{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T01:44:26Z","timestamp":1782956666435,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":61,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Liaoning Provincial Science and Technology Plan Joint Program","award":["JH4\/4800; 2024-MSLH-476"],"award-info":[{"award-number":["JH4\/4800; 2024-MSLH-476"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Long-tail segmentation is a crucial challenge in computer vision, where most models prioritize common head classes over rare tail classes. This problem is particularly prominent in retinal vessel segmentation, as conventional approaches often struggle to overcome underrepresented faint vessels, noise-induced boundary ambiguity, and excessive parameters that prohibit portable deployment. To address these challenges, we introduce LFU-Net, a lightweight and clinically applicable method for long-tail retinal vessel segmentation. It integrates a three-component ensemble: a Frequency-Aware Encoder with a Multi-Branch Frequency Convolution block, which uses wavelet decomposition to suppress noise and retain details; Hierarchical frequency-token enhanced Low-Rank Adaptation, which efficiently enhances the representation of tail classes (faint vessels) with minimal parameters; and a Recursive Residual Attention Fusion module to ensure vascular topological continuity. Extensive experiments on four public benchmark datasets demonstrate that LFU-Net achieves competitive performance compared to recent relevant models. Its lightweight nature supports real-time inference on portable devices. Ablation studies confirm the improvement contribution of each core component, indicating its potential utility in early disease detection when clinical resources are limited.<\/jats:p>","DOI":"10.1038\/s41598-026-50642-8","type":"journal-article","created":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:24:26Z","timestamp":1777706666000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LFU-Net: LoRA-enhanced frequency-aware U-Net with recursive residual attention fusion for retinal segmentation"],"prefix":"10.1038","volume":"16","author":[{"given":"Zhongshi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Luan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxia","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiulan","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,2]]},"reference":[{"key":"50642_CR1","doi-asserted-by":"publisher","unstructured":"Ye, L., Huang, X. & Xu, Y. Global trends and disparities in burden of blindness and vision loss caused by non-communicable diseases from 1990 to 2021, and forecasts to 2045: A systematic analysis for the global burden of disease study 2021. Frontiers in Medicine12, https:\/\/doi.org\/10.3389\/fmed.2025.1561568 (2025).","DOI":"10.3389\/fmed.2025.1561568"},{"key":"50642_CR2","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.preteyeres.2013.07.002","volume":"36","author":"T Bek","year":"2013","unstructured":"Bek, T. Regional morphology and pathophysiology of retinal vascular disease. Prog. Retin. Eye Res. 36, 247\u2013259. https:\/\/doi.org\/10.1016\/j.preteyeres.2013.07.002 (2013).","journal-title":"Prog. Retin. Eye Res."},{"key":"50642_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2024.101263","volume":"101","author":"Y Sun","year":"2024","unstructured":"Sun, Y. et al. Targeting inflammasomes and pyroptosis in retinal diseases\u2013molecular mechanisms and future perspectives. Prog. Retin. Eye Res. 101, 101263. https:\/\/doi.org\/10.1016\/j.preteyeres.2024.101263 (2024).","journal-title":"Prog. Retin. Eye Res."},{"key":"50642_CR4","doi-asserted-by":"publisher","unstructured":"Ye, R. et al. LiCAM: Long-tailed instance segmentation with real-time classification accuracy monitoring. Journal of Circuits, Systems and Computers32, https:\/\/doi.org\/10.1142\/s0218126623500329 (2022).","DOI":"10.1142\/s0218126623500329"},{"key":"50642_CR5","doi-asserted-by":"publisher","unstructured":"Ronneberger, Olaf, Fischer, Philipp & Brox, Thomas. U-Net: Convolutional Networks for Biomedical Image Segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)9351, 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (Springer) (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"50642_CR6","doi-asserted-by":"publisher","first-page":"12359","DOI":"10.1007\/s00500-024-09953-z","volume":"28","author":"A Talamantes-Roman","year":"2024","unstructured":"Talamantes-Roman, A., Ramirez-Alonso, G., Gaxiola, F., Prieto-Ordaz, O. & Lopez-Flores, D. R. A TransUNet model with an adaptive fuzzy focal loss for medical image segmentation. Soft. Comput. 28, 12359\u201312375. https:\/\/doi.org\/10.1007\/s00500-024-09953-z (2024).","journal-title":"Soft. Comput."