{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:00:21Z","timestamp":1777104021857,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Wenzhou Key Scientific and Technological Projects","award":["ZG2024007"],"award-info":[{"award-number":["ZG2024007"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476291"],"award-info":[{"award-number":["62476291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019092","name":"Science Fund for Distinguished Young Scholars of Hunan Province","doi-asserted-by":"publisher","award":["2025JJ20097"],"award-info":[{"award-number":["2025JJ20097"]}],"id":[{"id":"10.13039\/501100019092","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Foundation of Education Bureau of Hunan Province","award":["24B0003"],"award-info":[{"award-number":["24B0003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-01829-2","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T16:13:09Z","timestamp":1752163989000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["GH-UNet: group-wise hybrid convolution-VIT for robust medical image segmentation"],"prefix":"10.1038","volume":"8","author":[{"given":"Shengxiang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linlin","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangzheng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"1829_CR1","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.media.2019.04.005","volume":"55","author":"Y Wang","year":"2019","unstructured":"Wang, Y. et al. Abdominal multi-organ segmentation with organ-attention networks and statistical fusion. Med. Image Anal. 55, 88\u2013102 (2019).","journal-title":"Med. Image Anal."},{"key":"1829_CR2","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N. & Liang, J. Unet++: a nested U-Net architecture for medical image segmentation. In Proc. 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, 3\u201311 (Springer, 2018).","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"1829_CR3","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., Petersen, J. & Maier-Hein, K. H. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021).","journal-title":"Nat. Methods"},{"key":"1829_CR4","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: convolutional networks for biomedical image segmentation. In Proc. Medical Image Computing and Computer-assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, Proceedings, Part III 18, 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1829_CR5","unstructured":"Oktay, O. et al. Attention U-Net: Learning where to look for the pancreas. Preprint at https:\/\/openreview.net\/forum?id=Skft7cijM (2018)."},{"key":"1829_CR6","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In Proc. International Conference on Learning Representations (2020)."},{"key":"1829_CR7","doi-asserted-by":"crossref","unstructured":"Cao, H. et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In Proc. European conference on computer vision, 205\u2013218 (Springer, 2022).","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"1829_CR8","unstructured":"Chen, J. et al. Transunet: Transformers make strong encoders for medical image segmentation. Preprint at arXiv:2102.04306 (2021)."},{"key":"1829_CR9","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A. et al. Unetr: transformers for 3D medical image segmentation. In Proc. IEEE\/CVF Winter Conference on Applications of Computer Vision 574\u2013584 (IEEE, 2022).","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"1829_CR10","doi-asserted-by":"crossref","unstructured":"Wu, H. et al. Cvt: Introducing convolutions to vision transformers. In Proc. IEEE\/CVF International Conference on Computer Vision 22\u201331 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"1829_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y. et al. Rolling-unet: Revitalizing MLPs\u2019 ability to efficiently extract long-distance dependencies for medical image segmentation. In Proc. AAAI Conference on Artificial Intelligence Vol. 38, 3819\u20133827 (ACM, 2024).","DOI":"10.1609\/aaai.v38i4.28173"},{"key":"1829_CR12","doi-asserted-by":"crossref","unstructured":"Rahman, M. M., Munir, M. & Marculescu, R. Emcad: Efficient multi-scale convolutional attention decoding for medical image segmentation. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 11769\u201311779 (IEEE, 2024).","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"1829_CR13","doi-asserted-by":"crossref","unstructured":"Tan, D. et al. A novel skip-connection strategy by fusing spatial and channel wise features for multi-region medical image segmentation. IEEE J. Biomed. Health Inform. 28, 5396\u20135409 (2024).","DOI":"10.1109\/JBHI.2024.3406786"},{"key":"1829_CR14","doi-asserted-by":"crossref","unstructured":"Liu, J. et al. Mixformer: a mixed cnn-transformer backbone for medical image segmentation. IEEE Trans. Instrum. Meas. 74, 1\u201320 (2025).","DOI":"10.1109\/TIM.2024.3497060"},{"key":"1829_CR15","unstructured":"Duan, Y. et al. Vision-rwkv: Efficient and scalable visual perception with rwkv-like architectures. In The Thirteenth International Conference on Learning Representations {ICLR}, Singapore (OpenReview.net, 2025)."},{"key":"1829_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, X. & Chen, T. Bsbp-rwkv: background suppression with boundary preservation for efficient medical image segmentation. In Proc. 32nd ACM International Conference on Multimedia 4938\u20134946 (ACM, 2024).","DOI":"10.1145\/3664647.3681033"},{"key":"1829_CR17","doi-asserted-by":"publisher","unstructured":"Chen, T. et al. Zig-rir: Zigzag rwkv-in-rwkv for efficient medical image segmentation. IEEE Trans. Med. Imaging https:\/\/doi.org\/10.1109\/TMI.2025.3561797 (2025).","DOI":"10.1109\/TMI.2025.3561797"},{"key":"1829_CR18","unstructured":"Mehta, S. & Rastegari, M. Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. In The Tenth International Conference on Learning Representations {ICLR}, Virtual Event (OpenReview.net, 2022)."