{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:19:04Z","timestamp":1776979144723,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:00:00Z","timestamp":1774656000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:00:00Z","timestamp":1774656000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Guangxi Natural Science Foundation","award":["Grant No. 2024GXNSFFA010014"],"award-info":[{"award-number":["Grant No. 2024GXNSFFA010014"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["Grant No. 82360356)"],"award-info":[{"award-number":["Grant No. 82360356)"]}],"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":[[2026,4]]},"DOI":"10.1007\/s11760-026-05283-9","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T07:17:05Z","timestamp":1774855025000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CNN and transformer feature adaptive fusion for image segmentation with imbalanced weight information"],"prefix":"10.1007","volume":"20","author":[{"given":"Hongxiang","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjun","family":"Bian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xipeng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingqiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruojie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,28]]},"reference":[{"issue":"7","key":"5283_CR1","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.1109\/TPAMI.2021.3059968","volume":"44","author":"S Minaee","year":"2022","unstructured":"Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., Terzopoulos, D.: Image segmentation using deep learning: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3523\u20133542 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3059968","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5283_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102608","volume":"114","author":"KK Brar","year":"2025","unstructured":"Brar, K.K., Goyal, B., Dogra, A., Mustafa, M.A., Majumdar, R., Alkhayyat, A., Kukreja, V.: Image segmentation review: Theoretical background and recent advances. Information Fusion 114, 102608 (2025)","journal-title":"Information Fusion"},{"key":"5283_CR3","doi-asserted-by":"crossref","unstructured":"Koleilat, T., Asgariandehkordi, H., Rivaz, H., Xiao, Y.: Medclip-samv2: Towards universal text-driven medical image segmentation. Med. Image Anal. 103749 (2025)","DOI":"10.1016\/j.media.2025.103749"},{"key":"5283_CR4","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s11280-018-0556-3","volume":"22","author":"Q Zhou","year":"2019","unstructured":"Zhou, Q., Yang, W., Gao, G., Ou, W., Lu, H., Chen, J., Latecki, L.J.: Multi-scale deep context convolutional neural networks for semantic segmentation. World Wide Web 22, 555\u2013570 (2019)","journal-title":"World Wide Web"},{"key":"5283_CR5","doi-asserted-by":"publisher","first-page":"4652","DOI":"10.1609\/aaai.v39i5.32491","volume":"39","author":"C Li","year":"2025","unstructured":"Li, C., Liu, X., Li, W., Wang, C., Liu, H., Liu, Y., Chen, Z., Yuan, Y.: U-kan makes strong backbone for medical image segmentation and generation. Proceedings of the AAAI Conference on Artificial Intelligence 39, 4652\u20134660 (2025)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"5283_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, S., Huan, Z., Wang, H., Liu, Z., Lan, R., Pan, X.: Edge-semantic synergy fusion and adaptive noise-aware for weakly supervised pathological tissue segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 160\u2013169 (2025). Springer","DOI":"10.1007\/978-3-032-04984-1_16"},{"key":"5283_CR7","doi-asserted-by":"crossref","unstructured":"Lou, M., Yu, Y.: Overlock: An overview-first-look-closely-next convnet with context-mixing dynamic kernels. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 128\u2013138 (2025)","DOI":"10.1109\/CVPR52734.2025.00021"},{"key":"5283_CR8","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"5283_CR9","unstructured":"Meng, W., Luo, Y., Li, X., Jiang, D., Zhang, Z.: Polaformer: Polarity-aware linear attention for vision transformers. In: The Thirteenth International Conference on Learning Representations"},{"key":"5283_CR10","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"5283_CR11","doi-asserted-by":"crossref","unstructured":"Gillioz, A., Casas, J., Mugellini, E., Abou\u00a0Khaled, O.: Overview of the transformer-based models for nlp tasks. In: 2020 15th Conference on Computer Science and Information Systems (FedCSIS), pp. 179\u2013183 (2020). IEEE","DOI":"10.15439\/2020F20"},{"key":"5283_CR12","unstructured":"Miao, X., Zhu, S., Fu, F., Guo, Z., Yang, Z., Tu, Y., Jia, Z., Cui, B.: X-former elucidator: reviving efficient attention for long context language modeling. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2024)"},{"key":"5283_CR13","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5283_CR14","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"5283_CR15","doi-asserted-by":"crossref","unstructured":"Cao, X., Wang, X., Dun, X., Lian, Y., Cheng, X., Hao, X.: Cross-domain-aware deep unfolding transformer for hyperspectral image super-resolution. Pattern Recognition, 112374 (2025)","DOI":"10.1016\/j.patcog.2025.112374"},{"key":"5283_CR16","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-031-20053-3_30","volume-title":"Computer Vision - ECCV 2022","author":"H Touvron","year":"2022","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: Deit iii: Revenge of the vit. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 516\u2013533. Springer, Cham (2022)"},{"key":"5283_CR17","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"5283_CR18","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhang, Y., Xu, L., Jin, S., Chen, Y.: Ultra-high resolution segmentation via boundary-enhanced patch-merging transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 7087\u20137095 (2025)","DOI":"10.1609\/aaai.v39i7.32761"},{"issue":"6","key":"5283_CR19","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1109\/TMI.2024.3362879","volume":"43","author":"H Kuang","year":"2024","unstructured":"Kuang, H., Wang, Y., Liu, J., Wang, J., Cao, Q., Hu, B., Qiu, W., Wang, J.: Hybrid cnn-transformer network with circular feature interaction for acute ischemic stroke lesion segmentation on non-contrast ct scans. IEEE Trans. Med. Imaging 43(6), 2303\u20132316 (2024). https:\/\/doi.org\/10.1109\/TMI.2024.3362879","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"10","key":"5283_CR20","doi-asserted-by":"publisher","first-page":"4521","DOI":"10.1007\/s11263-024-02101-y","volume":"132","author":"M Cao","year":"2024","unstructured":"Cao, M., Wang, L., Zhu, M., Yuan, X.: Hybrid cnn-transformer architecture for efficient large-scale video snapshot compressive imaging. Int. J. Comput. Vision 132(10), 4521\u20134540 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"5283_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110491","volume":"152","author":"X Guo","year":"2024","unstructured":"Guo, X., Lin, X., Yang, X., Yu, L., Cheng, K.