{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T05:05:45Z","timestamp":1779771945803,"version":"3.53.1"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Medical image captioning bridges visual perception and clinical language, but its development is limited by the high cost of detailed anatomical annotation and by the risk of hallucinations or overconfidence in ambiguous endoscopic images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose ACE-Net, an Anatomy Collaborative Evidence Network for semi-supervised medical image captioning. ACE-Net integrates evidential deep learning into the visual encoding stage through an evidence-driven soft-gating mechanism that quantifies epistemic uncertainty and suppresses unreliable visual noise. A triple-guided Mixture-of-Experts decoder further organizes clinical reasoning into semantic anchoring, visual evidencing, and spatial calibration. Spatial consistency alignment is imposed within a teacher-student co-training framework to promote stable anatomical attention patterns without pixel-level supervision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On a high-resolution otolaryngology endoscopy dataset, ACE-Net achieved a BLEU-4 score of 0.7511 and a ROUGE-L score of 0.8728, demonstrating strong text-generation performance and improved anatomical grounding under limited annotation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results suggest that effective anatomical localization can be induced through evidence-constrained global supervision rather than expensive pixel-level annotations, providing a data-efficient and reliable paradigm for medical image captioning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1816295","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T04:48:11Z","timestamp":1779770891000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semi-supervised medical image captioning via anatomical collaborative evidence network"],"prefix":"10.3389","volume":"13","author":[{"given":"Shengxiang","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiurui","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology","place":["Ya'an People's Hospital, Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lushan","family":"Qiao","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanbo","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhan","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology","place":["Ya'an People's Hospital, Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University","place":["Ya'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"B1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"B2","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Li","year":"2022"},{"key":"B3","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Li","year":"2023"},{"key":"B4","doi-asserted-by":"publisher","first-page":"19724","DOI":"10.1109\/CVPR52734.2025.01837","article-title":"BIOMEDICA: an open biomedical image-caption archive, dataset, and vision-language models derived from scientific literature","author":"Lozano","year":"2025","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B5","doi-asserted-by":"publisher","first-page":"102002","DOI":"10.1016\/j.media.2021.102002","article-title":"Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy","volume":"70","author":"Ali","year":"2021","journal-title":"Med Image Anal"},{"key":"B6","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-032-05472-2_13","article-title":"From scope to script: an automated report generation model for gastrointestinal endoscopy","author":"Kaklamanos","year":"2025","journal-title":"MICCAI Workshop on Deep Generative Models"},{"key":"B7","doi-asserted-by":"publisher","first-page":"10704","DOI":"10.1038\/s41598-025-95666-8","article-title":"A vision attention driven Language framework for medical report generation","volume":"15","author":"Ar\u0131soy","year":"2025","journal-title":"Sci. Rep"},{"key":"B8","first-page":"42478","article-title":"Evidential interactive learning for medical image captioning","volume-title":"International Conference on Machine Learning (ICML)","author":"Zheng","year":"2023"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1007\/s10115-022-01684-7","article-title":"Diagnostic captioning: a survey","volume":"64","author":"Pavlopoulos","year":"2022","journal-title":"Knowl Inf Syst"},{"key":"B10","doi-asserted-by":"publisher","first-page":"103264","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":"Med Image Anal"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1511389","DOI":"10.3389\/fmed.2024.1511389","article-title":"DLAAD-deep learning algorithms assisted diagnosis of chest disease using radiographic medical images","volume":"11","author":"Al-Adhaileh","year":"2025","journal-title":"Front Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"101878","DOI":"10.1016\/j.artmed.2020.101878","article-title":"Deep learning in generating radiology reports: a survey","volume":"106","author":"Monshi","year":"2020","journal-title":"Artif Intell Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617592","article-title":"Deep