{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:19:42Z","timestamp":1776979182459,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"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":["SIViP"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11760-026-05269-7","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:14:53Z","timestamp":1774948493000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CSAFD: Cross-scale attention fusion decoder for medical image segmentation"],"prefix":"10.1007","volume":"20","author":[{"given":"Xiaoshan","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"issue":"5","key":"5269_CR1","doi-asserted-by":"publisher","first-page":"2473","DOI":"10.1007\/s11760-022-02464-0","volume":"17","author":"H Mkindu","year":"2023","unstructured":"Mkindu, H., Wu, L., Zhao, Y.: 3d multi-scale vision transformer for lung nodule detection in chest CT images. Signal Image Video Process. 17(5), 2473\u20132480 (2023)","journal-title":"Signal Image Video Process."},{"key":"5269_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2024.112134","volume":"224","author":"Y Cheng","year":"2025","unstructured":"Cheng, Y., Yan, J., Zhang, F., Li, M., Zhou, N., Shi, C., Jin, B., Zhang, W.: Surrogate modeling of pantograph-catenary system interactions. Mech. Syst. Signal Process. 224, 112134 (2025)","journal-title":"Mech. Syst. Signal Process."},{"key":"5269_CR3","first-page":"1","volume":"74","author":"J Yan","year":"2025","unstructured":"Yan, J., Cheng, Y., Zhang, F., Zhou, N., Wang, H., Jin, B., Wang, M., Zhang, W.: Multimodal imitation learning for arc detection in complex railway environments. IEEE Trans. Instrum. Meas. 74, 1\u201313 (2025)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"8","key":"5269_CR4","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1007\/s11227-025-07462-w","volume":"81","author":"Z Li","year":"2025","unstructured":"Li, Z., Li, L., Tang, M., Hu, J.: Pmsafe: parallel multi-scale attention fusion encoder for medical image segmentation. J. Supercomput. 81(8), 960 (2025)","journal-title":"J. Supercomput."},{"issue":"10","key":"5269_CR5","doi-asserted-by":"publisher","first-page":"5574","DOI":"10.1364\/BOE.529505","volume":"15","author":"D Cao","year":"2024","unstructured":"Cao, D., Zhang, R., Zhang, Y.: Mflunet: multi-scale fusion lightweight unet for medical image segmentation. Biomed. Opt. Express 15(10), 5574\u20135591 (2024)","journal-title":"Biomed. Opt. Express"},{"key":"5269_CR6","doi-asserted-by":"crossref","unstructured":"Zou, L., Bu, X., Jiang, F., Wu, Z., Sun, L., Dashtipour, K., Gogate, M., Hussain, A., Wang, X.: Lightweight 2d medical image segmentation via a decoder using linear deformable convolution and multi-scale self-attention, IEEE Journal of Biomedical and Health Informatics, pp. 1\u201341 (2025)","DOI":"10.1109\/JBHI.2025.3583108"},{"key":"5269_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109259","volume":"183","author":"X Huang","year":"2024","unstructured":"Huang, X., Tang, H., Ding, Y., Li, Y., Zhu, Z., Yang, P.: Ltmsegnet: lightweight multi-scale medical image segmentation combining transformer and mlp. Comput. Biol. Med. 183, 109259 (2024)","journal-title":"Comput. Biol. Med."},{"key":"5269_CR8","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation, vol. 9351, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5269_CR9","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman\u00a0Siddiquee, M.M., Tajbakhsh, N., Liang, J.: Unet++: a nested u-net architecture for medical image segmentation, pp. 3\u201311. Springer (2018)","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"5269_CR10","doi-asserted-by":"crossref","unstructured":"Huang, H., Lin, L., Tong, R., Hu, H., Zhang, Q., Iwamoto, Y., Han, X., Chen, Y.-W., Wu, J.: Unet 3+: a full-scale connected unet for medical image segmentation, pp. 1055\u20131059. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"issue":"2","key":"5269_CR11","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P.F., Kohl, S.A.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203\u2013211 (2021)","journal-title":"Nat. Methods"},{"key":"5269_CR12","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., Yan, S.: Metaformer is actually what you need for vision, pp. 10809\u201310819. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"5269_CR13","doi-asserted-by":"crossref","unstructured":"Lin, X., Yan, Z., Deng, X., Zheng, C., Yu, L.: Convformer: plug-and-play cnn-style transformers for improving medical image segmentation, vol. 14223, pp. 642\u2013651. Springer (2023)","DOI":"10.1007\/978-3-031-43901-8_61"},{"key":"5269_CR14","doi-asserted-by":"crossref","unstructured":"Xu, G., Wu, X., Zhang, X., He, X.: Levit-unet: make faster encoders with transformer for medical image segmentation, CoRR, vol. abs\/2107.08623 (2021)","DOI":"10.2139\/ssrn.4116174"},{"issue":"2","key":"5269_CR15","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1007\/s11760-023-02893-5","volume":"18","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Han, L., Yao, B., Li, Q.: Sta-former: enhancing medical image segmentation with shrinkage triplet attention in a hybrid cnn-transformer model. Signal Image Video Process. 18(2), 1901\u20131910 (2024)","journal-title":"Signal Image Video Process."