{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T15:48:47Z","timestamp":1777218527765,"version":"3.51.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:00:00Z","timestamp":1643241600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:00:00Z","timestamp":1643241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62041108"],"award-info":[{"award-number":["62041108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004772","name":"Natural Science Foundation of NingXia","doi-asserted-by":"crossref","award":["2020AAC03029"],"award-info":[{"award-number":["2020AAC03029"]}],"id":[{"id":"10.13039\/501100004772","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11760-021-02115-w","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:03:36Z","timestamp":1643241816000},"page":"1607-1614","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Multiscale transunet\u2009+\u2009\u2009+\u2009: dense hybrid U-Net with transformer for medical image segmentation"],"prefix":"10.1007","volume":"16","author":[{"given":"Bo","family":"Wang","sequence":"first","affiliation":[]},{"given":"\u00b7Fan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Pengwei","family":"Dong","sequence":"additional","affiliation":[]},{"given":"\u00b7Chongyi","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,27]]},"reference":[{"issue":"2","key":"2115_CR1","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TMI.2020.3035253","volume":"40","author":"R Gu","year":"2021","unstructured":"Gu, R., Wang, G., Song, T., et al.: CA-Net: comprehensive attention convolutional neural networks for explainable medical image segmentation. IEEE Trans. Med. Imaging 40(2), 699\u2013711 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"11","key":"2115_CR2","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/TMI.2017.2720119","volume":"36","author":"MM Farhangi","year":"2017","unstructured":"Farhangi, M.M., Frigui, H., Seow, A., et al.: 3-D active contour segmentation based on sparse linear combination of training shapes (SCoTS). IEEE Trans. Med. Imaging 36(11), 2239\u20132249 (2017)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"10","key":"2115_CR3","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1109\/TMI.2018.2824243","volume":"37","author":"Z Tang","year":"2018","unstructured":"Tang, Z., Ahmad, S., Yap, P.T., et al.: Multi-atlas segmentation of MR tumor brain images using low-rank based image recovery. IEEE Trans. Med. Imaging 37(10), 2224\u20132235 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2115_CR4","first-page":"1","volume":"59","author":"AG Roy","year":"2020","unstructured":"Roy, A.G., Siddiqui, S., Plsterl, S., et al.: \u2018Squeeze & excite\u2019 guided few shot segmentation of volumetric images. Med. Image Anal. 59, 1\u201312 (2020)","journal-title":"Med. Image Anal."},{"issue":"2","key":"2115_CR5","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TMI.2020.3034995","volume":"40","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Xie, Y., Wang, Y., et al.: Inter-slice context residual learning for 3D medical image segmentation. IEEE Trans. Med. Imaging 40(2), 661\u2013672 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2115_CR6","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G., Kooi, T., Bejnordi, B.E., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017)","journal-title":"Med. Image Anal."},{"key":"2115_CR7","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III, pp. 234\u2013241. Springer International Publishing, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"2115_CR8","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"2115_CR9","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S. S., et al.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention (2016)","DOI":"10.1007\/978-3-319-46723-8_49"},{"issue":"6","key":"2115_CR10","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Siddiquee, R., Tajbakhsh, N., et al.: UNet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans. Med. Imaging 39(6), 1856\u20131867 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2115_CR11","doi-asserted-by":"crossref","unstructured":"Huang, H., Lin, L., Tong, R., et al.: Unet 3+: A full-scale connected unet for medical image segmentation. In: IEEE international conference on acoustics, speech and signal processing (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"issue":"12","key":"2115_CR12","doi-asserted-by":"publisher","first-page":"2663","DOI":"10.1109\/TMI.2018.2845918","volume":"37","author":"X Li","year":"2018","unstructured":"Li, X., Hao, C., Qi, X., et al.: H-denseunet: hybrid densely connected unet for liver and tumor segmentation from ct volumes. IEEE Trans. Med. Imaging 37(12), 2663\u20132674 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"2115_CR13","unstructured":"Jose, J. M., Sindagi, V., Hacihaliloglu, I., et al: Kiu-net: Towards accurate segmentation of biomedical images using over-complete representations. In: International conference on medical image computing and computer-assisted intervention. (2020)"},{"issue":"4","key":"2115_CR14","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1002\/mp.13416","volume":"46","author":"W Bo","year":"2019","unstructured":"Bo, W., Lei, Y., Tian, S., et al.: Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation. Med. Phys. 46(4), 1707\u20131718 (2019)","journal-title":"Med. Phys."},{"issue":"12","key":"2115_CR15","doi-asserted-by":"publisher","first-page":"6270","DOI":"10.1002\/mp.14512","volume":"47","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Zhang, J., Li, Z., et al.: A multiple-channel and atrous convolution network for ultrasound image segmentation. Med. Phys. 47(12), 6270\u20136285 (2020)","journal-title":"Med. Phys."},{"key":"2115_CR16","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","volume":"53","author":"J Schlemper","year":"2019","unstructured":"Schlemper, J., Oktay, O., Schaap, M., et al.: Attention gated networks: learning to leverage salient regions in medical images. Med. Image Anal. 53, 197\u2013207 (2019)","journal-title":"Med. Image Anal."