{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T01:09:13Z","timestamp":1766106553798,"version":"3.48.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":27,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2022R1A2C1007169"],"award-info":[{"award-number":["2022R1A2C1007169"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2020-NR049579"],"award-info":[{"award-number":["RS-2020-NR049579"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10489-025-07009-9","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T04:31:19Z","timestamp":1764304279000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing transformer-based attention mechanisms for multi-scale feature fusion in medical image segmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Rabeea Fatma","family":"Khan","sequence":"first","affiliation":[]},{"given":"Mu Sook","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Byoung-Dai","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"issue":"3","key":"7009_CR1","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1080\/02564602.2014.906861","volume":"31","author":"A Norouzi","year":"2014","unstructured":"Norouzi A et al (2014) Medical image segmentation methods, algorithms, and applications. IETE Tech Rev 31(3):199\u2013213. https:\/\/doi.org\/10.1080\/02564602.2014.906861","journal-title":"IETE Tech Rev"},{"key":"7009_CR2","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Med Image Comput Comput Assist Interv\u2014MICCAI 2015: 18th International Conference, Munich, Germany, 2015:234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"7009_CR3","unstructured":"Vaswani A et al (2017) Attention is all you need. Adv Neural Inf Process Syst, Online, vol 30. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"7009_CR4","unstructured":"Dosovitskiy A et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"7009_CR5","doi-asserted-by":"publisher","unstructured":"Hatamizadeh A, Nath V, Tang Y, Yang D, Roth HR, Xu D (2021) Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. International MICCAI brainlesion workshop. Springer, pp 272\u2013284. https:\/\/doi.org\/10.1007\/978-3-031-08999-2_22","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"7009_CR6","doi-asserted-by":"publisher","unstructured":"Wang W, Chen C, Ding M, Yu H, Zha S, Li J (2021) Transbts: Mul- timodal brain tumor segmentation using transformer. In: Med Image Comput Comput Assist Interv MICCAI: 24th International Conference, Strasbourg, France 2021:109\u2013119. https:\/\/doi.org\/10.1007\/978-3-030-87193-2_11","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"7009_CR7","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","volume":"32","author":"HY Zhou","year":"2023","unstructured":"Zhou HY et al (2023) nn-Former: volumetric medical image segmentation via a 3d transformer. IEEE Trans Image Process Online 32:4036\u20134045. https:\/\/doi.org\/10.1109\/TIP.2023.3293771","journal-title":"IEEE Trans Image Process Online"},{"issue":"2","key":"7009_CR8","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.1007\/s00521-022-07859-1","volume":"35","author":"Y Wu","year":"2023","unstructured":"Wu Y et al (2023) D-former: a u-shaped dilated transformer for 3d medical image segmentation. Neural Comput Appl 35(2):1931\u20131944. https:\/\/doi.org\/10.1007\/s00521-022-07859-1","journal-title":"Neural Comput Appl"},{"key":"7009_CR9","doi-asserted-by":"publisher","unstructured":"Peiris H, Hayat M, Chen Z, Egan G, Harandi M (2022) A robust volumetric transformer for accurate 3D tumor segmentation. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S (eds), International Conference on Medical Image Computing and Computer-Assisted Intervention. Switzerland, p 162\u2013172. https:\/\/doi.org\/10.1007\/978-3-031-16443-9_16","DOI":"10.1007\/978-3-031-16443-9_16"},{"key":"7009_CR10","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A et al (2022) Unetr: Transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, p 574\u2013584. https:\/\/openaccess.thecvf.com\/content\/WACV2022\/html\/Hatamizadeh_UNETR_Transformers_for_3D_Medical_Image_Segmentation_WACV_2022_paper.html","DOI":"10.1109\/WACV51458.2022.00181"},{"issue":"1","key":"7009_CR11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/TETCI.2023.3309626","volume":"8","author":"B Chen","year":"2024","unstructured":"Chen B, Liu Y, Zhang Z, Lu G, Kong AWK (2024) Transattunet: multi-level attention-guided u-net with transformer for medical image segmentation. arXiv preprint arXiv:2107.05274. IEEE Trans Emerg Top Comput Intell 8(1):55\u201368. https:\/\/doi.org\/10.1109\/TETCI.2023.3309626","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"7009_CR12","doi-asserted-by":"publisher","unstructured":"Chen J et al (2021) Transunet: Transformers make strong encoders for medical image segmentation. Med Image Anal 97:103280.