},{"issue":"3","key":"5269_CR16","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Fan, D., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: PVT v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"5269_CR17","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: transformers make strong encoders for medical image segmentation, CoRR, vol. abs\/2102.04306 (2021)"},{"key":"5269_CR18","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., Wang, M.: Swin-unet: unet-like pure transformer for medical image segmentation, CoRR, vol. abs\/2105.05537 (2021)"},{"key":"5269_CR19","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Munir, M., Marculescu, R.: EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation, pp. 11769\u201311779. IEEE (2024)","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"5269_CR20","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions, pp. 548\u2013558. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"5269_CR21","unstructured":"Rahman, M.M., Marculescu, R.: Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation, vol. 227, pp. 1526\u20131544. PMLR (2023)"},{"key":"5269_CR22","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M.C.H., Heinrich, M.P., Misawa, K., Mori, K., McDonagh, S.G., Hammerla, N.Y., Kainz, B., Glocker, B., Rueckert, D.: Attention u-net: Learning where to look for the pancreas, CoRR, vol. abs\/1804.03999 (2018)"},{"key":"5269_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows, pp. 9992\u201310002. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5269_CR24","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: G-CASCADE: efficient cascaded graph convolutional decoding for 2d medical image segmentation, pp. 7713\u20137722. IEEE (2024)","DOI":"10.1109\/WACV57701.2024.00755"},{"issue":"4","key":"5269_CR25","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5269_CR26","doi-asserted-by":"crossref","unstructured":"Lou, A., Guan, S., Ko, H., Loew, M.H.: Caranet: context axial reverse attention network for segmentation of small medical objects, SPIE, vol. 12032 (2022)","DOI":"10.1117\/12.2611802"},{"key":"5269_CR27","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: Medical image segmentation via cascaded attention decoding, pp. 6211\u20136220. IEEE (2023)","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"5269_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Q., Tang, F., Meng, J., Su, J., Song, S.: Stepwise feature fusion: local guides global, vol. 13433, pp. 110\u2013120. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_11"},{"key":"5269_CR29","unstructured":"Dong, B., Wang, W., Fan, D., Li, J., Fu, H., Shao, L.: Polyp-pvt: polyp segmentation with pyramid vision transformers, CoRR, vol. abs\/2108.06932 (2021)"},{"key":"5269_CR30","doi-asserted-by":"crossref","unstructured":"Fan, D., Ji, G., Zhou, T., Chen, G., Fu, H., Shen, J., Shao, L.: Pranet: parallel reverse attention network for polyp segmentation, vol. 12266, pp. 263\u2013273. Springer (2020)","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"5269_CR31","doi-asserted-by":"crossref","unstructured":"Kim, T., Lee, H., Kim, D.: Uacanet: uncertainty augmented context attention for polyp segmentation, pp. 2167\u20132175. ACM (2021)","DOI":"10.1145\/3474085.3475375"},{"key":"5269_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, J., Chen, H.: EGAT: edge-featured graph attention network, vol. 12891, pp. 253\u2013264. Springer (2021)","DOI":"10.1007\/978-3-030-86362-3_21"},{"key":"5269_CR33","first-page":"1","volume":"63","author":"C Yu","year":"2025","unstructured":"Yu, C., Zuo, Y., Zhang, Q., Wang, Y.: Probability-guided edge enhancement network for remote sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. 63, 1\u201317 (2025)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"5269_CR34","doi-asserted-by":"crossref","unstructured":"Heidari, M., Kazerouni, A., Kadarvish, M.S., Azad, R., Aghdam, E.K., Cohen-Adad, J., Merhof, D.: Hiformer: hierarchical multi-scale representations using transformers for medical image segmentation, pp. 6191\u20136201. IEEE (2023)","DOI":"10.1109\/WACV56688.2023.00614"},{"key":"5269_CR35","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X.: Missformer: an effective medical image segmentation transformer, CoRR, vol. abs\/2109.07162 (2021)"},{"key":"5269_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Xie, S., Lin, L., Iwamoto, Y., Han, X., Chen, Y., Tong, R.: Mixed transformer u-net for medical image segmentation. pp. 2390\u20132394. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"5269_CR37","doi-asserted-by":"crossref","unstructured":"Y. Zhang, H. Liu, and Q. Hu, Transfuse: Fusing transformers and cnns for medical image segmentation, vol. 12901, pp. 14\u201324. Springer (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"5269_CR38","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Patel, V.M.: Unext: mlp-based rapid medical image segmentation network, vol. 13435, pp. 23\u201333. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_3"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05269-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05269-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05269-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:31:42Z","timestamp":1776976302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05269-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["5269"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05269-7","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"15 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"225"}}