{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:18:49Z","timestamp":1778080729109,"version":"3.51.4"},"reference-count":69,"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":[{"name":"National Key Research and Development Program of China","award":["2022YFF0608404"],"award-info":[{"award-number":["2022YFF0608404"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tmi.2024.3523333","type":"journal-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T19:12:53Z","timestamp":1735240373000},"page":"1821-1835","source":"Crossref","is-referenced-by-count":18,"title":["Cross-Modal Conditioned Reconstruction for Language-Guided Medical Image Segmentation"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9787-3643","authenticated-orcid":false,"given":"Xiaoshuang","family":"Huang","sequence":"first","affiliation":[{"name":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7710-8835","authenticated-orcid":false,"given":"Hongxiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-7822","authenticated-orcid":false,"given":"Chenyu","family":"You","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Yale University, New Haven, CT, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8389-987X","authenticated-orcid":false,"given":"Dong","family":"An","sequence":"additional","affiliation":[{"name":"College of Information and Electrical Engineering, China Agricultural University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3291719"},{"key":"ref3","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020","journal-title":"arXiv:2005.06465"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-020-00173-2"},{"key":"ref5","first-page":"679","article-title":"Multi-modal masked autoencoders for medical vision-and-language pre-training","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI)","author":"Chen"},{"key":"ref6","first-page":"486","article-title":"SwinMM: Masked multi-view with Swin transformers for 3D medical image segmentation","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI)","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00376"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435571"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.62051\/ijcsit.v2n1.05"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00575-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02520"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref15","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3371348"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00355"},{"key":"ref18","first-page":"1","article-title":"Generating images with multimodal language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Koh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01925"},{"key":"ref20","article-title":"CogVLM2: Visual language models for image and video understanding","author":"Hong","year":"2024","journal-title":"arXiv:2408.16500"},{"key":"ref21","first-page":"151","article-title":"TGANet: Text-guided attention for improved polyp segmentation","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI)","author":"Tomar"},{"key":"ref22","first-page":"399","article-title":"A refer-and-ground multimodal large language model for biomedicine","volume-title":"Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI)","author":"Huang"},{"key":"ref23","first-page":"3","article-title":"Unet++: A nested U-Net architecture for medical image segmentation","volume-title":"Proc. Deep Learn. Med. Image Anal. Multimodal Learn. Clin. Decis. Support: 4th Int. Workshop, DLMIA, 8th Int. Workshop, ML-CDS, Held Conjunct (MICCAI)","author":"Zhou"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"NnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nature Methods"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref27","first-page":"205","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Cao"},{"key":"ref28","article-title":"SegStitch: Multidimensional transformer for robust and efficient medical imaging segmentation","author":"Tan","year":"2024","journal-title":"arXiv:2408.00496"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00047"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3363190"},{"key":"ref31","first-page":"1526","article-title":"Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Rahman"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00755"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106153"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref37","first-page":"59","article-title":"Linguistic structure guided context modeling for referring image segmentation","volume-title":"Proc. 16th Eur. Conf. Comput. Vis. (ECCV)","author":"Hui"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111243"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01226"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"ref44","first-page":"21165","article-title":"LIMITR: Leveraging local information for medical image-text representation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Dawidowicz"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref46","article-title":"FILIP: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv:2111.07783"},{"key":"ref47","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022","journal-title":"arXiv:2203.07111"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref51","article-title":"Masked modeling for self-supervised representation learning on vision and beyond","author":"Li","year":"2023","journal-title":"arXiv:2401.00897"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01511"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306"},{"key":"ref57","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref58","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/144"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2677499"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2947628"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref68","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10948536\/10816606.pdf?arnumber=10816606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T19:57:55Z","timestamp":1743796675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":69,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3523333","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}