\u00a0https:\/\/doi.org\/10.1016\/j.media.2024.103280","DOI":"10.1016\/j.media.2024.103280"},{"key":"7009_CR13","doi-asserted-by":"publisher","unstructured":"Xie Y, Zhang J, Shen C, Xia Y (2021) COTR: Efficiently bridging CNN and transformer for 3D medical image segmentation. In: International Conference On Medical Image Computing And Computer-Assisted InterVention, Strasbourg, France, p 171\u2013180. https:\/\/doi.org\/10.1007\/978-3-030-87199-4_16","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"7009_CR14","doi-asserted-by":"publisher","unstructured":"Xu G, Wu X, Zhang X, He X (2024) LeVit-Unet: make faster encoders with transformer for medical image segmentation. In: Liu Q et al (ed) Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14432. Springer, Singapore.\u00a0https:\/\/doi.org\/10.1007\/978-981-99-8543-2_4","DOI":"10.1007\/978-981-99-8543-2_4"},{"issue":"12","key":"7009_CR15","doi-asserted-by":"publisher","first-page":"8747767","DOI":"10.21037\/qims-23-542","volume":"13","author":"RF Khan","year":"2023","unstructured":"Khan RF, Lee BD, Lee MS (2023) Transformers in medical image segmentation: a narrative review. Quant Imaging Med Surg Online 13(12):8747767\u20138748767. https:\/\/doi.org\/10.21037\/qims-23-542","journal-title":"Quant Imaging Med Surg Online"},{"key":"7009_CR16","doi-asserted-by":"publisher","unstructured":"Cao H et al (2021) Swin-Unet: Unet-like pure transformer for medical image segmentation. In: Karlinsky L, Michaeli T, Nishino K (eds) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13803. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"7009_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3178991","volume":"71","author":"A Lin","year":"2022","unstructured":"Lin A, Chen B, Xu J, Zhang Z, Lu G, Zhang D (2022) Ds-transunet: dual Swin transformer u-net for medical image segmentation. IEEE Trans Instrum Meas Online 71:1\u201315. https:\/\/doi.org\/10.1109\/TIM.2022.3178991","journal-title":"IEEE Trans Instrum Meas Online"},{"key":"7009_CR18","doi-asserted-by":"publisher","unstructured":"Huang X, Deng Z, Li D, Yuan X (2022) MISSformer: An effective medical image segmentation transformer. IEEE Trans Med Imaging 42(5):1484\u20131494.\u00a0https:\/\/doi.org\/10.1109\/TMI.2022.3230943","DOI":"10.1109\/TMI.2022.3230943"},{"key":"7009_CR19","unstructured":"Oktay O et al (2018) Attention u-net: learning where to look for the pancreas. Proceedings of the 1st on medical imaging with deep learning conference (MIDL 2018) https:\/\/arxiv.org\/abs\/1804.03999"},{"key":"7009_CR20","doi-asserted-by":"publisher","unstructured":"Rao A, Park J, Woo S, Lee J-Y, Aalami O (2021) Studying the effects of self-attention for medical image analysis. Proceedings of the IEEE\/CVF international conference on computer and vision workshops 2021:3409\u20133418.\u00a0https:\/\/doi.org\/10.1109\/iccvw54120.2021.00381","DOI":"10.1109\/iccvw54120.2021.00381"},{"key":"7009_CR21","doi-asserted-by":"publisher","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","volume":"28","author":"W Al-Dhabyani","year":"2020","unstructured":"Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A (2020) Dataset of breast ultrasound images. Data Brief 28:104863. https:\/\/doi.org\/10.1016\/j.dib.2019.104863","journal-title":"Data Brief"},{"key":"7009_CR22","doi-asserted-by":"crossref","unstructured":"Jha D, Smedsrud PH, Riegler MA, Halvorsen P, de Lange T, Johansen D, Johansen HD (2020) Kvasir-seg: A segmented polyp dataset. In International Conference on Multimedia Modeling (pp. 451\u2013462). Springer","DOI":"10.1007\/978-3-030-37734-2_37"},{"issue":"1","key":"7009_CR23","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli M, Reinke A, Bakas S, Farahani K, Kopp-Schneider A, Landman BA et al (2022) The medical segmentation decathlon. Nat Commun 13(1):4128. https:\/\/doi.org\/10.1038\/s41467-022-30695-9","journal-title":"Nat Commun"},{"key":"7009_CR24","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2146","volume":"10","author":"Z Xu","year":"2024","unstructured":"Xu Z, Wang Z (2024) Mcv-unet: a modified convolution & transformer hybrid encoder-decoder network with multi-scale information fusion for ultrasound image semantic segmentation. PeerJ Comput Sci 10:e2146. https:\/\/doi.org\/10.7717\/peerj-cs.2146","journal-title":"PeerJ Comput Sci"},{"key":"7009_CR25","doi-asserted-by":"publisher","unstructured":"He K, Xiangyu Z, Shaoqing R, Jian S (2016) Deep residual learning for image recognition. Proceedings of the IEEE\/CVF international conference on computer vision 2016:770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-07009-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-07009-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-07009-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T01:05:11Z","timestamp":1766106311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-07009-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":25,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["7009"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-07009-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"6 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing financial interests or personal relationships that may have influenced the work reported in this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1120"}}