{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:56:24Z","timestamp":1787003784874,"version":"build-2736575974"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"vor","delay-in-days":47,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"The 2024 Basic Scientific Research Business Expenses Project of Heilongjiang Provincial Undergraduate Universities","award":["2024KYYWF-0345"],"award-info":[{"award-number":["2024KYYWF-0345"]}]},{"name":"Qiqihar Science and Technology Plan Joint Guidance Project","award":["LHYD-2021042"],"award-info":[{"award-number":["LHYD-2021042"]}]},{"name":"the science and technology planning project of qiqhar","award":["LSFGG-2025131"],"award-info":[{"award-number":["LSFGG-2025131"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>While the segmentation of anatomical structures and pathological regions is indispensable for reliable disease assessment, contemporary algorithms often fail to achieve sharp demarcation. This deficiency stems from the high degree of morphological heterogeneity across different cases, which results in obscured contours and compromised segmentation accuracy. To address this gap, we propose a dual-branch attention network (D3T-Net) that combines deep split convolution and multi-dimensional Transformer. This network introduces parallel CNN branches and Transformer branches in the encoder and decoder, respectively, to capture local details and model global contextual information. In the CNN branch, a deep split module (DSM) is designed to enhance local representations through multiple sub-branches and fusion attention mechanisms. The Transformer stream employs multi-dimensional modules to capture extensive spatial and channel-wise dependencies, thereby mitigating the localized limitations inherent in standard self-attention. To facilitate robust feature exchange between the two pathways, we introduce a direction-aware interaction attention (LA) module within the encoder, designed to accentuate critical structural characteristics across various orientations. In the decoder, a cross-attention mechanism is introduced to achieve feature reorganization and integration. Additionally, to enhance feature expression capabilities, the model adopts a multi-scale fusion skip connection mechanism between the encoder and decoder to achieve efficient feature transfer, improve boundary retention ability, and enhance the segmentation effect of small objects. Extensive evaluations reveal that D3T-Net surpasses contemporary benchmarks in segmenting the liver and associated lesions. Such advancements in automated image analysis effectively augment diagnostic accuracy, thereby offering robust support for precision medicine in hepatology.<\/jats:p>","DOI":"10.1038\/s41598-026-44413-8","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T17:06:06Z","timestamp":1773939966000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dual-branch attention network with deep split convolution and multi-dimensional transformers for medical image segmentation"],"prefix":"10.1038","volume":"16","author":[{"given":"Debao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yexiang","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haobo","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"44413_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105814","volume":"89","author":"Z Huang","year":"2024","unstructured":"Huang, Z., Ling, Z., Gou, F. & Wu, J. Medical assisted-segmentation system based on global feature and stepwise feature integration for feature loss problem. Biomed. Signal Process. Control 89, 105814 (2024).","journal-title":"Biomed. Signal Process. Control"},{"key":"44413_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92715-0","volume":"15","author":"Z Wang","year":"2025","unstructured":"Wang, Z. et al. Dual-branch dynamic hierarchical u-net with multi-layer space fusion attention for medical image segmentation. Sci. Rep. 15, 8194 (2025).","journal-title":"Sci. Rep."},{"key":"44413_CR3","doi-asserted-by":"publisher","first-page":"17677","DOI":"10.1007\/s11042-024-19694-8","volume":"84","author":"A Nazir","year":"2025","unstructured":"Nazir, A., Hussain, A., Singh, M. & Assad, A. Deep learning in medicine: Advancing healthcare with intelligent solutions and the future of holography imaging in early diagnosis. Multimed. Tools Appl. 84, 17677\u201317740 (2025).","journal-title":"Multimed. Tools Appl."},{"key":"44413_CR4","doi-asserted-by":"publisher","first-page":"13521","DOI":"10.1007\/s10462-023-10466-8","volume":"56","author":"SF Ahmed","year":"2023","unstructured":"Ahmed, S. F. et al. Deep learning modelling techniques: Current progress, applications, advantages, and challenges. Artif. Intell. Rev. 56, 13521\u201313617 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"44413_CR5","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","volume":"57","author":"X Zhao","year":"2024","unstructured":"Zhao, X. et al. A review of convolutional neural networks in computer vision. Artif. Intell. Rev. 57, 99 (2024).","journal-title":"Artif. Intell. Rev."},{"key":"44413_CR6","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1007\/s10586-023-03979-y","volume":"27","author":"S Kassaymeh","year":"2024","unstructured":"Kassaymeh, S., Alweshah, M., Al-Betar, M. A., Hammouri, A. I. & Al-Ma\u2019aitah, M. A. Software effort estimation modeling and fully connected artificial neural network optimization using soft computing techniques. Cluster Comput. 27, 737\u2013760 (2024).","journal-title":"Cluster Comput."},{"key":"44413_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435571","author":"R Azad","year":"2024","unstructured":"Azad, R. et al. Medical image segmentation review: The success of u-net. IEEE Trans. Pattern Anal. Mach. Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3435571 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44413_CR8","doi-asserted-by":"crossref","unstructured":"Peng, Y., Chen, D.\u00a0Z. & Sonka, M. U-net v2: Rethinking the skip connections of u-net for medical image segmentation. In 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), 1\u20135 (IEEE, 2025).","DOI":"10.1109\/ISBI60581.2025.10980742"},{"key":"44413_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280","volume":"97","author":"J Chen","year":"2024","unstructured":"Chen, J. et al. Transunet: Rethinking the u-net architecture design for medical image segmentation through the lens of transformers. Med. Image Anal. 97, 103280 (2024).","journal-title":"Med. Image Anal."},{"key":"44413_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102800","volume":"150","author":"X Shu","year":"2024","unstructured":"Shu, X., Wang, J., Zhang, A., Shi, J. & Wu, X.-J. Csca u-net: A channel and space compound attention CNN for medical image segmentation. Artif. Intell. Med. 150, 102800 (2024).","journal-title":"Artif. Intell. Med."},{"key":"44413_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108013","volume":"170","author":"B Fu","year":"2024","unstructured":"Fu, B. et al. Hmsu-net: A hybrid multi-scale u-net based on a CNN and transformer for medical image segmentation. Comput. Biol. Med. 170, 108013 (2024).","journal-title":"Comput. Biol. Med."},{"key":"44413_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00842-0","volume":"11","author":"H Zhang","year":"2024","unstructured":"Zhang, H. & Shafiq, M. O. Survey of transformers and towards ensemble learning using transformers for Natural Language Processing. J. Big Data 11, 25 (2024).","journal-title":"J. Big Data"},{"key":"44413_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110057","volume":"144","author":"Y Haruna","year":"2025","unstructured":"Haruna, Y. et al. Exploring the synergies of hybrid convolutional neural network and vision transformer architectures for computer vision: A survey. Eng. Appl. Artif. Intell. 144, 110057 (2025).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"44413_CR14","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K. et al. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 45, 87\u2013110 (2022).","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"44413_CR15","doi-asserted-by":"crossref","unstructured":"Tragakis, A., Kaul, C., Murray-Smith, R. & Husmeier, D. The fully convolutional transformer for medical image segmentation. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 3660\u20133669 (2023).","DOI":"10.1109\/WACV56688.2023.00365"},{"key":"44413_CR16","doi-asserted-by":"publisher","first-page":"195","DOI":"10.3390\/info16030195","volume":"16","author":"ID Mienye","year":"2025","unstructured":"Mienye, I. D., Swart, T. G., Obaido, G., Jordan, M. & Ilono, P. Deep convolutional neural networks in medical image analysis: A review. Information 16, 195 (2025).","journal-title":"Information"},{"key":"44413_CR17","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","volume":"173","author":"T Kattenborn","year":"2021","unstructured":"Kattenborn, T., Leitloff, J., Schiefer, F. & Hinz, S. Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS J. Photogramm. Remote Sens. 173, 24\u201349 (2021).","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"44413_CR18","doi-asserted-by":"publisher","first-page":"12041","DOI":"10.1038\/s41598-025-96101-8","volume":"15","author":"P Pan","year":"2025","unstructured":"Pan, P., Zhang, C., Sun, J. & Guo, L. Multi-scale conv-attention U-Net for medical image segmentation. Sci. Rep. 15, 12041 (2025).","journal-title":"Sci. Rep."},{"key":"44413_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, M.\u00a0M., Tajbakhsh, N. & Liang, J. Unet++: A nested u-net architecture for medical image segmentation. In International workshop on deep learning in medical image analysis, 3\u201311 (Springer, 2018).","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"44413_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpcardiol.2023.102129","volume":"49","author":"N Das","year":"2024","unstructured":"Das, N. & Das, S. Attention-Unet architectures with pretrained backbones for multi-class cardiac MR image segmentation. Curr. Probl. Cardiol. 49, 102129 (2024).","journal-title":"Curr. Probl. Cardiol."},{"key":"44413_CR21","doi-asserted-by":"crossref","unstructured":"Alom, M.\u00a0Z., Yakopcic, C., Taha, T.\u00a0M. & Asari, V.\u00a0K. Nuclei segmentation with recurrent residual convolutional neural networks based u-net (r2u-net). In NAECON 2018-IEEE National Aerospace and Electronics Conference, 228\u2013233 (IEEE, 2018).","DOI":"10.1109\/NAECON.2018.8556686"},{"key":"44413_CR22","doi-asserted-by":"publisher","first-page":"063012","DOI":"10.1117\/1.JEI.32.6.063012","volume":"32","author":"C Chen","year":"2023","unstructured":"Chen, C., Shi, J., Xu, Z. & Wang, Z. Attention Unet3+: A full-scale connected attention-aware Unet for CT image segmentation of liver. J. Electron. Imaging 32, 063012\u2013063012 (2023).","journal-title":"J. Electron. Imaging"},{"key":"44413_CR23","doi-asserted-by":"crossref","unstructured":"Wolf, T. et al. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, 38\u201345 (2020).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"44413_CR24","doi-asserted-by":"crossref","unstructured":"Arnab, A. et al. Vivit: A video vision transformer. In Proceedings of the IEEE\/CVF international conference on computer vision, 6836\u20136846 (2021).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"44413_CR25","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.\u00a0R., Fan, Q. & Panda, R. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE\/CVF international conference on computer vision, 357\u2013366 (2021).","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"44413_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107141","volume":"226","author":"GI Okolo","year":"2022","unstructured":"Okolo, G. I., Katsigiannis, S. & Ramzan, N. Ievit: An enhanced vision transformer architecture for chest x-ray image classification. Comput. Methods Programs Biomed. 226, 107141 (2022).","journal-title":"Comput. Methods Programs Biomed."},{"key":"44413_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106791","volume":"157","author":"ON Manzari","year":"2023","unstructured":"Manzari, O. N., Ahmadabadi, H., Kashiani, H., Shokouhi, S. B. & Ayatollahi, A. Medvit: A robust vision transformer for generalized medical image classification. Comput. Biol. Med. 157, 106791 (2023).","journal-title":"Comput. Biol. Med."},{"key":"44413_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3554184","author":"T Hussain","year":"2025","unstructured":"Hussain, T. et al. Effresnet-vit: A fusion-based convolutional and vision transformer model for explainable medical image classification. IEEE Access https:\/\/doi.org\/10.1109\/ACCESS.2025.3554184 (2025).","journal-title":"IEEE Access"},{"key":"44413_CR29","unstructured":"Chen, J. et al. 3d transunet: Advancing medical image segmentation through vision transformers. arXiv:2310.07781 (2023)."},{"key":"44413_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W. et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE\/CVF international conference on computer vision, 568\u2013578 (2021).","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"44413_CR31","doi-asserted-by":"publisher","first-page":"2847","DOI":"10.1007\/s13042-023-01802-z","volume":"14","author":"P Song","year":"2023","unstructured":"Song, P., Li, J., Fan, H. & Fan, L. Dbcgn: Dual branch cascade graph network for skin lesion segmentation. Int. J. Mach. Learn. Cybern. 14, 2847\u20132865 (2023).","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"44413_CR32","unstructured":"Hou, R., Chang, H., Ma, B., Shan, S. & Chen, X. Cross attention network for few-shot classification. Advances in neural information processing systems 32 (2019)."},{"key":"44413_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Dong, J., Tang, J. & Pan, J. Dlgsanet: lightweight dynamic local and global self-attention networks for image super-resolution. In Proceedings of the IEEE\/CVF international conference on computer vision, 12792\u201312801 (2023).","DOI":"10.1109\/ICCV51070.2023.01175"},{"key":"44413_CR34","doi-asserted-by":"crossref","unstructured":"Chen, S. et al. Sparse sampling transformer with uncertainty-driven ranking for unified removal of raindrops and rain streaks. In Proceedings of the IEEE\/CVF international conference on computer vision, 13106\u201313117 (2023).","DOI":"10.1109\/ICCV51070.2023.01205"},{"key":"44413_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J. & Koltun, V. Exploring self-attention for image recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 10076\u201310085 (2020).","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"44413_CR36","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"44413_CR37","doi-asserted-by":"crossref","unstructured":"Cao, H. et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision, 205\u2013218 (Springer, 2022).","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"44413_CR38","doi-asserted-by":"crossref","unstructured":"Heidari, M. et al. Hiformer: Hierarchical multi-scale representations using transformers for medical image segmentation. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, 6202\u20136212 (2023).","DOI":"10.1109\/WACV56688.2023.00614"},{"key":"44413_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106626","volume":"154","author":"Q Xu","year":"2023","unstructured":"Xu, Q. et al. Dcsau-net: A deeper and more compact split-attention u-net for medical image segmentation. Comput. Biol. Med. 154, 106626 (2023).","journal-title":"Comput. Biol. Med."},{"key":"44413_CR40","unstructured":"Jiao, Y. et al. Tm-unet: Token-memory enhanced sequential modeling for efficient medical image segmentation. arXiv:2511.12270 (2025)."},{"key":"44413_CR41","unstructured":"Xu, Q. et al. Hrmedseg: Unlocking high-resolution medical image segmentation via memory-efficient attention modeling. arXiv:2504.06205(2025)."},{"key":"44413_CR42","doi-asserted-by":"publisher","unstructured":"Xu, Q., Luo, Y., Duan, W. & Chen, Z. Co-seg++: Mutual prompt-guided collaborative learning for versatile medical segmentation. IEEE Trans. Med. Imaging https:\/\/doi.org\/10.1109\/TMI.2025.3643631 (2025).","DOI":"10.1109\/TMI.2025.3643631"},{"key":"44413_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.131137","author":"Y Zhao","year":"2025","unstructured":"Zhao, Y. et al. Spatio-temporal memory-driven CT organ segmentation with hybrid CNN-mamba encoding and frequency-domain decoding. Neurocomputing https:\/\/doi.org\/10.1016\/j.neucom.2025.131137 (2025).","journal-title":"Neurocomputing"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44413-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44413-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44413-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:17:58Z","timestamp":1778581078000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44413-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["44413"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-44413-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"23 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2026","order":3,"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":"14238"}}