.2026.131946_bib0102","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.121868","article-title":"Open-world multi-modal machine learning decision model based on uncertain data analysis for fetal heart diagnosis","volume":"701","author":"Zhu","year":"2025","journal-title":"Information Sciences"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426008596?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426008596?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T12:41:37Z","timestamp":1784896897000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426008596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":102,"alternative-id":["S0957417426008596"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131946","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automated diagnostic reporting from medical images using deep learning architectures: Methods, challenges, and future directions","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.131946","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":"131946"}}