learning approaches on image captioning: a review","volume":"56","author":"Ghandi","year":"2024","journal-title":"ACM Comput Surv"},{"key":"B14","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1007\/s10462-025-11337-0","article-title":"Automatic radiology report generation with deep learning: a comprehensive review of methods and advances","volume":"58","author":"Li","year":"2025","journal-title":"Artif Intell Rev"},{"key":"B15","doi-asserted-by":"publisher","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 Rev Biomed Eng"},{"key":"B16","doi-asserted-by":"publisher","first-page":"100823","DOI":"10.1016\/j.jrras.2024.100823","article-title":"Chest radiology report generation based on cross-modal multi-scale feature fusion","volume":"17","author":"Pan","year":"2024","journal-title":"J Radiat Res Appl Sci"},{"key":"B17","article-title":"Medical report generation: a hierarchical task structure-based cross-modal causal intervention framework","author":"Song","year":"2025","journal-title":"arXiv preprint arXiv:251102271"},{"key":"B18","doi-asserted-by":"publisher","first-page":"821120","DOI":"10.3389\/fmed.2021.821120","article-title":"MEDUSA: multi-scale encoder-decoder self-attention deep neural network architecture for medical image analysis","volume":"8","author":"Aboutalebi","year":"2022","journal-title":"Front Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679668","article-title":"CLR2G: cross modal contrastive learning on radiology report generation","author":"Xue","year":"2024","journal-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM)"},{"key":"B20","article-title":"Weakly supervised contrastive adversarial training for learning robust features from semi-supervised data","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv:250311032"},{"key":"B21","article-title":"Automatic radiology report generation by learning with increasingly hard negatives","author":"Voutharoja","year":"2023","journal-title":"arXiv preprint arXiv:230507176"},{"key":"B22","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s44267-025-00080-3","article-title":"Pre-training on high-resolution X-ray images: an experimental study","volume":"3","author":"Wang","year":"2025","journal-title":"Visual Intell"},{"key":"B23","article-title":"KIA: knowledge-guided implicit vision-language alignment for chest X-ray report generation","author":"Yin","year":"2025","journal-title":"arXiv preprint arXiv:250100000"},{"key":"B24","article-title":"Uncertainty-aware abstention in medical diagnosis based on medical texts","author":"Vazhentsev","year":"2025","journal-title":"arXiv preprint arXiv:250218050"},{"key":"B25","doi-asserted-by":"publisher","first-page":"104576","DOI":"10.1016\/j.jbi.2023.104576","article-title":"Deep learning uncertainty quantification for clinical text classification","volume":"149","author":"Peluso","year":"2024","journal-title":"J Biomed Inform"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2118","DOI":"10.1109\/TPAMI.2025.3625258","article-title":"A comprehensive survey on evidential deep learning and its applications","volume":"48","author":"Gao","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B27","article-title":"Label calibration in source free domain adaptation","author":"Rai","year":"2025","journal-title":"arXiv preprint arXiv:250107072"},{"key":"B28","doi-asserted-by":"publisher","first-page":"8658","DOI":"10.1109\/TPAMI.2025.3583410","article-title":"Revisiting essential and nonessential settings of evidential deep learning","volume":"47","author":"Chen","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B29","article-title":"Semantic consistency-based uncertainty quantification for factuality in radiology report generation","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv:241204606"},{"key":"B30","article-title":"MedMoE: modality-specialized mixture of experts for medical vision-language understanding","author":"Chopra","year":"2025","journal-title":"arXiv preprint arXiv:250608356"},{"key":"B31","doi-asserted-by":"publisher","first-page":"11558","DOI":"10.1109\/CVPR52729.2023.01112","article-title":"METransformer: radiology report generation by transformer with multiple learnable expert tokens","author":"Wang","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B32","article-title":"REN: anatomically-informed mixture-of-experts for interstitial lung disease diagnosis","author":"Peltekian","year":"2025","journal-title":"arXiv preprint arXiv:251004923"},{"key":"B33","article-title":"Topicwise separable sentence retrieval for medical report generation","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv:240504175"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1816295\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T04:48:14Z","timestamp":1779770894000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1816295\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":33,"alternative-id":["10.3389\/fmed.2026.1816295"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1816295","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,26]]},"article-number":"1816295"}}