-T., Yan, Z.: Uctnet: Uncertainty-guided cnn-transformer hybrid networks for medical image segmentation. Pattern Recogn. 152, 110491 (2024)","journal-title":"Pattern Recogn."},{"key":"5283_CR22","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":"5283_CR23","first-page":"1","volume":"62","author":"J He","year":"2024","unstructured":"He, J., Chen, J., Xu, H., Yu, Y.: Sonarnet: Hybrid cnn-transformer-hog framework and multifeature fusion mechanism for forward-looking sonar image segmentation. IEEE Trans. Geosci. Remote Sens. 62, 1\u201317 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"5283_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108762","volume":"219","author":"X Li","year":"2024","unstructured":"Li, X., Li, X., Zhang, M., Dong, Q., Zhang, G., Wang, Z., Wei, P.: Sugarcanegan: A novel dataset generating approach for sugarcane leaf diseases based on lightweight hybrid cnn-transformer network. Comput. Electron. Agric. 219, 108762 (2024)","journal-title":"Comput. Electron. Agric."},{"key":"5283_CR25","doi-asserted-by":"crossref","unstructured":"Feng, S., Chen, J., Liu, Z., Liu, W., Wang, Z., Lan, R., Pan, X.: Mining gold from the sand: Weakly supervised histological tissue segmentation with activation relocalization and mutual learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 414\u2013423 (2024). Springer","DOI":"10.1007\/978-3-031-72111-3_39"},{"key":"5283_CR26","doi-asserted-by":"crossref","unstructured":"He, Y., Guo, P., Tang, Y., Myronenko, A., Nath, V., Xu, Z., Yang, D., Zhao, C., Simon, B., Belue, M., et al.: Vista3d: A unified segmentation foundation model for 3d medical imaging. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 20863\u201320873 (2025)","DOI":"10.1109\/CVPR52734.2025.01943"},{"key":"5283_CR27","doi-asserted-by":"crossref","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. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"5283_CR28","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"5283_CR29","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"5283_CR30","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 (2018). Springer","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"5283_CR31","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"issue":"2","key":"5283_CR32","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1118\/1.3528204","volume":"38","author":"SG Armato III","year":"2011","unstructured":"Armato, S.G., III., McLennan, G., Bidaut, L., McNitt-Gray, M.F., Meyer, C.R., Reeves, A.P., Zhao, B., Aberle, D.R., Henschke, C.I., Hoffman, E.A., et al.: The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans. Med. Phys. 38(2), 915\u2013931 (2011)","journal-title":"Med. Phys."},{"issue":"4","key":"5283_CR33","doi-asserted-by":"publisher","first-page":"2923","DOI":"10.1007\/s10462-022-10245-x","volume":"56","author":"P Jyothi","year":"2023","unstructured":"Jyothi, P., Singh, A.R.: Deep learning models and traditional automated techniques for brain tumor segmentation in mri: a review. Artif. Intell. Rev. 56(4), 2923\u20132969 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"5283_CR34","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 (2015). Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5283_CR35","doi-asserted-by":"crossref","unstructured":"Drozdzal, M., Vorontsov, E., Chartrand, G., Kadoury, S., Pal, C.: The importance of skip connections in biomedical image segmentation. In: International Workshop on Deep Learning in Medical Image Analysis, International Workshop on Large-scale Annotation of Biomedical Data and Expert Label Synthesis, pp. 179\u2013187 (2016). Springer","DOI":"10.1007\/978-3-319-46976-8_19"},{"key":"5283_CR36","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 (2021). Springer","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"5283_CR37","doi-asserted-by":"crossref","unstructured":"Du, S., Bayasi, N., Hamarneh, G., Garbi, R.: Avit: Adapting vision transformers for small skin lesion segmentation datasets. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 25\u201336 (2023). Springer","DOI":"10.1007\/978-3-031-47401-9_3"},{"key":"5283_CR38","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"5283_CR39","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"issue":"1","key":"5283_CR40","first-page":"9580991","volume":"2022","author":"P Malhotra","year":"2022","unstructured":"Malhotra, P., Gupta, S., Koundal, D., Zaguia, A., Enbeyle, W.: [retracted] deep neural networks for medical image segmentation. Journal of Healthcare Engineering 2022(1), 9580991 (2022)","journal-title":"Journal of Healthcare Engineering"},{"key":"5283_CR41","unstructured":"Jha, D., Tomar, N.K., Sharma, V., Bagci, U.: Transnetr: transformer-based residual network for polyp segmentation with multi-center out-of-distribution testing. In: Medical Imaging with Deep Learning, pp. 1372\u20131384 (2024). PMLR"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05283-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05283-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05283-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:31:33Z","timestamp":1776976293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05283-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,28]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["5283"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05283-9","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,28]]},"assertion":[{"value":"18 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"216"}}