{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T14:17:37Z","timestamp":1772979457650,"version":"3.50.1"},"reference-count":42,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"crossref","award":["24511104200"],"award-info":[{"award-number":["24511104200"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"crossref","award":["2024-GZL-RGZN-01013"],"award-info":[{"award-number":["2024-GZL-RGZN-01013"]}],"id":[{"id":"10.13039\/501100008838","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Noncommunicable Chronic Diseases-National Science and Technology Major Project, Research on the Pathogenesis of Pancreatic Cancer and Novel Strategies for Precision Medicine","award":["2025ZD0552303"],"award-info":[{"award-number":["2025ZD0552303"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Pediatric respiratory diseases are a leading cause of hospital admissions and childhood mortality worldwide, highlighting the critical need for accurate and timely diagnosis to support effective treatment and long-term care. Chest radiography remains the most widely used imaging modality for pediatric pulmonary assessment. Consequently, reliable AI-assisted diagnostic methods are essential for alleviating the workload of clinical radiologists. However, most existing deep learning-based approaches are data-driven and formulate diagnosis as a black-box image classification task, resulting in limited interpretability and reduced clinical trustworthiness. To address these challenges, we propose a trustworthy two-stage diagnostic paradigm for pediatric chest X-ray diagnosis that closely aligns with the radiological workflow in clinical practice, in which the diagnosis procedure is constrained by evidence. In the first stage, a vision\u2013language model fine-tuned on pediatric data identifies radiological findings from chest radiographs, producing structured and interpretable diagnostic evidence. In the second stage, a multimodal large language model integrates the radiograph, extracted findings, patient demographic information, and external medical domain knowledge with RAG mechanism to generate the final diagnosis. Experiments conducted on the VinDr-PCXR dataset demonstrate that our method achieves 90.1% diagnostic accuracy, 70.9% F1-score, and 82.5% AUC, representing up to a 13.1% increase in diagnosis accuracy over the state-of-the-art baselines. These results validate the effectiveness of combining multimodal reasoning with explicit medical evidence and domain knowledge, and indicate the strong potential of the proposed approach for trustworthy pediatric radiology diagnosis.<\/jats:p>","DOI":"10.3390\/jimaging12030111","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T11:05:44Z","timestamp":1772795144000},"page":"111","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evidence-Guided Diagnostic Reasoning for Pediatric Chest Radiology Based on Multimodal Large Language Models"],"prefix":"10.3390","volume":"12","author":[{"given":"Yuze","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Biomedical Engineering, Fudan University, Shanghai 200433, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Children\u2019s Medical Center, Children\u2019s Hospital of Fudan University, Shanghai 201102, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0155-5046","authenticated-orcid":false,"given":"Yingwen","family":"Wang","sequence":"additional","affiliation":[{"name":"National Children\u2019s Medical Center, Children\u2019s Hospital of Fudan University, Shanghai 201102, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Biomedical Engineering, Fudan University, Shanghai 200433, China"},{"name":"Fudan Zhangjiang Institute, Shanghai 200120, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Feng","sequence":"additional","affiliation":[{"name":"National Children\u2019s Medical Center, Children\u2019s Hospital of Fudan University, Shanghai 201102, China"},{"name":"Fudan Zhangjiang Institute, Shanghai 200120, China"},{"name":"Shanghai Key Laboratory of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai 200433, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Children\u2019s Medical Center, Children\u2019s Hospital of Fudan University, Shanghai 201102, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e2022058389","DOI":"10.1542\/peds.2022-058389","article-title":"Pediatric Respiratory Illnesses: An Update on Achievable Benchmarks of Care","volume":"152","author":"Reyes","year":"2023","journal-title":"Pediatrics"},{"key":"ref_2","unstructured":"World Health Organization (2005). The World Health Report 2005: Make Every Mother and Child Count, World Health Organization."