{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T18:07:58Z","timestamp":1789150078513,"version":"build-2803163510"},"reference-count":79,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Agencia Estatal de Investigaci\u00f3n of Spain","award":["PID2025-171806OB-I00"],"award-info":[{"award-number":["PID2025-171806OB-I00"]}]},{"award":["PID2025-171806OB-I00"],"award-info":[{"award-number":["PID2025-171806OB-I00"]}],"id":[{"id":"https:\/\/ror.org\/003x0zc53","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Regional Government of Madrid of Spain","award":["TEC-2024\/COM-322"],"award-info":[{"award-number":["TEC-2024\/COM-322"]}]},{"name":"FPI-UAM"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Access to reliable medical images is essential for clinical training. To address this need, this paper presents an extended version of MIRAGE, a multimodal retrieval and generation system that utilizes a shared latent space to process medical queries by retrieving real images from the ROCO dataset, generating synthetic scans, and providing LLM-based clinical descriptions alongside dual-concept visual comparisons. To overcome previous computational limits and the lack of clinical validation, we introduce three core enhancements: first, an Auto-\u03b1 module to dynamically weight visual and textual similarities; second, the integration of LCM-LoRA to accelerate synthetic image generation; and third, an automated clinical auditor based on Gemini 2.5 Flash. Experimental results demonstrate that Auto-\u03b1 improves retrieval accuracy for heterogeneous queries, reaching 38.83% Top-1 Recall over a 65,419-image gallery and outperforming nine fusion baselines evaluated under a unified configuration, with a controlled ablation attributing most of this gain to learning the weight rather than merely making it query-adaptive, while the LCM-LoRA module reduces computational costs by a factor of 12.5\u00d7 in CPU environments, with a blinded radiologist evaluation confirming only a small drop in clinical quality. Furthermore, the clinical auditor achieves a 0.805 Pearson correlation against an expert radiologist, effectively correcting the systematic overestimation of traditional CLIP scores. Finally, the optimized platform is publicly deployed on Hugging Face.<\/jats:p>","DOI":"10.3390\/jimaging12090438","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T17:14:59Z","timestamp":1789146899000},"page":"438","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal AI Framework for Medical Education: Integrating Adaptive Image Retrieval, Fast Synthesis, and LLM-Based Clinical Auditing"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2110-9972","authenticated-orcid":false,"given":"Miguel","family":"D\u00edaz-Benito","sequence":"first","affiliation":[{"name":"Department of Signal Theory and Communications, Universidad Carlos III de Madrid, 28911 Legan\u00e9s, Spain"},{"name":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9210-0853","authenticated-orcid":false,"given":"Cecilia","family":"Diana-Albelda","sequence":"additional","affiliation":[{"name":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1705-3972","authenticated-orcid":false,"given":"\u00c1lvaro","family":"Garc\u00eda-Mart\u00edn","sequence":"additional","affiliation":[{"name":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4964-5626","authenticated-orcid":false,"given":"Mario Rub\u00e9n","family":"Paz Campos","sequence":"additional","affiliation":[{"name":"Hospital Universitario de La Princesa, 28006 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6238-6859","authenticated-orcid":false,"given":"Jesus","family":"Bescos","sequence":"additional","affiliation":[{"name":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"ref_1","first-page":"407","article-title":"Health Information on the Internet: Gold Mine or Minefield?","volume":"60","author":"Tonsaker","year":"2014","journal-title":"Can. Fam. Physician"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102690","DOI":"10.1016\/j.inffus.2024.102690","article-title":"Review of multimodal machine learning approaches in healthcare","volume":"114","author":"Krones","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Capuozzo, S., Gravina, M., Gatta, G., Marrone, S., and Sansone, C. (2022). A Multimodal Knowledge-Based Deep Learning Approach for MGMT Promoter Methylation Identification. J. Imaging, 8.","DOI":"10.3390\/jimaging8120321"},{"key":"ref_4","first-page":"1","article-title":"A Survey on Composed Image Retrieval","volume":"21","author":"Du","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"103553","DOI":"10.1016\/j.media.2025.103553","article-title":"Revisiting medical image retrieval via knowledge consolidation","volume":"102","author":"Nan","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"19511","DOI":"10.1109\/ACCESS.2026.3656368","article-title":"Multimodal Vision\u2013Language Models in Medical Imaging: A Survey of Retrieval, Interpretability, and Trust","volume":"14","author":"Imran","year":"2026","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., and Sun, J. (2022, January 7\u201311). MedCLIP: Contrastive Learning from Unpaired Medical Images and Text. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref_8","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18\u201324). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning (ICML), Virtual."