},{"key":"2115_CR17","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020"},{"key":"2115_CR18","unstructured":"Touvron, H., Cord, M., Douze, M., et al.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357 (2021)"},{"key":"2115_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 , 2021","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2115_CR20","unstructured":"Chen, J., Lu, Y., Yu, Q., et al.: TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, 2021"},{"key":"2115_CR21","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Yang, D., Roth, H., et al.: Unetr: transformers for 3d medical image segmentation. arXiv preprint arXiv:2103.10504, 2021","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"2115_CR22","doi-asserted-by":"crossref","unstructured":"Valanarasu, J., Oza, P., Hacihaliloglu, I., et al.: Medical transformer: gated axial-attention for medical image segmentation. arXiv preprint arXiv:2102.10662 , 2021","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"2115_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q., et al.: Transfuse: fusing transformers and cnns for medical image segmentation. arXiv preprint arXiv:2102.08005 , 2021","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"2115_CR24","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, C., Ding, M., et al.: Transbts: multimodal brain tumor segmentation using transformer. arXiv preprint arXiv:2103.04430, 2021","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"2115_CR25","doi-asserted-by":"crossref","unstructured":"Xie, Y., Zhang, J., Shen, C., et al.: CoTr: efficiently bridging CNN and transformer for 3d medical image segmentation. arXiv preprint arXiv:2103.03024, 2021","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"2115_CR26","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"CH Sudre","year":"2017","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Sebastien Ourselin, M., Cardoso, J.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Jorge Cardoso, M., Arbel, Tal, Carneiro, G., Syeda-Mahmood, T., Jo\u00e3o Manuel, R.S., Tavares, M.M., Bradley, A., Greenspan, H., Papa, J.P., Madabhushi, A., Nascimento, J.C., Cardoso, J.S., Belagiannis, V., Zhi, L. (eds.) Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 240\u2013248. Springer International Publishing, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28"},{"key":"2115_CR27","unstructured":"Devlin, J., Chang, M. W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2115_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems. (2017)"},{"key":"2115_CR29","doi-asserted-by":"crossref","unstructured":"Gao, Y., Zhou, M., Metaxas, D., et al.: Utnet: a hybrid transformer architecture for medical image segmentation. arXiv preprint arXiv:2107.00781 , 2021","DOI":"10.1007\/978-3-030-87199-4_6"},{"key":"2115_CR30","unstructured":"Zhang, Q., Yang, Y.: ResT: an efficient transformer for visual recognition. arXiv preprint arXiv:2105.13677, 2021"},{"issue":"2","key":"2115_CR31","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318\u2013327 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2115_CR32","unstructured":"Wang, Z., Simoncelli, E. P., Bovik, A. C., et al.: Multiscale structural similarity for image quality assessment. In: Asilomar Conference on Signals, System & Computers. (2003)"},{"key":"2115_CR33","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., et al.: UnitBox: an advanced object detection network. In: Proceedings of the 2016 ACM Multimedia Conference. (2016)","DOI":"10.1145\/2964284.2967274"},{"issue":"2","key":"2115_CR34","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/j.media.2013.12.002","volume":"18","author":"G Litjens","year":"2014","unstructured":"Litjens, G., Toth, R., van de Ven, W., et al.: Evaluation of prostate segmentation algorithms for mri: the promise12 challenge. Med. Image Anal. 18(2), 359\u2013373 (2014)","journal-title":"Med. Image Anal."},{"key":"2115_CR35","unstructured":"Bilic, P., Christ, P. F., Vorontsov, E., et al.: The liver tumor segmentation benchmark (lits). arXiv preprint arXiv:1901.04056 (2019)"},{"key":"2115_CR36","doi-asserted-by":"publisher","first-page":"105821","DOI":"10.1016\/j.cmpb.2020.105821","volume":"200","author":"A Meyer","year":"2020","unstructured":"Meyer, A., Chlebus, G., Rak, G., et al.: Anisotropic 3d multi-stream cnn for accurate prostate segmentation from multi-planar mri. Comput. Methods Programs Biomed. 200, 105821 (2020)","journal-title":"Comput. Methods Programs Biomed."},{"key":"2115_CR37","doi-asserted-by":"crossref","unstructured":"Li, C., Tan, Y., Chen, W., et al.: Attention unet++: a nested attention-aware U-Net for liver CT image segmentation. In: IEEE International conference on image processing (2020)","DOI":"10.1109\/ICIP40778.2020.9190761"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02115-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-02115-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02115-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T11:10:23Z","timestamp":1659093023000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-02115-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,27]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["2115"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-02115-w","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,27]]},"assertion":[{"value":"25 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest exists in the submission of this manuscript, and the manuscript is approved by all authors for publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"The code can be shared in the near future for the sake of development.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"The raw data can be shared if the researchers need to do research on relevant topic and cite it in their papers.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}}]}}