{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:25:04Z","timestamp":1787757904086,"version":"build-2784847793"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["RS-2023-00220408"],"award-info":[{"award-number":["RS-2023-00220408"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Biology and Medicine"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1016\/j.compbiomed.2025.110297","type":"journal-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T02:54:25Z","timestamp":1747623265000},"page":"110297","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Text-guided cross-position attention for image analysis: Case of medical image"],"prefix":"10.1016","volume":"193","author":[{"given":"Go-Eun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2074-1733","authenticated-orcid":false,"given":"Sang Tae","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seon Ho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaewoo","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3859-1702","authenticated-orcid":false,"given":"Jungchan","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang-Il","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compbiomed.2025.110297_b1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2025.110297_b2","doi-asserted-by":"crossref","unstructured":"S. Woo, J. Park, J.-Y. Lee, I.S. Kweon, Cbam: Convolutional block attention module, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.compbiomed.2025.110297_b3","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.compbiomed.2025.110297_b4","doi-asserted-by":"crossref","unstructured":"J.M.J. Valanarasu, P. Oza, I. Hacihaliloglu, V.M. Patel, Medical transformer: Gated axial-attention for medical image segmentation, in: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24, 2021, pp. 36\u201346.","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"10.1016\/j.compbiomed.2025.110297_b5","doi-asserted-by":"crossref","unstructured":"W. Wang, C. Chen, M. Ding, H. Yu, S. Zha, J. Li, Transbts: Multimodal brain tumor segmentation using transformer, in: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24, 2021, pp. 109\u2013119.","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"10.1016\/j.compbiomed.2025.110297_b6","doi-asserted-by":"crossref","unstructured":"Z. Xing, L. Yu, L. Wan, T. Han, L. Zhu, Nestedformer: Nested modality-aware transformer for brain tumor segmentation, in: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part V, 2022, pp. 140\u2013150.","DOI":"10.1007\/978-3-031-16443-9_14"},{"issue":"21","key":"10.1016\/j.compbiomed.2025.110297_b7","doi-asserted-by":"crossref","first-page":"11086","DOI":"10.3390\/ijerph182111086","article-title":"Covid-transformer: Interpretable covid-19 detection using vision transformer for healthcare","volume":"18","author":"Shome","year":"2021","journal-title":"Int. J. Environ. Res. Public Heal."},{"key":"10.1016\/j.compbiomed.2025.110297_b8","unstructured":"A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, et al., Learning transferable visual models from natural language supervision, in: International Conference on Machine Learning, 2021, pp. 8748\u20138763."},{"key":"10.1016\/j.compbiomed.2025.110297_b9","series-title":"Medclip: Contrastive learning from unpaired medical images and text","author":"Wang","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110297_b10","doi-asserted-by":"crossref","unstructured":"R. Bhalodia, A. Hatamizadeh, L. Tam, Z. Xu, X. Wang, E. Turkbey, D. Xu, Improving pneumonia localization via cross-attention on medical images and reports, in: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part II 24, 2021, pp. 571\u2013581.","DOI":"10.1007\/978-3-030-87196-3_53"},{"key":"10.1016\/j.compbiomed.2025.110297_b11","series-title":"LViT: language meets vision transformer in medical image segmentation","author":"Li","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110297_b12","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"537","article-title":"Text-guided cross-position attention for segmentation: Case of medical image","author":"Lee","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110297_b13","doi-asserted-by":"crossref","DOI":"10.1155\/2018\/4303161","article-title":"Brain midline shift measurement and its automation: a review of techniques and algorithms","volume":"2018","author":"Liao","year":"2018","journal-title":"Int. J. Biomed. Imaging"},{"key":"10.1016\/j.compbiomed.2025.110297_b14","doi-asserted-by":"crossref","unstructured":"J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10.1016\/j.compbiomed.2025.110297_b15","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10.1016\/j.compbiomed.2025.110297_b16","doi-asserted-by":"crossref","unstructured":"Z. Zhou, M.M. Rahman Siddiquee, N. Tajbakhsh, J. Liang, Unet++: A nested u-net architecture for medical image segmentation, in: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 2018, pp. 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"10.1016\/j.compbiomed.2025.110297_b17","series-title":"Attention u-net: Learning where to look for the pancreas","author":"Oktay","year":"2018"},{"issue":"4","key":"10.1016\/j.compbiomed.2025.110297_b18","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compbiomed.2025.110297_b19","series-title":"Deeplab2: A tensorflow library for deep labeling","author":"Weber","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110297_b20","series-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"10.1016\/j.compbiomed.2025.110297_b21","doi-asserted-by":"crossref","unstructured":"L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.compbiomed.2025.110297_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108115","article-title":"Cfanet: Context fusing attentional network for preoperative CT image segmentation in robotic surgery","volume":"171","author":"Lin","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.compbiomed.2025.110297_b23","series-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110297_b24","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24","first-page":"14","article-title":"Transfuse: Fusing transformers and cnns for medical image segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110297_b25","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110297_b26","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"4","key":"10.1016\/j.compbiomed.2025.110297_b27","doi-asserted-by":"crossref","first-page":"5355","DOI":"10.1109\/TNNLS.2022.3204090","article-title":"Swinpa-net: Swin transformer-based multiscale feature pyramid aggregation network for medical image segmentation","volume":"35","author":"Du","year":"2022","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.compbiomed.2025.110297_b28","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.compbiomed.2025.110297_b29","doi-asserted-by":"crossref","unstructured":"Z. Yang, J. Wang, Y. Tang, K. Chen, H. Zhao, P.H. Torr, Lavt: Language-aware vision transformer for referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18155\u201318165.","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"10.1016\/j.compbiomed.2025.110297_b30","doi-asserted-by":"crossref","unstructured":"H. Ding, C. Liu, S. Wang, X. Jiang, Vision-language transformer and query generation for referring segmentation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 16321\u201316330.","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"10.1016\/j.compbiomed.2025.110297_b31","doi-asserted-by":"crossref","unstructured":"Z. Wang, Y. Lu, Q. Li, X. Tao, Y. Guo, M. Gong, T. Liu, Cris: Clip-driven referring image segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11686\u201311695.","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"10.1016\/j.compbiomed.2025.110297_b32","series-title":"Machine Learning for Healthcare Conference","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022"},{"key":"10.1016\/j.compbiomed.2025.110297_b33","doi-asserted-by":"crossref","unstructured":"S. Eslami, C. Meinel, G. De Melo, Pubmedclip: How much does clip benefit visual question answering in the medical domain?, in: Findings of the Association for Computational Linguistics: EACL 2023, 2023, pp. 1181\u20131193.","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"10.1016\/j.compbiomed.2025.110297_b34","doi-asserted-by":"crossref","unstructured":"S.C. Huang, L. Shen, M.P. Lungren, S. Yeung, Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 3942\u20133951.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.compbiomed.2025.110297_b35","article-title":"Medklip: Medical knowledge enhanced language-image pre-training","author":"Wu","year":"2023","journal-title":"MedRxiv"},{"key":"10.1016\/j.compbiomed.2025.110297_b36","series-title":"Bi-VLGM: Bi-level class-severity-aware vision-language graph matching for text guided medical image segmentation","author":"Wenting","year":"2023"},{"key":"10.1016\/j.compbiomed.2025.110297_b37","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.compbiomed.2025.110297_b38","doi-asserted-by":"crossref","unstructured":"C.-F.R. Chen, Q. Fan, R. Panda, Crossvit: Cross-attention multi-scale vision transformer for image classification, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 357\u2013366.","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"10.1016\/j.compbiomed.2025.110297_b39","doi-asserted-by":"crossref","unstructured":"J. Fu, J. Liu, H. Tian, Y. Li, Y. Bao, Z. Fang, H. Lu, Dual attention network for scene segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"issue":"7","key":"10.1016\/j.compbiomed.2025.110297_b40","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/TMI.2017.2677499","article-title":"A dataset and a technique for generalized nuclear segmentation for computational pathology","volume":"36","author":"Kumar","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"21","key":"10.1016\/j.compbiomed.2025.110297_b41","doi-asserted-by":"crossref","first-page":"30615","DOI":"10.1007\/s11042-022-12156-z","article-title":"Covid-cxnet: Detecting covid-19 in frontal chest x-ray images using deep learning","volume":"81","author":"Haghanifar","year":"2022","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.compbiomed.2025.110297_b42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41747-020-00173-2","article-title":"Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem","volume":"4","author":"Hofmanninger","year":"2020","journal-title":"Eur. Radiol. Exp."},{"key":"10.1016\/j.compbiomed.2025.110297_b43","series-title":"Mosmeddata: Chest ct scans with covid-19 related findings dataset","author":"Morozov","year":"2020"},{"key":"10.1016\/j.compbiomed.2025.110297_b44","doi-asserted-by":"crossref","unstructured":"B. Xiao, H. Wu, Y. Wei, Simple baselines for human pose estimation and tracking, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 466\u2013481.","DOI":"10.1007\/978-3-030-01231-1_29"},{"issue":"7","key":"10.1016\/j.compbiomed.2025.110297_b45","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.3390\/diagnostics11071156","article-title":"Method for diagnosing the bone marrow edema of sacroiliac joint in patients with axial spondyloarthritis using magnetic resonance image analysis based on deep learning","volume":"11","author":"Lee","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.compbiomed.2025.110297_b46","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.compbiomed.2025.110297_b47","doi-asserted-by":"crossref","unstructured":"N.P. Nguyen, Y. Yoo, A. Chekkoury, E. Eibenberger, T.J. Re, J. Das, A. Balachandran, Y.W. Lui, P.C. Sanelli, T.J. Schroeppel, et al., Brain midline shift detection and quantification by a cascaded deep network pipeline on non-contrast computed tomography scans, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 487\u2013495.","DOI":"10.1109\/ICCVW54120.2021.00059"}],"container-title":["Computers in Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482525006481?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482525006481?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T17:31:57Z","timestamp":1766424717000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010482525006481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":47,"alternative-id":["S0010482525006481"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110297","relation":{},"ISSN":["0010-4825"],"issn-type":[{"value":"0010-4825","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Text-guided cross-position attention for image analysis: Case of medical image","name":"articletitle","label":"Article Title"},{"value":"Computers in Biology and Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110297","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"110297"}}