},{"key":"1829_CR19","unstructured":"Gutman, D. et al. Skin lesion analysis toward melanoma detection: a challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC). http:\/\/arxiv.org\/abs\/1605.01397 (2016)."},{"key":"1829_CR20","doi-asserted-by":"crossref","unstructured":"Jha, D. et al. Kvasir-seg: a segmented polyp dataset. In Proc. MultiMedia modeling: 26th international conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26, 451\u2013462 (Springer, 2020).","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"1829_CR21","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/data3030025","volume":"3","author":"P Porwal","year":"2018","unstructured":"Porwal, P. et al. Indian diabetic retinopathy image dataset (IDRID): a database for diabetic retinopathy screening research. Data 3, 25 (2018).","journal-title":"Data"},{"key":"1829_CR22","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O. et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37, 2514\u20132525 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1829_CR23","unstructured":"Landman, B. et al. MICCAI multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In Proc. MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge Vol. 5, 12 (Sage, 2015)."},{"key":"1829_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X. & Jia, J. Pyramid scene parsing network. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2881\u20132890 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.660"},{"key":"1829_CR25","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proc. European Conference on Computer Vision (ECCV), 801\u2013818 (Springer, 2018).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1829_CR26","doi-asserted-by":"crossref","unstructured":"Fang, Y., Chen, C., Yuan, Y. & Tong, K.-y. Selective feature aggregation network with area-boundary constraints for polyp segmentation. In Proc. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part I 22, 302\u2013310 (Springer, 2019).","DOI":"10.1007\/978-3-030-32239-7_34"},{"key":"1829_CR27","doi-asserted-by":"crossref","unstructured":"Fan, D.-P. et al. Pranet: Parallel reverse attention network for polyp segmentation. In Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention 263\u2013273 (Springer, 2020).","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"1829_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, R. et al. Adaptive context selection for polyp segmentation. In Proc. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part VI 23, 253\u2013262 (Springer, 2020).","DOI":"10.1007\/978-3-030-59725-2_25"},{"key":"1829_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, H.-Y. et al. nnFormer: volumetric medical image segmentation via a 3D transformer. IEEE Trans. Image Process. 32, 4036\u20134045 (2023).","DOI":"10.1109\/TIP.2023.3293771"},{"key":"1829_CR30","doi-asserted-by":"crossref","unstructured":"Huang, X., Deng, Z., Li, D. & Yuan, X. Missformer: An effective transformer for 2d medical image segmentation. IEEE Trans. Image Process. 42, 1484\u20131494 (2021).","DOI":"10.1109\/TMI.2022.3230943"},{"key":"1829_CR31","first-page":"15475","volume":"34","author":"Q Zhang","year":"2021","unstructured":"Zhang, Q. & Yang, Y.-B. Rest: an efficient transformer for visual recognition. Adv. Neural Inf. Process. Syst. 34, 15475\u201315485 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1829_CR32","doi-asserted-by":"crossref","unstructured":"Srinivas, A. et al. Bottleneck transformers for visual recognition. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16519\u201316529 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"1829_CR33","doi-asserted-by":"publisher","first-page":"2763","DOI":"10.1109\/TMI.2023.3264513","volume":"42","author":"A He","year":"2023","unstructured":"He, A. et al. H2former: an efficient hierarchical hybrid transformer for medical image segmentation. IEEE Trans. Med. Imaging 42, 2763\u20132775 (2023).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1829_CR34","doi-asserted-by":"publisher","first-page":"109819","DOI":"10.1016\/j.patcog.2023.109819","volume":"143","author":"G Xu","year":"2023","unstructured":"Xu, G. et al. Haar wavelet downsampling: a simple but effective downsampling module for semantic segmentation. Pattern Recognit. 143, 109819 (2023).","journal-title":"Pattern Recognit."},{"key":"1829_CR35","doi-asserted-by":"crossref","unstructured":"Liu, W., Lu, H., Fu, H. & Cao, Z. Learning to upsample by learning to sample. In Proc. IEEE\/CVF International Conference on Computer Vision 6027\u20136037 (IEEE, 2023).","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"1829_CR36","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","volume":"21","author":"H Li","year":"2024","unstructured":"Li, H. et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures. J. Real Time Image Process. 21, 62 (2024).","journal-title":"J. Real Time Image Process."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01829-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01829-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01829-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T04:44:15Z","timestamp":1757220255000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01829-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1829"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01829-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6481879\/v1","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,10]]},"assertion":[{"value":"19 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The collection of BT-Seg private dataset adhered to ethical standards and received approval from the Ethics Review Committee of Second Xiangya Hospital, Central South University, which waived the requirement for patients\u2019 informed consent, referring to the Council for International Organizations of Medical Sciences (CIOMS) guidelines. And the data were anonymized to ensure patient privacy. Due to institutional privacy policies, these datasets are not publicly available; however, access may be granted for legitimate academic and research purposes.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"426"}}