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1586\/14787210.2014.866517","article-title":"Epidemiology, etiology, x-ray features, importance of co-infections and clinical features of viral pneumonia in developing countries","volume":"12","author":"Lanaspa","year":"2014","journal-title":"Expert Rev. Anti-Infect. Ther."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1002\/jhm.2624","article-title":"Epidemiology of pediatric hospitalizations at general hospitals and freestanding children\u2019s hospitals in the United States","volume":"11","author":"Leyenaar","year":"2016","journal-title":"J. Hosp. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1038\/s41390-024-03049-y","article-title":"Emerging trends and concerns in Mycoplasma pneumoniae pneumonia among Chinese pediatric population","volume":"95","author":"Xie","year":"2024","journal-title":"Pediatr. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.5606\/tgkdc.dergisi.2024.25707","article-title":"Radiological imaging and interventional procedures of the thorax in children","volume":"32","author":"Beyoglu","year":"2024","journal-title":"Turk Gogus Kalp Damar Cerrahisi Derg."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Elhanashi, A., Saponara, S., Zheng, Q., Almutairi, N., Singh, Y., Kuanar, S., Ali, F., Unal, O., and Faghani, S. (2025). AI-Powered Object Detection in Radiology: Current Models, Challenges, and Future Direction. J. Imaging, 11.","DOI":"10.3390\/jimaging11050141"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s12960-020-0448-3","article-title":"Physician workforce in the United States of America: Forecasting nationwide shortages","volume":"18","author":"Zhang","year":"2020","journal-title":"Hum. Resour. Health"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/s13244-021-01031-4","article-title":"Workload of diagnostic radiologists in the foreseeable future based on recent scientific advances: Growth expectations and role of artificial intelligence","volume":"12","author":"Kwee","year":"2021","journal-title":"Insights Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1007\/s00330-024-10794-5","article-title":"Performance of AI to exclude normal chest radiographs to reduce radiologists\u2019 workload","volume":"34","author":"Schalekamp","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shi, P., Zhang, X., Liu, L., Tang, L., Li, J., Wang, L., Li, A.M., Cao, Y., Xu, H., and Huang, G. (2020). Age- and gender-specific trends in respiratory outpatient visits and diagnoses at a tertiary pediatric hospital in China: A 10-year retrospective study. BMC Pediatr., 20.","DOI":"10.1186\/s12887-020-2001-x"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Siddiqi, R., and Javaid, S. (2024). Deep learning for pneumonia detection in chest x-ray images: A comprehensive survey. J. Imaging, 10.","DOI":"10.3390\/jimaging10080176"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102320","DOI":"10.1016\/j.compmedimag.2023.102320","article-title":"Deep learning for report generation on chest X-ray images","volume":"111","author":"Ouis","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109319","DOI":"10.1016\/j.asoc.2022.109319","article-title":"Chest X-ray analysis empowered with deep learning: A systematic review","volume":"126","author":"Meedeniya","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102125","DOI":"10.1016\/j.media.2021.102125","article-title":"Deep learning for chest X-ray analysis: A survey","volume":"72","author":"Sogancioglu","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jandoubi, B., and Akhloufi, M.A. (2025). Multimodal Artificial Intelligence in Medical Diagnostics. Information, 16.","DOI":"10.3390\/info16070591"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tran, T.T., Pham, H.H., Nguyen, T.V., Le, T.T., Nguyen, H.T., and Nguyen, H.Q. (2021). Learning to Automatically Diagnose Multiple Diseases in Pediatric Chest Radiographs Using Deep Convolutional Neural Networks. arXiv.","DOI":"10.1101\/2021.08.12.21261954"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6150","DOI":"10.1038\/s41598-024-56819-3","article-title":"Enhancing pediatric pneumonia diagnosis through masked autoencoders","volume":"14","author":"Yoon","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7551","DOI":"10.1038\/s41598-024-58163-y","article-title":"Supervised representation learning based on various levels of pediatric radiographic views for transfer learning","volume":"14","author":"Kyung","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1186\/s43055-024-01356-2","article-title":"Explainability, transparency and black box challenges of AI in radiology: Impact on patient care in cardiovascular radiology","volume":"55","author":"Marey","year":"2024","journal-title":"Egypt. J. Radiol. Nucl. Med."},{"key":"ref_21","unstructured":"Liu, H., Li, C., Wu, Q., and Lee, Y.J. (2023). Visual Instruction Tuning. arXiv."