{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T08:35:58Z","timestamp":1768725358380,"version":"3.49.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Henan Provincial Key R&D Project","award":["232102211021"],"award-info":[{"award-number":["232102211021"]}]},{"name":"Henan Provincial Key R&D Project","award":["232102211021"],"award-info":[{"award-number":["232102211021"]}]},{"name":"Henan Provincial Key R&D Project","award":["232102211021"],"award-info":[{"award-number":["232102211021"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62250410371"],"award-info":[{"award-number":["62250410371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62250410371"],"award-info":[{"award-number":["62250410371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11760-025-03953-8","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T10:13:02Z","timestamp":1740996782000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PACAF-Net: pixel shuffling based fiderality-preserved up\/downsampling and adaptive cross-attention fusion for effective medical image segmentation"],"prefix":"10.1007","volume":"19","author":[{"given":"Yuanhang","family":"Cai","sequence":"first","affiliation":[]},{"given":"Kamel","family":"Aouaidjia","sequence":"additional","affiliation":[]},{"given":"Chongsheng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"3953_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10278-024-00981-7","volume":"37","author":"W Yao","year":"2024","unstructured":"Yao, W., Bai, J., Liao, W., Chen, Y., Liu, M., Xie, Y.: From CNN to transformer: a review of medical image segmentation models. J. Imaging Inform. Med. 37, 1\u201319 (2024)","journal-title":"J. Imaging Inform. Med."},{"key":"3953_CR2","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3953_CR3","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3953_CR4","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Patel, V.M.: UNeXt: MLP-based rapid medical image segmentation network. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 23\u201333. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"3953_CR5","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","volume":"121","author":"N Ibtehaz","year":"2020","unstructured":"Ibtehaz, N., Rahman, M.S.: MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 121, 74\u201387 (2020)","journal-title":"Neural Netw."},{"key":"3953_CR6","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. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 3\u201311. Springer (2018)","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"3953_CR7","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.: An image is worth 16x16 words: transformers for image recognition at scale. ICLR (2021)"},{"key":"3953_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q.: TransFuse: Fusing transformers and CNNs 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. 14\u201324. Springer (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"3953_CR9","doi-asserted-by":"crossref","unstructured":"Heidari, M., Kazerouni, A., Soltany, M., Azad, R., Aghdam, E.K., Cohen-Adad, J., Merhof, D.: 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 (2023)","DOI":"10.1109\/WACV56688.2023.00614"},{"issue":"9","key":"3953_CR10","doi-asserted-by":"publisher","first-page":"2763","DOI":"10.1109\/TMI.2023.3264513","volume":"42","author":"A He","year":"2023","unstructured":"He, A., Wang, K., Li, T., Du, C., Xia, S., Fu, H.: H2Former: an efficient hierarchical hybrid transformer for medical image segmentation. IEEE Trans. Med. Imaging 42(9), 2763\u20132775 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3953_CR11","doi-asserted-by":"crossref","unstructured":"Wei, J., Hu, Y., Zhang, R., Li, Z., Zhou, S.K., Cui, S.: Shallow attention network for polyp 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. 699\u2013708. Springer (2021)","DOI":"10.1007\/978-3-030-87193-2_66"},{"issue":"6","key":"3953_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1109\/TMI.2023.3236037","volume":"42","author":"J Wang","year":"2023","unstructured":"Wang, J., Chen, F., Ma, Y., Wang, L., Fei, Z., Shuai, J., Tang, X., Zhou, Q., Qin, J.: XBound-former: toward cross-scale boundary modeling in transformers. IEEE Trans. Med. Imaging 42(6), 1735\u20131745 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3953_CR13","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Krishnan, D., Taylor, G.W., Fergus, R.: Deconvolutional networks. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2528\u20132535. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"3953_CR14","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z.: 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 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"3953_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101971","volume":"69","author":"T Li","year":"2021","unstructured":"Li, T., Bo, W., Hu, C., Kang, H., Liu, H., Wang, K., Fu, H.: Applications of deep learning in fundus images: a review. Med. Image Anal. 69, 101971 (2021)","journal-title":"Med. Image Anal."