{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:56:43Z","timestamp":1776293803300,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T00:00:00Z","timestamp":1734739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T00:00:00Z","timestamp":1734739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Zhejiang Provincial Natural Science Foundation of  China","award":["LQ23F020021"],"award-info":[{"award-number":["LQ23F020021"]}]},{"name":"Science Foundation of Zhejiang Sci-Tech University","award":["22232262-Y"],"award-info":[{"award-number":["22232262-Y"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00371-024-03756-x","type":"journal-article","created":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T01:21:44Z","timestamp":1734744104000},"page":"5855-5872","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CaVMamba: convolution-augmented VMamba for medical image segmentation"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0595-341X","authenticated-orcid":false,"given":"Qiaohong","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zhenyang","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5161-2574","authenticated-orcid":false,"given":"Xian","family":"Fang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,21]]},"reference":[{"issue":"2","key":"3756_CR1","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1038\/s41591-023-02702-z","volume":"30","author":"L Dai","year":"2024","unstructured":"Dai, L., Sheng, B., Chen, T., Wu, Q., Liu, R., Cai, C., Wu, L., Yang, D., Hamzah, H., Liu, Y., et al.: A deep learning system for predicting time to progression of diabetic retinopathy. Nat. Med. 30(2), 584\u2013594 (2024)","journal-title":"Nat. Med."},{"key":"3756_CR2","doi-asserted-by":"publisher","unstructured":"Muksimova, S., Umirzakova, S., Mardieva, S., Cho, Y.-I.: Enhancing medical image denoising with innovative teacher-student model-based approaches for precision diagnostics. Sensors 23(23) (2023) https:\/\/doi.org\/10.3390\/s23239502","DOI":"10.3390\/s23239502"},{"issue":"11","key":"3756_CR3","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"key":"3756_CR4","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"3756_CR5","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 . Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"6","key":"3756_CR6","doi-asserted-by":"publisher","first-page":"4319","DOI":"10.1007\/s00371-023-03084-6","volume":"40","author":"W Liu","year":"2024","unstructured":"Liu, W., Li, Y., Huang, D.: Ra-unet: an improved network model for image denoising. Vis. Comput. 40(6), 4319\u20134335 (2024)","journal-title":"Vis. Comput."},{"issue":"1","key":"3756_CR7","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/TMI.2023.3289859","volume":"43","author":"J Li","year":"2023","unstructured":"Li, J., Zhang, P., Wang, T., Zhu, L., Liu, R., Yang, X., Wang, K., Shen, D., Sheng, B.: Dsmt-net: Dual self-supervised multi-operator transformation for multi-source endoscopic ultrasound diagnosis. IEEE Trans. Med. Imaging 43(1), 64\u201375 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3756_CR8","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.48550\/arXiv.2102.04306","DOI":"10.48550\/arXiv.2102.04306"},{"issue":"8","key":"3756_CR9","doi-asserted-by":"publisher","first-page":"3811","DOI":"10.1007\/s00371-023-03031-5","volume":"39","author":"R Wang","year":"2023","unstructured":"Wang, R., Duan, Y., Li, Y., Zheng, D., Liu, X., Lam, C.T., Tan, T.: Pctmf-net: heart sound classification with parallel cnns-transformer and second-order spectral analysis. Vis. Comput. 39(8), 3811\u20133822 (2023)","journal-title":"Vis. Comput."},{"issue":"1","key":"3756_CR10","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R.E.: A New Approach to Linear Filtering and Prediction Problems. J. Basic Eng. 82(1), 35\u201345 (1960). https:\/\/doi.org\/10.1115\/1.3662552","journal-title":"J. Basic Eng."