},{"key":"50642_CR7","doi-asserted-by":"publisher","unstructured":"Balzano, L. et al. An overview of low-rank structures in the training and adaptation of large models, https:\/\/doi.org\/10.48550\/ARXIV.2503.19859 (2025). arXiv: 2503.19859.","DOI":"10.48550\/ARXIV.2503.19859"},{"key":"50642_CR8","doi-asserted-by":"publisher","unstructured":"Gwetu, M.\u00a0V., Tapamo, J.\u00a0R. & Viriri, S. Segmentation of retinal blood vessels using normalized gabor filters and automatic thresholding. South African Computer Journal53, https:\/\/doi.org\/10.18489\/sacj.v55i0.228 (2014).","DOI":"10.18489\/sacj.v55i0.228"},{"key":"50642_CR9","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1155\/2015\/895267","volume":"1\u201315","author":"T Mapayi","year":"2015","unstructured":"Mapayi, T., Viriri, S. & Tapamo, J.-R. Comparative study of retinal vessel segmentation based on global thresholding techniques. Comput. Math. Methods Med. 1\u201315, 2015. https:\/\/doi.org\/10.1155\/2015\/895267 (2015).","journal-title":"Comput. Math. Methods Med."},{"key":"50642_CR10","doi-asserted-by":"publisher","unstructured":"Xu, W.-H., Yi, F.-L., Wang, W.-J. & Zang, J. Segmenting the retinal hemorrhage in fundus with marked-cluster segmentation and pre-segment using OTSU and morphological segmentation. 2016 International Conference on Machine Learning and Cybernetics (ICMLC) 257\u2013261, https:\/\/doi.org\/10.1109\/icmlc.2016.7860910 (2016).","DOI":"10.1109\/icmlc.2016.7860910"},{"key":"50642_CR11","unstructured":"Zhu, C. et al. A survey of retinal vessel segmentation in fundus images. Journal of Computer-Aided Design & Computer Graphics (2015)."},{"key":"50642_CR12","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.bbe.2015.06.004","volume":"36","author":"R GeethaRamani","year":"2016","unstructured":"GeethaRamani, R. & Balasubramanian, L. Retinal blood vessel segmentation employing image processing and data mining techniques for computerized retinal image analysis. Biocybernet. Biomed. Eng. 36, 102\u2013118. https:\/\/doi.org\/10.1016\/j.bbe.2015.06.004 (2016).","journal-title":"Biocybernet. Biomed. Eng."},{"key":"50642_CR13","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Rahman Siddiquee, M.\u00a0M., Tajbakhsh, N. & Liang, J. UNet++: A nested U-net architecture for medical image segmentation. In Stoyanov, D. et al. (eds.) Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, vol. 11045, 3\u201311, https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1 (Springer International Publishing, Cham, 2018).","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"50642_CR14","doi-asserted-by":"crossref","unstructured":"Wang, B., Qiu, S. & He, H. Dual encoding u-net for retinal vessel segmentation. In Shen, D. et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, 84\u201392 (Springer International Publishing, Cham, 2019).","DOI":"10.1007\/978-3-030-32239-7_10"},{"key":"50642_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, S. et al. Attention guided network for retinal image segmentation. In Shen, D. et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, 797\u2013805 (Springer International Publishing, Cham, 2019).","DOI":"10.1007\/978-3-030-32239-7_88"},{"key":"50642_CR16","doi-asserted-by":"publisher","first-page":"2616","DOI":"10.3390\/electronics11162616","volume":"11","author":"R Liu","year":"2022","unstructured":"Liu, R., Nan, H., Zou, Y., Xie, T. & Ye, Z. LSW-net: A learning scattering wavelet network for brain tumor and retinal image segmentation. Electronics 11, 2616. https:\/\/doi.org\/10.3390\/electronics11162616 (2022).","journal-title":"Electronics"},{"key":"50642_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105355","volume":"86","author":"X Li","year":"2023","unstructured":"Li, X., Zheng, Y., Zang, M. & Jiao, W. Wavelet transform and edge loss-based three-stage segmentation model for retinal vessel. Biomed. Signal Process. Control 86, 105355. https:\/\/doi.org\/10.1016\/j.bspc.2023.105355 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"50642_CR18","doi-asserted-by":"publisher","unstructured":"Makkar, V., Tewary, A., Pandey, R.\u00a0K. & Pachori, R.\u00a0B. Collation of a few retinal vessel segmentation techniques: Is the problem solved? SN Computer Science6, https:\/\/doi.org\/10.1007\/s42979-025-03722-x (2025).","DOI":"10.1007\/s42979-025-03722-x"},{"key":"50642_CR19","doi-asserted-by":"publisher","unstructured":"Mehmood, M., Spence, I. & Fahim, M. LFA-net: A lightweight network with LiteFusion attention for retinal vessel segmentation, https:\/\/doi.org\/10.48550\/ARXIV.2509.21738 (2025). arXiv: 2509.21738.","DOI":"10.48550\/ARXIV.2509.21738"},{"key":"50642_CR20","doi-asserted-by":"publisher","first-page":"194551","DOI":"10.1109\/access.2020.3033273","volume":"8","author":"X Guo","year":"2020","unstructured":"Guo, X. et al. Retinal vessel segmentation combined with generative adversarial networks and dense u-net. IEEE Access 8, 194551\u2013194560. https:\/\/doi.org\/10.1109\/access.2020.3033273 (2020).","journal-title":"IEEE Access"},{"key":"50642_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106829","volume":"158","author":"L Du","year":"2023","unstructured":"Du, L. et al. Deep ensemble learning for accurate retinal vessel segmentation. Comput. Biol. Med. 158, 106829. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.106829 (2023).","journal-title":"Comput. Biol. Med."},{"key":"50642_CR22","unstructured":"Hu, E. J. et al. Lora: Low-rank adaptation of large language models. In Advances in Neural Information Processing Systems, vol 34, 0\u201313, https:\/\/doi.org\/10.48550\/arXiv.2106.09685 (2021)"},{"key":"50642_CR23","doi-asserted-by":"publisher","unstructured":"Mahla, N., D\u2019souza, A., Gupta, S., Kanekar, B. & Jadhav, K.\u00a0S. MedSAGa: Few-shot memory efficient medical image segmentation using gradient low-rank projection in SAM, https:\/\/doi.org\/10.48550\/ARXIV.2407.15042 (2024). arXiv: 2407.15042.","DOI":"10.48550\/ARXIV.2407.15042"},{"key":"50642_CR24","doi-asserted-by":"publisher","unstructured":"Baklouti, G., Silva-Rodr\u00edguez, J., Dolz, J., Bahig, H. & Ayed, I.\u00a0B. Regularized low-rank adaptation for few-shot organ segmentation, https:\/\/doi.org\/10.48550\/ARXIV.2507.15793 (2025). arXiv: 2507.15793.","DOI":"10.48550\/ARXIV.2507.15793"},{"key":"50642_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.101981","volume":"36","author":"P Fan","year":"2024","unstructured":"Fan, P., Diao, Y., Li, F., Zhao, W. & Chen, Z. SRSegNet: Super-resolution-assisted small targets polyp segmentation network with combined high and low resolution. J. King Saud Univ. - Computer Inf. Sci. 36, 101981. https:\/\/doi.org\/10.1016\/j.jksuci.2024.101981 (2024).","journal-title":"J. King Saud Univ. - Computer Inf. Sci."},{"key":"50642_CR26","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. MobileNetV2: Inverted residuals and linear bottlenecks. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4510\u20134520, https:\/\/doi.org\/10.1109\/CVPR.2018.00474 (IEEE, Salt Lake City, UT, 2018).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"50642_CR27","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3390\/bioengineering11050468","volume":"11","author":"Z Hong","year":"2024","unstructured":"Hong, Z., Xiong, J., Yang, H. & Mo, Y. K. Lightweight low-rank adaptation vision transformer framework for cervical cancer detection and cervix type classification. Bioengineering 11, 468. https:\/\/doi.org\/10.3390\/bioengineering11050468 (2024).","journal-title":"Bioengineering"},{"key":"50642_CR28","doi-asserted-by":"publisher","unstructured":"Kisel, N., Volkov, I., Hanzelkova, K., Janouskova, K. & Matas, J. Flaws of ImageNet, computer vision\u2019s favourite dataset, https:\/\/doi.org\/10.48550\/ARXIV.2412.00076 (2024). , arXiv: 2412.00076.","DOI":"10.48550\/ARXIV.2412.00076"},{"key":"50642_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104829","volume":"85","author":"J Ni","year":"2023","unstructured":"Ni, J., Sun, H., Xu, J., Liu, J. & Chen, Z. A feature aggregation and feature fusion network for retinal vessel segmentation. Biomed. Signal Process. Control 85, 104829. https:\/\/doi.org\/10.1016\/j.bspc.2023.104829 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"50642_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128124","volume":"287","author":"K Li","year":"2025","unstructured":"Li, K., Zhang, Y., Wang, T. & Lei, B. FreqUNet: A lightweight dual-branch network with frequency-aware decomposition for retinal vessel segmentation. Expert Syst. Appl. 287, 128124. https:\/\/doi.org\/10.1016\/j.eswa.2025.128124 (2025).","journal-title":"Expert Syst. Appl."},{"key":"50642_CR31","doi-asserted-by":"publisher","unstructured":"Yang, X. & Agam, G. MSLoRA: Multi-scale low-rank adaptation via attention reweighting, https:\/\/doi.org\/10.48550\/ARXIV.2511.12400 (2025). , arXiv: 2511.12400.","DOI":"10.48550\/ARXIV.2511.12400"},{"key":"50642_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110078","volume":"192","author":"S Umirzakova","year":"2025","unstructured":"Umirzakova, S., Muksimova, S., Mardieva, S. & Whangbo, T. K. Deep learning for multiple sclerosis lesion classification and stratification using mri. Comput. Biol. Med. 192, 110078. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.110078 (2025).","journal-title":"Comput. Biol. Med."