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"bbac409","DOI":"10.1093\/bib\/bbac409","article-title":"BioGPT: Generative pre-trained transformer for biomedical text generation and mining","volume":"23","author":"Luo","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref_10","unstructured":"Conover, M., Hayes, M., Mathur, A., Xie, J., Wan, J., Shah, S., Ghodsi, A., Wendell, P., Zaharia, M., and Xin, R. (2026, September 05). Free Dolly: Introducing the World\u2019s First Truly Open Instruction-Tuned LLM. Available online: https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm."},{"key":"ref_11","first-page":"105","article-title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","volume":"56","author":"Yang","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102846","DOI":"10.1016\/j.media.2023.102846","article-title":"Diffusion models in medical imaging: A comprehensive survey","volume":"88","author":"Kazerouni","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e48785","DOI":"10.2196\/48785","article-title":"Opportunities, challenges, and future directions of generative artificial intelligence in medical education: Scoping review","volume":"9","author":"Preiksaitis","year":"2023","journal-title":"JMIR Med. Educ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e46885","DOI":"10.2196\/46885","article-title":"The role of ChatGPT, generative language models, and artificial intelligence in medical education: A conversation with ChatGPT and a call for papers","volume":"9","author":"Eysenbach","year":"2023","journal-title":"JMIR Med. Educ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1097\/ACM.0000000000005439","article-title":"ChatGPT and generative artificial intelligence for medical education: Potential impact and opportunity","volume":"99","author":"Boscardin","year":"2024","journal-title":"Acad. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s40670-023-01934-5","article-title":"ChatGPT-based learning: Generative artificial intelligence in medical education","volume":"34","author":"Stretton","year":"2024","journal-title":"Med. Sci. Educ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1038\/s41746-025-01650-x","article-title":"Synthetic medical education in dermatology leveraging generative artificial intelligence","volume":"8","author":"Rao","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Janumpally, S., Nanua, S., Ngo, A., and Youens, K. (2025). Generative artificial intelligence in graduate medical education. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1525604"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Benito, M.D., Diana-Albelda, C., Garc\u00eda-Mart\u00edn, \u00c1., Bescos, J., Vi\u00f1olo, M.E., and SanMiguel, J.C. (2026). MIRAGE: Retrieval and Generation of Multimodal Images and Texts for Medical Education. Proceedings of the Applications of Medical Artificial Intelligence, Springer.","DOI":"10.1007\/978-3-032-09569-5_11"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., and Friedrich, C. (2018). Radiology Objects in COntext (ROCO): A Multimodal Image Dataset. CVII-STENT\/LABELS@MICCAI, Springer. Available online: https:\/\/api.semanticscholar.org\/CorpusID:53087891.","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref_21","unstructured":"luhuitong (2026, September 05). CLIP-ViT-L-14-448px-MedICaT-ROCO. Available online: https:\/\/huggingface.co\/luhuitong\/CLIP-ViT-L-14-448px-MedICaT-ROCO."},{"key":"ref_22","unstructured":"(2026, September 05). Prompt2MedImage. Available online: https:\/\/huggingface.co\/Nihirc\/Prompt2MedImage."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Song, Y., and Soleymani, M. (2019, January 15\u201320). Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, Q., and Albanie, S. (2021, January 20\u201325). Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01471"},{"key":"ref_25","unstructured":"Liang, Z., Rajaraman, S., Marini, N., Xue, Z., and Antani, S. (2026). Multi-task Cross-modal Learning for Chest X-ray Image Retrieval. arXiv."},{"key":"ref_26","unstructured":"Reyes, M., Abreu, H., and Cardoso, P. (2026). Prototype-Enhanced Confidence Modeling for Cross-Modal Medical Image-Report Retrieval. Proceedings of the Interpretability of Machine Intelligence in Medical Image Computing, Springer."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5134","DOI":"10.1109\/TIP.2022.3193288","article-title":"MATR: Multimodal Medical Image Fusion via Multiscale Adaptive Transformer","volume":"31","author":"Tang","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","unstructured":"Wang, Z., Zheng, L., and Wang, S. (2018). Query Adaptive Late Fusion for Image Retrieval. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Dong, W., Diao, M., and Yang, M. (2026). An Adaptive Multi-Source Retrieval-Augmented Generation Framework Integrating Query Complexity Awareness and Confidence-Aware Fusion. Appl. Sci., 16.","DOI":"10.3390\/app16052495"},{"key":"ref_30","unstructured":"Hsu, H.L., and Tzeng, J. (2025). DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation. arXiv."},{"key":"ref_31","unstructured":"Loweimi, E., Qian, M., Knill, K., Wu, G., Chan, C.H., Haider, A., Awan, M., Kittler, J., Wang, H., and Gales, M. (2026). To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Modality Detection. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"You, X., and Si, J. (March, January 17\u2013). Adaptive Image Retrieval Based on Multi-Feature Fusion. Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019), Qingdao, China.","DOI":"10.2991\/cnci-19.2019.84"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"103119","DOI":"10.1016\/j.ipm.2022.103119","article-title":"Adaptive multi-feature fusion via cross-entropy normalization for effective image retrieval","volume":"60","author":"Ma","year":"2023","journal-title":"Inf. Process. Manag."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, J., Li, X., Yang, M., and Zhang, X. (2018). An Adaptive Weight Method for Image Retrieval Based Multi-Feature Fusion. Entropy, 20.","DOI":"10.3390\/e20080577"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"7449","DOI":"10.1038\/s41598-026-38699-x","article-title":"Entropy guided multi level feature fusion network for high precision content based image retrieval","volume":"16","author":"Lavanya","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"5585","DOI":"10.1109\/TIP.2018.2852503","article-title":"Modality-Specific Cross-Modal Similarity Measurement With Recurrent Attention Network","volume":"27","author":"Peng","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_37","unstructured":"Thanh, T., Huu, P.H., Duy, T.N., Minh, T.N.L., and Tinh, A.N.N. (2025). Unified Interactive Multimodal Moment Retrieval via Cascaded Embedding-Reranking and Temporal-Aware Score Fusion. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sharma, S., and Aggarwal, A. (2024). A New Approach for Effective Retrieval of Medical Images: A Step towards Computer-Assisted Diagnosis. J. Imaging, 10.","DOI":"10.3390\/jimaging10090210"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1136\/bjo-2023-324923","article-title":"Using artificial intelligence to improve human performance: Efficient retinal disease detection training with synthetic images","volume":"108","author":"Tabuchi","year":"2024","journal-title":"Br. J. Ophthalmol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10916-026-02350-z","article-title":"Generative Artificial Intelligence for Medical Image Creation in Health Professions Education: A Scoping Review","volume":"50","author":"Gupta","year":"2026","journal-title":"J. Med. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18\u201324). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion Models in Vision: A Survey","volume":"45","author":"Croitoru","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"7506","DOI":"10.1109\/TPAMI.2025.3569700","article-title":"Efficient Diffusion Models: A Comprehensive Survey From Principles to Practices","volume":"47","author":"Ma","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_44","unstructured":"Hu, J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., and Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv."},{"key":"ref_45","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., and Zhao, H. (2023). Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference. arXiv."},{"key":"ref_46","unstructured":"Chen, J., Wu, Y., Luo, S., Xie, E., Paul, S., Luo, P., Zhao, H., and Li, Z. (2024). PIXART-\u03b4: Fast and Controllable Image Generation with Latent Consistency Models. arXiv."},{"key":"ref_47","unstructured":"Luo, S., Tan, Y., Patil, S., Gu, D., von Platen, P., Passos, A., Huang, L., Li, J., and Zhao, H. (2023). LCM-LoRA: A Universal Stable-Diffusion Acceleration Module. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/TPAMI.2024.3461721","article-title":"Efficient Diffusion Model for Image Restoration by Residual Shifting","volume":"47","author":"Yue","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"8078","DOI":"10.1007\/s11263-025-02570-9","article-title":"Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey","volume":"133","author":"Li","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"102075","DOI":"10.1016\/j.artmed.2021.102075","article-title":"Evaluating diagnostic content of AI-generated radiology reports of chest X-rays","volume":"116","author":"Babar","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_51","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":"2025","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Lu, Y., Yang, X., Li, X., Wang, X.E., and Wang, W.Y. (2023). LLMScore: Unveiling the power of large language models in text-to-image synthesis evaluation. Proceedings of the 37th International Conference on Neural Information Processing Systems, Curran Associates Inc.. NIPS \u201923.","DOI":"10.52202\/075280-1001"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"103551","DOI":"10.1016\/j.media.2025.103551","article-title":"CLIP in medical imaging: A survey","volume":"102","author":"Zhao","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_54","unstructured":"Vu, J., and Sheshappanavar, S. (2025). The Effect of Negation on CLIP in Medical Imaging: Limitations of Contrastive Language-Image Pretraining. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Cino, L., Mazzeo, P.L., Martella, A., Radi, G., Rossi, R., and Distante, C. (2026). When AI and Experts Agree on Error: Intrinsic Ambiguity in Dermatoscopic Images. J. Imaging, 12.","DOI":"10.3390\/jimaging12060231"},{"key":"ref_56","unstructured":"Zhu, L., Wang, X., and Wang, X. (2023). JudgeLM: Fine-tuned Large Language Models are Scalable Judges. arXiv."},{"key":"ref_57","unstructured":"Chen, D., Chen, R., Zhang, S., Liu, Y., Wang, Y., Zhou, H., Zhang, Q., Zhou, P., Wan, Y., and Sun, L. (2024). MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. arXiv."