{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:32:57Z","timestamp":1780464777958,"version":"3.54.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Technology Innovation Program","award":["RS-2025-02221011"],"award-info":[{"award-number":["RS-2025-02221011"]}]},{"name":"Development of Medical-Specialized Multimodal Hyperscale Generative AI Technology for Global Integration) funded by the Ministry of Trade Industry & Energy"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3587687","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T18:15:25Z","timestamp":1754072125000},"page":"17841-17855","source":"Crossref","is-referenced-by-count":8,"title":["M4CXR: Exploring Multitask Potentials of Multimodal Large Language Models for Chest X-Ray Interpretation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4131-0729","authenticated-orcid":false,"given":"Jonggwon","family":"Park","sequence":"first","affiliation":[{"name":"DEEPNOID Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5088-1208","authenticated-orcid":false,"given":"Soobum","family":"Kim","sequence":"additional","affiliation":[{"name":"DEEPNOID Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5387-4328","authenticated-orcid":false,"given":"Byungmu","family":"Yoon","sequence":"additional","affiliation":[{"name":"DEEPNOID Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2623-8143","authenticated-orcid":false,"given":"Jihun","family":"Hyun","sequence":"additional","affiliation":[{"name":"DEEPNOID Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8240-4716","authenticated-orcid":false,"given":"Kyoyun","family":"Choi","sequence":"additional","affiliation":[{"name":"DEEPNOID Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02318-w"},{"key":"ref2","article-title":"Large model driven radiology report generation with clinical quality reinforcement learning","volume-title":"arXiv:2403.06728","author":"Zhou","year":"2024"},{"key":"ref3","article-title":"MAIRA-1: A specialised large multimodal model for radiology report generation","volume-title":"arXiv:2311.13668","author":"Hyland","year":"2023"},{"key":"ref4","article-title":"Towards a clinically accessible radiology foundation model: Open-access and lightweight, with automated evaluation","author":"Chaves","year":"2024","journal-title":"arXiv:2403.08002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref6","article-title":"RaDialog: A large vision-language model for radiology report generation and conversational assistance","volume-title":"arXiv:2311.18681","author":"Pellegrini","year":"2023"},{"key":"ref7","article-title":"LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation","author":"Lee","year":"2023","journal-title":"arXiv:2305.11490"},{"key":"ref8","article-title":"A vision-language foundation model to enhance efficiency of chest X-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv:2401.12208"},{"key":"ref9","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"issue":"140","key":"ref10","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref12","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref13","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref14","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.274"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3114747"},{"issue":"3","key":"ref20","first-page":"2607","article-title":"PromptMRG: Diagnosis-driven prompts for medical report generation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Jin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687707"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112913"},{"key":"ref23","article-title":"Advancing multimodal medical capabilities of Gemini","author":"Yang","year":"2024","journal-title":"arXiv:2405.03162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_35"},{"key":"ref27","article-title":"MAIRA-2: Grounded radiology report generation","volume-title":"arXiv:2406.04449","author":"Bannur","year":"2024"},{"key":"ref28","article-title":"Ferret: Refer and ground anything anywhere at any granularity","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"You"},{"key":"ref29","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref31","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01608-8"},{"key":"ref34","article-title":"VinDr-CXR: An open dataset of chest X-rays with radiologist\u2019s annotations","author":"Nguyen","year":"2020","journal-title":"arXiv:2012.15029"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref36","article-title":"ChestX-det10: Chest X-ray dataset on detection of thoracic abnormalities","author":"Liu","year":"2020","journal-title":"arXiv:2006.10550"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.174.1.1740071"},{"key":"ref38","volume-title":"SIIM-ACR Pneumothorax Segmentation","author":"Zawacki","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010287"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104319"},{"key":"ref42","volume-title":"COVID-Qu-EX Dataset","author":"Tahir","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-021-00146-8"},{"key":"ref44","article-title":"Chest ImaGenome dataset for clinical reasoning","author":"Wu","year":"2021","journal-title":"arXiv:2108.00316"},{"key":"ref45","first-page":"3867","article-title":"EHRXQA: A multi-modal question answering dataset for electronic health records with chest X-ray images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Bae"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599819"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref49","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"key":"ref52","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Jain"},{"key":"ref53","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00965-w"},{"key":"ref55","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref56","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv:2307.08691"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref60","article-title":"Radialog instruct dataset (version 1.1.0)","author":"Pellegrini","year":"2024","journal-title":"PhysioNet"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62385-7"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11106750.pdf?arnumber=11106750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:35Z","timestamp":1759945115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11106750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3587687","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}