},{"key":"50642_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106280","volume":"175","author":"Y Chen","year":"2024","unstructured":"Chen, Y. et al. Medical image segmentation network based on multi-scale frequency domain filter. Neural Netw. 175, 106280. https:\/\/doi.org\/10.1016\/j.neunet.2024.106280 (2024).","journal-title":"Neural Netw."},{"key":"50642_CR34","doi-asserted-by":"publisher","first-page":"3196","DOI":"10.1109\/tmi.2025.3559402","volume":"44","author":"Y Chu","year":"2025","unstructured":"Chu, Y. et al. Improving representation of high-frequency components for medical visual foundation models. IEEE Trans. Med. Imaging 44, 3196\u20133209. https:\/\/doi.org\/10.1109\/tmi.2025.3559402 (2025).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"50642_CR35","doi-asserted-by":"publisher","unstructured":"Xu, Y., Fang, L., Li, X. & Zhang, C. ERN: An edge reconstruction network for image super-resolution diffusion model. Knowledge-Based Systems 115016, https:\/\/doi.org\/10.1016\/j.knosys.2025.115016 (2025).","DOI":"10.1016\/j.knosys.2025.115016"},{"key":"50642_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109107","volume":"115","author":"R Vij","year":"2024","unstructured":"Vij, R. & Arora, S. A hybrid evolutionary weighted ensemble of deep transfer learning models for retinal vessel segmentation and diabetic retinopathy detection. Comput. Electr. Eng. 115, 109107. https:\/\/doi.org\/10.1016\/j.compeleceng.2024.109107 (2024).","journal-title":"Comput. Electr. Eng."},{"key":"50642_CR37","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TMI.2004.825627","volume":"23","author":"J Staal","year":"2004","unstructured":"Staal, J., Abr\u00e0moff, M., Niemeijer, M., Viergever, M. & van Ginneken, B. Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23, 501\u2013509 (2004).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"50642_CR38","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1038\/s41597-022-01564-3","volume":"9","author":"K Jin","year":"2022","unstructured":"Jin, K. et al. Fives: A fundus image dataset for artificial intelligence based vessel segmentation. Sci. Data 9, 475. https:\/\/doi.org\/10.1038\/s41597-022-01564-3 (2022).","journal-title":"Sci. Data"},{"key":"50642_CR39","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/42.845178","volume":"19","author":"A Hoover","year":"2000","unstructured":"Hoover, A., Kouznetsova, V. & Goldbaum, M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging 19, 203\u2013210 (2000).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"50642_CR40","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1109\/TBME.2012.2205687","volume":"59","author":"MM Fraz","year":"2012","unstructured":"Fraz, M. M. et al. An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans. Biomed. Eng. 59, 2538\u20132548 (2012).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"50642_CR41","doi-asserted-by":"publisher","first-page":"6486","DOI":"10.1109\/tpami.2024.3382294","volume":"46","author":"P Zhou","year":"2024","unstructured":"Zhou, P., Xie, X., Lin, Z. & Yan, S. Towards understanding convergence and generalization of AdamW. IEEE Trans. Pattern Anal. Mach. Intell. 46, 6486\u20136493. https:\/\/doi.org\/10.1109\/tpami.2024.3382294 (2024).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50642_CR42","unstructured":"Loshchilov, Ilya;Hutter, Frank. SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations (ICLR 2016) (Toulon, France, 2016)."},{"key":"50642_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.120007","volume":"657","author":"W Ding","year":"2024","unstructured":"Ding, W. et al. RCAR-UNet: Retinal vessel segmentation network algorithm via novel rough attention mechanism. Inf. Sci. 657, 120007. https:\/\/doi.org\/10.1016\/j.ins.2023.120007 (2024).","journal-title":"Inf. Sci."},{"key":"50642_CR44","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1167\/tvst.11.7.12","volume":"11","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y. et al. Automorph: Automated retinal vascular morphology quantification via a deep learning pipeline. Transl. Vis. Sci. Technol. 11, 12. https:\/\/doi.org\/10.1167\/tvst.11.7.12 (2022).","journal-title":"Transl. Vis. Sci. Technol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50642-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50642-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50642-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:50:39Z","timestamp":1782953439000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50642-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,2]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["50642"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-50642-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,2]]},"assertion":[{"value":"4 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 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":"20310"}}