{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T08:05:50Z","timestamp":1769760350676,"version":"3.49.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP24K14998"],"award-info":[{"award-number":["JP24K14998"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00371-025-03979-6","type":"journal-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T14:40:40Z","timestamp":1748356840000},"page":"6809-6821","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["RaEUNet: a retentive and efficient UNet for medical image segmentation"],"prefix":"10.1007","volume":"41","author":[{"given":"Yiyi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jia","family":"Su","sequence":"additional","affiliation":[]},{"given":"Song","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Eisei","family":"Nakahara","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"3979_CR1","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","volume":"43","author":"J Bernal","year":"2015","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 Graph. 43, 99\u2013111 (2015)","journal-title":"Comput. Med. Imaging Graph."},{"key":"3979_CR2","doi-asserted-by":"crossref","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. In: European conference on computer vision, pp. 205\u2013218. Springer (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3979_CR3","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. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"3979_CR4","unstructured":"Dong, B., Wang, W., Fan, D.P., Li, J., Fu, H., Shao, L.: Polyp-pvt: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932 (2021)"},{"key":"3979_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3979_CR6","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":"3979_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Q., Huang, H., Chen, M., Liu, H., He, R.: Rmt: Retentive networks meet vision transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5641\u20135651 (2024)","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"3979_CR8","doi-asserted-by":"crossref","unstructured":"Feng, M., Lu, H., Ding, E.: Attentive feedback network for boundary-aware salient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00172"},{"key":"3979_CR9","doi-asserted-by":"crossref","unstructured":"Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., J\u00e9gou, H., Douze, M.: Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 12,259\u201312,269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"issue":"10","key":"3979_CR10","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","volume":"38","author":"Z Gu","year":"2019","unstructured":"Gu, Z., Cheng, J., Fu, H., Zhou, K., Hao, H., Zhao, Y., Zhang, T., Gao, S., Liu, J.: Ce-net: Context encoder network for 2d medical image segmentation. IEEE Trans. Med. Imag. 38(10), 2281\u20132292 (2019)","journal-title":"IEEE Trans. Med. Imag."},{"key":"3979_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3979_CR12","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"},{"key":"3979_CR13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3979_CR14","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. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 1055\u20131059. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"issue":"5","key":"3979_CR15","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1109\/TMI.2022.3230943","volume":"42","author":"X Huang","year":"2022","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X., Fu, Y.: Missformer: an effective transformer for 2d medical image segmentation. IEEE Trans. Med. Imag. 42(5), 1484\u20131494 (2022)","journal-title":"IEEE Trans. Med. Imag."},{"key":"3979_CR16","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":"3979_CR17","doi-asserted-by":"crossref","unstructured":"Kim, T., Lee, H., Kim, D.: Uacanet: Uncertainty augmented context attention for polyp segmentation. In: Proceedings of the 29th ACM international conference on multimedia, pp. 2167\u20132175 (2021)","DOI":"10.1145\/3474085.3475375"},{"key":"3979_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., Wen, Y., He, L.: Scconv: Spatial and channel reconstruction convolution for feature redundancy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6153\u20136162 (2023)","DOI":"10.1109\/CVPR52729.2023.00596"},{"key":"3979_CR19","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. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 10,012\u201310,022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3979_CR20","unstructured":"Loshchilov, I.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"3979_CR21","unstructured":"Naderi, M., Givkashi, M., Piri, F., Karimi, N., Samavi, S.: Focal-unet: Unet-like focal modulation for medical image segmentation. arXiv preprint arXiv:2212.09263 (2022)"},{"key":"3979_CR22","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., et\u00a0al.: Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)"},{"key":"3979_CR23","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: Medical image segmentation via cascaded attention decoding. In: Proceedings of the IEEE\/CVF winter conference on applications of computer Vision, pp. 6222\u20136231 (2023)","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"3979_CR24","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Munir, M., Marculescu, R.: Emcad: Efficient multi-scale convolutional attention decoding for medical image segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11,769\u201311,779 (2024)","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"3979_CR25","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\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3979_CR26","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.media.2023.102802","volume":"88","author":"F Shamshad","year":"2023","unstructured":"Shamshad, F., Khan, S., Zamir, S.W., Khan, M.H., Hayat, M., Khan, F.S., Fu, H.: Transformers in medical imaging: a survey. Med. Image Anal. 88, 102\u2013802 (2023)","journal-title":"Med. Image Anal."},{"key":"3979_CR27","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":"3979_CR28","unstructured":"Sun, Y., Dong, L., Huang, S., Ma, S., Xia, Y., Xue, J., Wang, J., Wei, F.: Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)"},{"issue":"2","key":"3979_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. Imag. 35(2), 630\u2013644 (2015)","journal-title":"IEEE Trans. Med. Imag."},{"key":"3979_CR30","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: international conference on machine learning, pp. 10,347\u201310,357. PMLR (2021)"},{"key":"3979_CR31","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Oza, P., Hacihaliloglu, I., Patel, V.M.: 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 (2021)","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"3979_CR32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"3979_CR33","first-page":"4037190","volume":"1","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. Healthcare Eng. 1, 4037190 (2017)","journal-title":"J. Healthcare Eng."},{"key":"3979_CR34","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11,534\u201311,542 (2020)"},{"key":"3979_CR35","doi-asserted-by":"crossref","unstructured":"Xu, G., Zhang, X., He, X., Wu, X.: Levit-unet: Make faster encoders with transformer for medical image segmentation. In: Chinese conference on pattern recognition and computer vision (PRCV), pp. 42\u201353. Springer (2023)","DOI":"10.1007\/978-981-99-8543-2_4"},{"key":"3979_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"3979_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chung, A.C.: Retinal vessel segmentation by a transformer-u-net hybrid model with dual-path decoder. IEEE Journal of Biomedical and Health Informatics (2024)","DOI":"10.1109\/JBHI.2024.3394151"},{"key":"3979_CR38","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: 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, pp. 3\u201311. Springer (2018)","DOI":"10.1007\/978-3-030-00889-5_1"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03979-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03979-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03979-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:02:45Z","timestamp":1751886165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03979-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["3979"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03979-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,27]]},"assertion":[{"value":"28 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no Conflict of interest in our work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}