},{"key":"ref_58","unstructured":"Pires, C., Nunes, S., and Teixeira, L.F. (2025). Expanding Relevance Judgments for Medical Case-based Retrieval Task with Multimodal LLMs. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"103265","DOI":"10.1016\/j.artmed.2025.103265","article-title":"Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions","volume":"170","author":"Sun","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_60","unstructured":"Gong, H., Ji, X., Liu, Y., Wu, W., Yan, X., Liu, J., Wu, K., Pan, J., Jian, B., and Zhang, J. (2025). Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"103421","DOI":"10.1016\/j.artmed.2026.103421","article-title":"Measuring the Quality of AI-Generated Clinical Notes: A Systematic Review and Experimental Benchmark of Evaluation Methods","volume":"177","author":"Dahlberg","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.compmedimag.2007.10.001","article-title":"Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion","volume":"32","author":"Rahman","year":"2008","journal-title":"Comput. Med. Imaging Graph. Off. J. Comput. Med. Imaging Soc."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Huang, F., Zhang, L., Fu, X., and Song, S. (2023). Dynamic Weighted Combiner for Mixed-Modal Image Retrieval. arXiv.","DOI":"10.1609\/aaai.v38i3.28004"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/0306-4573(94)00057-A","article-title":"Combining the evidence of multiple query representations for information retrieval","volume":"31","author":"Belkin","year":"1995","journal-title":"Inf. Process. Manag."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Cormack, G.V., Clarke, C.L.A., and Buettcher, S. (2009, January 19\u201323). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Boston, MA, USA.","DOI":"10.1145\/1571941.1572114"},{"key":"ref_66","unstructured":"Perez, J.R., Zhou, J., Le, R., Menchtchikov, A., and Lagasse, R. (2025, January 18). Entropy-Based Dynamic Hybrid Retrieval for Adaptive Query Weighting in RAG Pipelines. Proceedings of the 1st Workshop on Vector Databases at ICML, Vancouver, BC, Canada. Available online: https:\/\/algoverseairesearch.org\/news\/entropy-hybrid-retrieval."},{"key":"ref_67","unstructured":"Latent-Consistency (2026, September 05). lcm-lora-sdv1-5. Available online: https:\/\/huggingface.co\/latent-consistency\/lcm-lora-sdv1-5."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual Comparisons by Ranking Methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."},{"key":"ref_69","unstructured":"Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences, Lawrence Erlbaum Associates. [2nd ed.]. Available online: https:\/\/www.sciencedirect.com\/book\/monograph\/9780121790608\/statistical-power-analysis-for-the-behavioral-sciences."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1098\/rspl.1895.0041","article-title":"Notes on Regression and Inheritance in the Case of Two Parents","volume":"58","author":"Pearson","year":"1895","journal-title":"Proc. R. Soc. Lond."},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"107979","DOI":"10.1016\/j.neunet.2025.107979","article-title":"Enhancing feature discrimination with pseudo-labels for foundation model in segmentation of 3D medical images","volume":"193","author":"Jin","year":"2026","journal-title":"Neural Netw."},{"key":"ref_72","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N., Dhillon, I., Blistein, M., Ram, O., Zhang, D., and Rosen, E. (2025). Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. arXiv."},{"key":"ref_73","unstructured":"Agrawal, P., Antoniak, S., Hanna, E.B., Bout, B., Chaplot, D., Chudnovsky, J., Costa, D., De Monicault, B., Garg, S., and Gervet, T. (2024). Pixtral 12B. arXiv."},{"key":"ref_74","unstructured":"Meta Llama Team (2026, September 05). The Llama 4 Open Source Large Language Model Collection. Technical Report, Meta AI. Available online: https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/."},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","article-title":"Intraclass Correlations: Uses in Assessing Rater Reliability","volume":"86","author":"Shrout","year":"1979","journal-title":"Psychol. Bull."},{"key":"ref_76","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical Methods for Assessing Agreement Between Two Methods of Clinical Measurement","volume":"327","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_77","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1037\/0033-2909.87.2.245","article-title":"Tests for Comparing Elements of a Correlation Matrix","volume":"87","author":"Steiger","year":"1980","journal-title":"Psychol. Bull."},{"key":"ref_78","unstructured":"D\u00edaz, M. (2026, September 05). Multimodal-AI-Medical-Education. Available online: https:\/\/github.com\/migueldiaz1\/multimodal-ai-medical-education."},{"key":"ref_79","unstructured":"D\u00edaz-Benito, M. (2026, September 05). MIRAGE: Multimodal Retrieval and Generation for Medical Education. Hugging Face Space. Available online: https:\/\/huggingface.co\/spaces\/Migueldiaz1\/mirage-backend-pro."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/438\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T17:25:53Z","timestamp":1789147553000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/438"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":79,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090438"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090438","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]}}}