},{"key":"3756_CR11","doi-asserted-by":"publisher","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently Modeling Long Sequences with Structured State Spaces. https:\/\/doi.org\/10.48550\/arXiv.2111.00396","DOI":"10.48550\/arXiv.2111.00396"},{"key":"3756_CR12","doi-asserted-by":"publisher","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time Sequence Modeling with Selective State Spaces. https:\/\/doi.org\/10.48550\/arXiv.2312.00752","DOI":"10.48550\/arXiv.2312.00752"},{"key":"3756_CR13","doi-asserted-by":"publisher","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) https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"3756_CR14","doi-asserted-by":"publisher","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Liu, Y.: Vmamba: Visual State Space Model. https:\/\/doi.org\/10.48550\/arXiv.2401.10166","DOI":"10.48550\/arXiv.2401.10166"},{"key":"3756_CR15","doi-asserted-by":"publisher","unstructured":"Yue, Y., Li, Z.: Medmamba: Vision Mamba for Medical Image Classification. https:\/\/doi.org\/10.48550\/arXiv.2403.03849","DOI":"10.48550\/arXiv.2403.03849"},{"key":"3756_CR16","doi-asserted-by":"publisher","unstructured":"Ruan, J., Xiang, S.: Vm-unet: Vision Mamba Unet for Medical Image Segmentation. https:\/\/doi.org\/10.48550\/arXiv.2402.02491","DOI":"10.48550\/arXiv.2402.02491"},{"key":"3756_CR17","doi-asserted-by":"publisher","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, pp. 3\u201311 (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1 . Springer","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"3756_CR18","doi-asserted-by":"publisher","unstructured":"Ibtehaz, N., Kihara, D.: Acc-unet: A completely convolutional unet model for the 2020s. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 692\u2013702 (2023). https:\/\/doi.org\/10.1007\/978-3-031-43898-1_66 . Springer","DOI":"10.1007\/978-3-031-43898-1_66"},{"key":"3756_CR19","doi-asserted-by":"publisher","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 (2022). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9 . Springer","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3756_CR20","doi-asserted-by":"publisher","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. 10012\u201310022 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3756_CR21","doi-asserted-by":"publisher","unstructured":"Azad, R., Arimond, R., Aghdam, E.K., Kazerouni, A., Merhof, D.: Dae-former: Dual attention-guided efficient transformer for medical image segmentation. In: International Workshop on PRedictive Intelligence In MEdicine, pp. 83\u201395 (2023). https:\/\/doi.org\/10.1007\/978-3-031-46005-0_8 . Springer","DOI":"10.1007\/978-3-031-46005-0_8"},{"key":"3756_CR22","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/WACV56688.2023.00614","DOI":"10.1109\/WACV56688.2023.00614"},{"key":"3756_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":"3756_CR24","doi-asserted-by":"publisher","unstructured":"Jin, Q., Cui, H., Sun, C., Meng, Z., Su, R.: Cascade knowledge diffusion network for skin lesion diagnosis and segmentation. Applied Soft Computing 99, 106881 (2021) https:\/\/doi.org\/10.1016\/j.asoc.2020.106881","DOI":"10.1016\/j.asoc.2020.106881"},{"key":"3756_CR25","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1007\/978-3-031-43901-8_46","volume-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2023","author":"J Ruan","year":"2023","unstructured":"Ruan, J., Xie, M., Gao, J., Liu, T., Fu, Y.: Ege-unet: An efficient group enhanced unet for\u00c2 skin lesion segmentation. In: Greenspan, H., Madabhushi, A., Mousavi, P., Salcudean, S., Duncan, J., Syeda-Mahmood, T., Taylor, R. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2023, pp. 481\u2013490. Springer, Cham (2023)"},{"key":"3756_CR26","doi-asserted-by":"publisher","unstructured":"Qiu, S., Li, C., Feng, Y., Zuo, S., Liang, H., Xu, A.: Gfanet: Gated fusion attention network for skin lesion segmentation. Computers in Biology and Medicine 155, 106462 (2023) https:\/\/doi.org\/10.1016\/j.compbiomed.2022.106462","DOI":"10.1016\/j.compbiomed.2022.106462"},{"key":"3756_CR27","doi-asserted-by":"publisher","unstructured":"Wang, Z., Zheng, J.