{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T05:23:36Z","timestamp":1779254616909,"version":"3.51.4"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371409"],"award-info":[{"award-number":["62371409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fujian Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2023J01005"],"award-info":[{"award-number":["2023J01005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tmi.2024.3516954","type":"journal-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T18:56:23Z","timestamp":1734116183000},"page":"1671-1685","source":"Crossref","is-referenced-by-count":1,"title":["Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation"],"prefix":"10.1109","volume":"44","author":[{"given":"Jinghan","family":"Sun","sequence":"first","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5969-6987","authenticated-orcid":false,"given":"Dong","family":"Wei","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1950-0959","authenticated-orcid":false,"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8399-7410","authenticated-orcid":false,"given":"Donghuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6520-7681","authenticated-orcid":false,"given":"Hong","family":"Wang","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8795-9294","authenticated-orcid":false,"given":"Sotirios A.","family":"Tsaftaris","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Edinburgh, Edinburgh, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7025-5197","authenticated-orcid":false,"given":"Steven","family":"McDonagh","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Edinburgh, Edinburgh, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2195-2847","authenticated-orcid":false,"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Jarvis Research Center, Tencent YouTu Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2096-454X","authenticated-orcid":false,"given":"Liansheng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-018-0544-y"},{"key":"ref2","article-title":"Deep learning in generating radiology reports: A survey","volume-title":"Artif. Intell. Med.","volume":"106","author":"Monshi","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1148\/radio1.2017162326"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11128-5_38"},{"key":"ref5","article-title":"CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning","author":"Rajpurkar","year":"2017","journal-title":"arXiv:1711.05225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01398"},{"key":"ref9","article-title":"A simple semi-supervised learning framework for object detection","author":"Sohn","year":"2020","journal-title":"arXiv:2005.04757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref13","article-title":"UniTAB: Unifying text and box outputs for grounded vision-language modeling","author":"Yang","year":"2021","journal-title":"arXiv:2111.12085"},{"key":"ref14","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Cho"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01591"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","first-page":"1","article-title":"Making the most of text semantics to improve biomedical vision-language processing","volume-title":"Proc. ECCV","author":"Boecking"},{"key":"ref19","first-page":"45","article-title":"Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies","volume-title":"Proc. MICCAI","author":"Tam"},{"key":"ref20","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref21","first-page":"363","article-title":"You\u2019ve got two teachers: Co-evolutionary image and report distillation for semi-supervised anatomical abnormality detection in chest X-ray","volume-title":"Proc. MICCAI","author":"Sun"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","volume-title":"3rd Place Solution for the 2018 RSNA Pneumonia Detection Challenge","author":"Cheng","year":"2019"},{"key":"ref27","article-title":"Self-EMD: Self-supervised object detection without ImageNet","author":"Liu","year":"2020","journal-title":"arXiv:2011.13677"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074313"},{"key":"ref29","first-page":"16797","article-title":"Comprehensive attention self-distillation for weakly-supervised object detection","volume-title":"Proc. NIPS","author":"Huang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2987161"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref32","first-page":"571","article-title":"Improving pneumonia localization via cross-attention on medical images and reports","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent","author":"Bhalodia"},{"key":"ref33","first-page":"658","article-title":"Anatomy-guided weakly-supervised abnormality localization in chest X-rays","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent.","author":"Yu"},{"key":"ref34","first-page":"549","article-title":"What\u2019s the point: Semantic segmentation with point supervision","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Bearman"},{"key":"ref35","first-page":"249","article-title":"Point beyond class: A benchmark for weakly semi-supervised abnormality localization in chest X-rays","volume-title":"Proc. MICCAI","author":"Ji"},{"key":"ref36","first-page":"10759","article-title":"Consistency-based semi-supervised learning for object detection","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Jeong"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00234"},{"key":"ref38","article-title":"On the automatic generation of medical imaging reports","volume-title":"arXiv:1711.08195","author":"Jing","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_52"},{"key":"ref40","first-page":"721","article-title":"Automatic radiology report generation based on multi-view image fusion and medical concept enrichment","volume-title":"Proc. MICCAI","author":"Yuan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28038"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref43","article-title":"BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref44","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref45","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"issue":"1","key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans. Comput. Healthcare"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref48","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref49","article-title":"CogVLM: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv:2311.03079"},{"key":"ref50","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. NeurIPS","volume":"36","author":"Liu"},{"key":"ref51","first-page":"28541","article-title":"LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. NeurIPS","volume":"36","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref53","article-title":"CheXagent: Towards a foundation model for chest X-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv:2401.12208"},{"key":"ref54","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref55","article-title":"Cross-modal memory networks for radiology report generation","volume-title":"arXiv:2204.13258","author":"Chen","year":"2022"},{"key":"ref56","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref57","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref59","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref60","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref61","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref62","article-title":"CheXBERT: Combining automatic labelers and expert annotations for accurate radiology report labeling using BERT","volume-title":"arXiv:2004.09167","author":"Smit","year":"2020"},{"key":"ref63","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref67","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. NeurIPS","author":"Zhang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.451"},{"key":"ref69","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI45749.2020.9098482"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00441"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10948536\/10798513.pdf?arnumber=10798513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:57:47Z","timestamp":1743796667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10798513\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":74,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3516954","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}