},{"key":"ref_22","unstructured":"Li, J., Li, D., Savarese, S., and Hoi, S. (2023). BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv."},{"key":"ref_23","unstructured":"OpenAI (2023). GPT-4 Technical Report. arXiv."},{"key":"ref_24","unstructured":"Anil, R., Borgeaud, S., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., Millican, K., and Silver, D. (2023). Gemini: A family of highly capable multimodal models. arXiv."},{"key":"ref_25","unstructured":"Fan, Z., Liang, C., Wu, C., Zhang, Y., Wang, Y., and Xie, W. (2025). ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, W., Zhang, Y., Sun, H., Li, Y., Zhang, F., Xu, M., Clausich, V.B., Mellin, S., Yang, R., and Wang, C. (2025). CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning. arXiv.","DOI":"10.1016\/j.inffus.2025.104027"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lee, S., Youn, J., Kim, H., Kim, M., and Yoon, S.H. (2024). CXR-LLAVA: A multimodal large language model for interpreting chest X-ray images. arXiv.","DOI":"10.1007\/s00330-024-11339-6"},{"key":"ref_28","unstructured":"Lou, J., Yang, Y., Yu, Z., Fu, Z., Han, W., Huang, Q., and Yu, J. (2025). CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1038\/s41597-023-02102-5","article-title":"PedICXR: An Open, Large-Scale Chest Radiograph Dataset for Interpretation of Common Thoracic Diseases in Children","volume":"10","author":"Pham","year":"2023","journal-title":"Sci. Data"},{"key":"ref_30","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., and Horng, S. (2019). MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv.","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","article-title":"VinDr-CXR: An Open Dataset of Chest X-rays with Radiologist\u2019s Annotations","volume":"9","author":"Nguyen","year":"2022","journal-title":"Sci. Data"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., and Shpanskaya, K. (2019). CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. arXiv.","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","article-title":"Knowledge-Enhanced Visual-Language Pre-training on Chest Radiology Images","volume":"14","author":"Zhang","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_34","unstructured":"Wu, C., Zhang, X., Wang, Y., Zhang, Y., and Xie, W. (2023). K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Kohne, J., Wittrup, E., and Najarian, K. (2024). Three-Stage Framework for Accurate Pediatric Chest X-ray Diagnosis Using Self-Supervision and Transfer Learning on Small Datasets. Diagnostics, 14.","DOI":"10.3390\/diagnostics14151634"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"87981","DOI":"10.1109\/ACCESS.2024.3418985","article-title":"Dual-Masked Autoencoders: Application to Multi-Labeled Pediatric Thoracic Diseases","volume":"12","author":"Yoon","year":"2024","journal-title":"IEEE Access"},{"key":"ref_37","first-page":"e3019","article-title":"CurriMAE: Curriculum learning based masked autoencoders for multi-labeled pediatric thoracic disease classification","volume":"11","author":"Yoon","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_38","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"103228","DOI":"10.1016\/j.eclinm.2025.103228","article-title":"Artificial intelligence for Diagnostics in Radiology Practice: A Rapid Scoping Review","volume":"83","author":"Lawrence","year":"2025","journal-title":"EClinicalMedicine"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kufel, J., Biel\u00f3wka, M., Rojek, M., Mitr\u0119ga, A., Lewandowski, P., Cebula, M., Krawczyk, D., Biel\u00f3wka, M., Kondo\u0142, D., and Bargie\u0142-\u0141\u0105czek, K. (2023). Multi-Label Classification of Chest X-ray Abnormalities Using Transfer Learning Techniques. J. Pers. Med., 13.","DOI":"10.3390\/jpm13101426"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Ahmed, F., Sammar Naz, N., Khan, S., Ur Rehman, A., Ismael, W.M., and Adnan Khan, M. (2026). Explainable Artificial Intelligence (XAI) in Medical Imaging: A Systematic Review of Techniques, Applications, and Challenges. BMC Med. Imaging, 26.","DOI":"10.1186\/s12880-025-02118-w"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e233261","DOI":"10.1148\/radiol.233261","article-title":"Care to Explain? Effect of Explanation Type on Trust and Performance When AI Assists Physicians","volume":"313","author":"Prinster","year":"2024","journal-title":"Radiology"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/111\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T05:29:26Z","timestamp":1772947766000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/111"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":42,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["jimaging12030111"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12030111","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]}}}