-Q., Zhang, Y., Cui, G., Li, L.: Mamba-unet: Unet-like Pure Visual Mamba for Medical Image Segmentation. https:\/\/doi.org\/10.48550\/arXiv.2402.05079","DOI":"10.48550\/arXiv.2402.05079"},{"key":"3756_CR28","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.48550\/arXiv.2008.07669","volume":"33","author":"A Gu","year":"2020","unstructured":"Gu, A., Dao, T., Ermon, S., Rudra, A., R\u00e9, C.: Hippo: Recurrent memory with optimal polynomial projections. Adv. Neural. Inf. Process. Syst. 33, 1474\u20131487 (2020). https:\/\/doi.org\/10.48550\/arXiv.2008.07669","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"3756_CR29","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"3756_CR30","doi-asserted-by":"publisher","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., et al.: Attention U-net: Learning Where to Look for the Pancreas. https:\/\/doi.org\/10.48550\/arXiv.1804.03999","DOI":"10.48550\/arXiv.1804.03999"},{"key":"3756_CR31","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3756_CR32","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.-S.: Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.667","DOI":"10.1109\/CVPR.2017.667"},{"key":"3756_CR33","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3756_CR34","doi-asserted-by":"publisher","unstructured":"Shan, T., Yan, J.: Sca-net: A spatial and channel attention network for medical image segmentation. IEEE Access 9, 160926\u2013160937 (2021) https:\/\/doi.org\/10.1109\/ACCESS.2021.3132293","DOI":"10.1109\/ACCESS.2021.3132293"},{"key":"3756_CR35","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01350","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"3756_CR36","doi-asserted-by":"publisher","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks 107, 3\u201311 (2018) https:\/\/doi.org\/10.1016\/j.neunet.2017.12.012","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"3756_CR37","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"3756_CR38","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015). pmlr. https:\/\/proceedings.mlr.press\/v37\/ioffe15.html"},{"key":"3756_CR39","doi-asserted-by":"publisher","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer Normalization. https:\/\/doi.org\/10.48550\/arXiv.1607.06450","DOI":"10.48550\/arXiv.1607.06450"},{"key":"3756_CR40","doi-asserted-by":"publisher","unstructured":"Wang, H., Xie, S., Lin, L., Iwamoto, Y., Han, X.-H., Chen, Y.-W., Tong, R.: Mixed transformer u-net for medical image segmentation. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2390\u20132394 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746172 . IEEE","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"3756_CR41","doi-asserted-by":"publisher","unstructured":"Azad, R., Heidari, M., Shariatnia, M., Aghdam, E.K., Karimijafarbigloo, S., Adeli, E., Merhof, D.: Transdeeplab: Convolution-free transformer-based deeplab v3+ for medical image segmentation. In: International Workshop on PRedictive Intelligence In MEdicine, pp. 91\u2013102 (2022). https:\/\/doi.org\/10.1007\/978-3-031-16919-9_9 . Springer","DOI":"10.1007\/978-3-031-16919-9_9"},{"issue":"5","key":"3756_CR42","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1109\/TMI.2022.3230943","volume":"42","author":"X Huang","year":"2023","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X., Fu, Y.: Missformer: An effective transformer for 2d medical image segmentation. IEEE Trans. Med. Imaging 42(5), 1484\u20131494 (2023). https:\/\/doi.org\/10.1109\/TMI.2022.3230943","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3756_CR43","doi-asserted-by":"publisher","unstructured":"Feng, Y., Su, J., Zheng, J., Zheng, Y., Zhang, X.: A parallelly contextual convolutional transformer for medical image segmentation. Biomedical Signal Processing and Control 98, 106674 (2024) https:\/\/doi.org\/10.1016\/j.bspc.2024.106674","DOI":"10.1016\/j.bspc.2024.106674"},{"key":"3756_CR44","doi-asserted-by":"publisher","unstructured":"Ruan, J., Xiang, S., Xie, M., Liu, T., Fu, Y.: Malunet: A multi-attention and light-weight unet for skin lesion segmentation. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1150\u20131156 (2022). https:\/\/doi.org\/10.1109\/BIBM55620.2022.9995040 . IEEE","DOI":"10.1109\/BIBM55620.2022.9995040"},{"key":"3756_CR45","doi-asserted-by":"publisher","unstructured":"Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P.-A., Cetin, I., Lekadir, K., Camara, O., Gonzalez\u00a0Ballester, M.A., Sanroma, G., Napel, S., Petersen, S., Tziritas, G., Grinias, E., Khened, M., Kollerathu, V.A., Krishnamurthi, G., Roh\u00c3\u00a9, M.-M., Pennec, X., Sermesant, M., Isensee, F., J\u00c3\u00a4ger, P., Maier-Hein, K.H., Full, P.M., Wolf, I., Engelhardt, S., Baumgartner, C.F., Koch, L.M., Wolterink, J.M., I\u00c5\u00a1gum, I., Jang, Y., Hong, Y., Patravali, J., Jain, S., Humbert, O., Jodoin, P.-M.: Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Transactions on Medical Imaging 37(11), 2514\u20132525 (2018) https:\/\/doi.org\/10.1109\/TMI.2018.2837502","DOI":"10.1109\/TMI.2018.2837502"},{"key":"3756_CR46","doi-asserted-by":"publisher","unstructured":"Gao, Y., Zhou, M., Liu, D., Yan, Z., Zhang, S., Metaxas, D.N.: A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark. https:\/\/doi.org\/10.48550\/arXiv.2203.00131","DOI":"10.48550\/arXiv.2203.00131"},{"issue":"10","key":"3756_CR47","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.1109\/TMI.2020.2983721","volume":"39","author":"S Feng","year":"2020","unstructured":"Feng, S., Zhao, H., Shi, F., Cheng, X., Wang, M., Ma, Y., Xiang, D., Zhu, W., Chen, X.: Cpfnet: Context pyramid fusion network for medical image segmentation. IEEE Trans. Med. Imaging 39(10), 3008\u20133018 (2020). https:\/\/doi.org\/10.1109\/TMI.2020.2983721","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3756_CR48","doi-asserted-by":"publisher","unstructured":"Wu, H., Chen, S., Chen, G., Wang, W., Lei, B., Wen, Z.: Fat-net: Feature adaptive transformers for automated skin lesion segmentation. Medical Image Analysis 76, 102327 (2022) https:\/\/doi.org\/10.1016\/j.media.2021.102327","DOI":"10.1016\/j.media.2021.102327"},{"key":"3756_CR49","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Liu, H., Hu, Q.: Transfuse: Fusing transformers and cnns for medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021, pp. 14\u201324 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_2 . Springer","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"3756_CR50","doi-asserted-by":"publisher","unstructured":"Wei, J., Hu, Y., Zhang, R., Li, Z., Zhou, S.K., Cui, S.: Shallow attention network for polyp segmentation. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021, pp. 699\u2013708 (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_66 . Springer","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"3756_CR51","doi-asserted-by":"publisher","unstructured":"Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"3756_CR52","doi-asserted-by":"publisher","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: Stochastic Gradient Descent with Warm Restarts. https:\/\/doi.org\/10.48550\/arXiv.1608.03983","DOI":"10.48550\/arXiv.1608.03983"},{"key":"3756_CR53","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 (ICCV), pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03756-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03756-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03756-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T08:49:31Z","timestamp":1747385371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03756-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,21]]},"references-count":53,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["3756"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03756-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,21]]},"assertion":[{"value":"7 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2024","order":2,"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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}