},{"key":"3953_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: 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 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"3953_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: G-cascade: efficient cascaded graph convolutional decoding for 2d medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7728\u20137737 (2024)","DOI":"10.1109\/WACV57701.2024.00755"},{"key":"3953_CR18","doi-asserted-by":"crossref","unstructured":"Zeiler, M.: Visualizing and understanding convolutional networks. In: European Conference on Computer vision\/arXiv, vol. 1311 (2014)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"3953_CR19","unstructured":"Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. CoRR arXiv:1301.3557 (2013)"},{"key":"3953_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3953_CR21","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"3953_CR22","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., Huang, Q.: $$\\text{F}^3$$net: fusion, feedback and focus for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12321\u201312328 (2020)","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"3953_CR23","doi-asserted-by":"crossref","unstructured":"Ruan, J., Xiang, S., Xie, M., Liu, T., Fu, Y.: MALUNet: A multi-attention and light-weight UNet for skin lesion segmentation. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1150\u20131156. IEEE (2022)","DOI":"10.1109\/BIBM55620.2022.9995040"},{"key":"3953_CR24","doi-asserted-by":"crossref","unstructured":"Ruan, J., Xie, M., Gao, J., Liu, T., Fu, Y.: EGE-UNet: an efficient group enhanced UNet for skin lesion segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 481\u2013490. Springer (2023)","DOI":"10.1007\/978-3-031-43901-8_46"},{"key":"3953_CR25","doi-asserted-by":"publisher","unstructured":"Codella, N.C.F., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., Halpern, A.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 168\u2013172 (2018). https:\/\/doi.org\/10.1109\/ISBI.2018.8363547","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"3953_CR26","unstructured":"Codella, N., Rotemberg, V., Tschandl, P., Celebi, M.E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., Marchetti, M., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)"},{"key":"3953_CR27","doi-asserted-by":"crossref","unstructured":"Jha, D., Smedsrud, P.H., Riegler, M.A., Halvorsen, P., De\u00a0Lange, T., Johansen, D., Johansen, H.D.: Kvasir-seg: A segmented polyp dataset. In: MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26, pp. 451\u2013462. Springer (2020)","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"3953_CR28","doi-asserted-by":"crossref","unstructured":"Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., Gil, D., Rodr\u00edguez, C., Vilari\u00f1o, F.: WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Comput. Med. Imaging Gr. 43, 99\u2013111 (2015)","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"issue":"2","key":"3953_CR29","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","volume":"35","author":"N Tajbakhsh","year":"2015","unstructured":"Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automated polyp detection in colonoscopy videos using shape and context information. IEEE Trans. Med. Imaging 35(2), 630\u2013644 (2015)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"3953_CR30","first-page":"4037190","volume":"2017","author":"D V\u00e1zquez","year":"2017","unstructured":"V\u00e1zquez, D., Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., L\u00f3pez, A.M., Romero, A., Drozdzal, M., Courville, A.: A benchmark for endoluminal scene segmentation of colonoscopy images. J. Healthc. Eng. 2017(1), 4037190 (2017)","journal-title":"J. Healthc. Eng."},{"key":"3953_CR31","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","volume":"9","author":"J Silva","year":"2014","unstructured":"Silva, J., Histace, A., Romain, O., Dray, X., Granado, B.: Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 9, 283\u2013293 (2014)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"3953_CR32","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., Shao, L.: Pranet: Parallel reverse attention network for polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 263\u2013273. Springer (2020)","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"3953_CR33","doi-asserted-by":"crossref","unstructured":"Dong, B., Wang, W., Fan, D.-P., Li, J., Fu, H., Shao, L.: Polyp-pvt: polyp segmentation with pyramid vision transformers. CAAI Artificial Intelligence Research 2 (2023)","DOI":"10.26599\/AIR.2023.9150015"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03953-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03953-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03953-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T20:06:36Z","timestamp":1744142796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03953-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":33,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["3953"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03953-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"6 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"348"}}