{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T18:08:46Z","timestamp":1762625326180,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"41","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20338-0","type":"journal-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T07:02:09Z","timestamp":1728630129000},"page":"89355-89373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Sub-pixel multi-scale fusion network for medical image segmentation"],"prefix":"10.1007","volume":"83","author":[{"given":"Jing","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-341X","authenticated-orcid":false,"given":"Qiaohong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xian","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, 5-9 October 2015, Proceedings, Part III 18, Springer, pp 234\u2013241","key":"20338_CR1","DOI":"10.1007\/978-3-319-24574-4_28"},{"doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Fan DP, Song K, Liang D, Lu T, Luo P, Shao L (2021) Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 568\u2013578","key":"20338_CR2","DOI":"10.1109\/ICCV48922.2021.00061"},{"unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3-7 May 2021","key":"20338_CR3"},{"unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306","key":"20338_CR4"},{"unstructured":"Zhang Z, Sun B, Zhang W (2021) Pyramid medical transformer for medical image segmentation. ArXiv:abs\/2104.14702","key":"20338_CR5"},{"doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, Roth HR, Xu D (2022) Unetr: Transformers for 3d medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 574\u2013584","key":"20338_CR6","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"20338_CR7","first-page":"1","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 71:1\u201315","journal-title":"IEEE Trans Instrum Meas"},{"doi-asserted-by":"publisher","unstructured":"Gu J, Kwon H, Wang D, Ye W, Li M, Chen YH, Lai L, Chandra V, Pan DZ (2022) Multi-scale high-resolution vision transformer for semantic segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12084\u201312093. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01178","key":"20338_CR8","DOI":"10.1109\/CVPR52688.2022.01178"},{"doi-asserted-by":"crossref","unstructured":"Heidari M, Kazerouni A, Soltany M, Azad R, Aghdam EK, Cohen-Adad J, Merhof D (2023) Hiformer: Hierarchical multi-scale representations using transformers for medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 6202\u20136212","key":"20338_CR9","DOI":"10.1109\/WACV56688.2023.00614"},{"doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3431\u20133440","key":"20338_CR10","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"12","key":"20338_CR11","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"doi-asserted-by":"crossref","unstructured":"Christ PF, Elshaer MEA, Ettlinger F, Tatavarty S, Bickel M, Bilic P, Rempfler M, Armbruster M, Hofmann F, D\u2019Anastasi M et al (2016) Automatic liver and lesion segmentation in ct using cascaded fully convolutional neural networks and 3d conditional random fields. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp 415\u2013423. Springer","key":"20338_CR12","DOI":"10.1007\/978-3-319-46723-8_48"},{"issue":"6","key":"20338_CR13","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2019) Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 39(6):1856\u20131867","journal-title":"IEEE Trans Med Imaging"},{"issue":"5","key":"20338_CR14","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","volume":"15","author":"Z Zhang","year":"2018","unstructured":"Zhang Z, Liu Q, Wang Y (2018) Road extraction by deep residual u-net. IEEE Geosci Remote Sens Lett 15(5):749\u2013753","journal-title":"IEEE Geosci Remote Sens Lett"},{"doi-asserted-by":"crossref","unstructured":"Huang H, Lin L, Tong R, Hu H, Zhang Q, Iwamoto Y, Han X, Chen YW, Wu J (2020) Unet 3+: A full-scale connected unet for medical image segmentation. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1055\u20131059. IEEE","key":"20338_CR15","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"doi-asserted-by":"crossref","unstructured":"Xue Y, Xu T, Zhang H, Long LR, Huang X () Segan: Adversarial network with multi-scale l1 loss for medical image segmentation. Neuroinformatics 16:383\u2013392","key":"20338_CR16","DOI":"10.1007\/s12021-018-9377-x"},{"unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30","key":"20338_CR17"},{"doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022","key":"20338_CR18","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"crossref","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, Wang M (2022) Swin-unet: Unet-like pure transformer for medical image segmentation. In: European Conference on Computer Vision, pp 205\u2013218. Springer","key":"20338_CR19","DOI":"10.1007\/978-3-031-25066-8_9"},{"doi-asserted-by":"crossref","unstructured":"Tran TT, Vu DT, Nguyen TH, Pham VT (2023) A cnn-transformer-based approach for medical image segmentation. In: 2023 International Conference on System Science and Engineering (ICSSE), pp 22\u201327. IEEE","key":"20338_CR20","DOI":"10.1109\/ICSSE58758.2023.10227162"},{"issue":"1","key":"20338_CR21","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1002\/mp.14585","volume":"48","author":"T Liu","year":"2021","unstructured":"Liu T, Liu J, Ma Y, He J, Han J, Ding X, Chen CT (2021) Spatial feature fusion convolutional network for liver and liver tumor segmentation from ct images. Med Phys 48(1):264\u2013272","journal-title":"Med Phys"},{"doi-asserted-by":"crossref","unstructured":"Chen X, Zhang R, Yan P (2019) Feature fusion encoder decoder network for automatic liver lesion segmentation. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp 430\u2013433. IEEE","key":"20338_CR22","DOI":"10.1109\/ISBI.2019.8759555"},{"doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2881\u20132890","key":"20338_CR23","DOI":"10.1109\/CVPR.2017.660"},{"doi-asserted-by":"crossref","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 801\u2013818","key":"20338_CR24","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"20338_CR25","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1609\/aaai.v37i1.25111","volume":"37","author":"X Chen","year":"2023","unstructured":"Chen X, Pan J, Lu J, Fan Z, Li H (2023) Hybrid cnn-transformer feature fusion for single image deraining. Proceedings of the AAAI Conference on Artificial Intelligence 37:378\u2013386","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"crossref","unstructured":"Shi W, Caballero J, Husz\u00e1r F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1874\u20131883","key":"20338_CR26","DOI":"10.1109\/CVPR.2016.207"},{"key":"20338_CR27","doi-asserted-by":"publisher","DOI":"10.7303\/syn3193805","author":"B Landman","year":"2015","unstructured":"Landman B, Xu Z, Igelsias J, Styner M, Langerak T, Klein A (2015). Miccai multi-atlas labeling beyond the cranial vault-workshop and challenge. https:\/\/doi.org\/10.7303\/syn3193805","journal-title":"Miccai multi-atlas labeling beyond the cranial vault-workshop and challenge."},{"issue":"11","key":"20338_CR28","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard O, Lalande A, Zotti C, Cervenansky F, Yang X, Heng PA, Cetin I, Lekadir K, Camara O, Ballester MAG et al (2018) Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging 37(11):2514\u20132525","journal-title":"IEEE Trans Med Imaging"},{"unstructured":"Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, Helba B, Kalloo A, Liopyris K, Marchetti M et al (2019) Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368","key":"20338_CR29"},{"issue":"1","key":"20338_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl P, Rosendahl C, Kittler H (2018) The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 5(1):1\u20139","journal-title":"Sci Data"},{"issue":"2","key":"20338_CR31","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.1007\/s00521-022-07859-1","volume":"35","author":"Y Wu","year":"2023","unstructured":"Wu Y, Liao K, Chen J, Wang J, Chen DZ, Gao H, Wu J (2023) D-former: A u-shaped dilated transformer for 3d medical image segmentation. Neural Comput & Applic 35(2):1931\u20131944","journal-title":"Neural Comput & Applic"},{"doi-asserted-by":"crossref","unstructured":"Fu S, Lu Y, Wang Y, Zhou Y, Shen W, Fishman E, Yuille A (2020) Domain adaptive relational reasoning for 3d multi-organ segmentation. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, 4\u20138 October 2020, Proceedings, Part I 23, pp 656\u2013666. Springer","key":"20338_CR32","DOI":"10.1007\/978-3-030-59710-8_64"},{"key":"20338_CR33","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","volume":"53","author":"J Schlemper","year":"2019","unstructured":"Schlemper J, Oktay O, Schaap M, Heinrich M, Kainz B, Glocker B, Rueckert D (2019) Attention gated networks: Learning to leverage salient regions in medical images. Med Image Anal 53:197\u2013207","journal-title":"Med Image Anal"},{"doi-asserted-by":"crossref","unstructured":"Xu G, Zhang X, He X, Wu X (2023) Levit-unet: Make faster encoders with transformer for medical image segmentation. In: Liu Q, Wang H, Ma Z, Zheng W, Zha H, Chen X, Wang L, Ji R (eds) Pattern Recognition and Computer Vision - 6th Chinese Conference PRCV 2023, Xiamen, China, 13-15 October 2023, Proceedings, Part VIII, vol 14432. pp 42\u201353","key":"20338_CR34","DOI":"10.1007\/978-981-99-8543-2_4"},{"issue":"5","key":"20338_CR35","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1109\/TMI.2022.3230943","volume":"42","author":"X Huang","year":"2023","unstructured":"Huang X, Deng Z, Li D, Yuan X, Fu Y (2023) Missformer: An effective transformer for 2d medical image segmentation. IEEE Trans Med Imaging 42(5):1484\u20131494. https:\/\/doi.org\/10.1109\/TMI.2022.3230943","journal-title":"IEEE Trans Med Imaging"},{"doi-asserted-by":"crossref","unstructured":"Zhou HY, Guo J, Zhang Y, Han X, Yu L, Wang L, Yu Y (2023) nnformer: Volumetric medical image segmentation via a 3d transformer. IEEE Trans Med Imaging","key":"20338_CR36","DOI":"10.1109\/TIP.2023.3293771"},{"doi-asserted-by":"crossref","unstructured":"Shaker AM, Maaz M, Rasheed H, et al. (2024) UNETR++: delving into efficient and accurate 3D medical image segmentation [J]. IEEE Trans Med Imaging, 43(9):3377\u2013339","key":"20338_CR37","DOI":"10.1109\/TMI.2024.3398728"},{"key":"20338_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101716","volume":"64","author":"B Lei","year":"2020","unstructured":"Lei B, Xia Z, Jiang F, Jiang X, Ge Z, Xu Y, Qin J, Chen S, Wang T, Wang S (2020) Skin lesion segmentation via generative adversarial networks with dual discriminators. Med Image Anal 64:101716","journal-title":"Med Image Anal"},{"doi-asserted-by":"crossref","unstructured":"Valanarasu JMJ, Oza P, Hacihaliloglu I, Patel VM (2021) 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, pp 36\u201346. Springer","key":"20338_CR39","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"20338_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102327","volume":"76","author":"H Wu","year":"2022","unstructured":"Wu H, Chen S, Chen G, Wang W, Lei B, Wen Z (2022) Fat-net: Feature adaptive transformers for automated skin lesion segmentation. Med Image Anal 76:102327","journal-title":"Med Image Anal"},{"doi-asserted-by":"crossref","unstructured":"Azad R, Heidari M, Wu Y, Merhof D (2022) Contextual attention network: Transformer meets u-net. In: International Workshop on Machine Learning in Medical Imaging, pp 377\u2013386. Springer","key":"20338_CR41","DOI":"10.1007\/978-3-031-21014-3_39"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20338-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20338-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20338-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T12:17:26Z","timestamp":1734956246000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20338-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":41,"journal-issue":{"issue":"41","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["20338"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20338-0","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,10,11]]},"assertion":[{"value":"26 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2024","order":4,"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 there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article contains no studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}}]}}