{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T11:55:35Z","timestamp":1784289335547,"version":"3.55.0"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00371-024-03589-8","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T12:02:35Z","timestamp":1723464155000},"page":"3095-3107","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Directional latent space representation for medical image segmentation"],"prefix":"10.1007","volume":"41","author":[{"given":"Xintao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqing","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Wangr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"3589_CR1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/TMI.2023.3289859","volume":"43","author":"J Li","year":"2024","unstructured":"Li, J., et al.: Dsmt-net: dual self-supervised multi-operator transformation for multi-source endoscopic ultrasound diagnosis. IEEE Trans. Med. Imaging 43, 64\u201375 (2024). https:\/\/doi.org\/10.1109\/TMI.2023.3289859","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3589_CR2","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1038\/s41591-023-02702-z","volume":"30","author":"L Dai","year":"2024","unstructured":"Dai, L., et al.: A deep learning system for predicting time to progression of diabetic retinopathy. Nat. Med. 30, 584\u2013594 (2024). https:\/\/doi.org\/10.1038\/s41591-023-02702-z","journal-title":"Nat. Med."},{"key":"3589_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/J.PATTER.2024.100929","volume":"5","author":"B Qian","year":"2024","unstructured":"Qian, B., et al.: DRAC 2022: a public benchmark for diabetic retinopathy analysis on ultra-wide optical coherence tomography angiography images. Patterns 5, 100929 (2024). https:\/\/doi.org\/10.1016\/J.PATTER.2024.100929","journal-title":"Patterns"},{"key":"3589_CR4","doi-asserted-by":"publisher","first-page":"3242","DOI":"10.1038\/s41467-021-23458-5","volume":"12","author":"L Dai","year":"2021","unstructured":"Dai, L., et al.: A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat. Commun. 12, 3242 (2021). https:\/\/doi.org\/10.1038\/s41467-021-23458-5","journal-title":"Nat. Commun."},{"key":"3589_CR5","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1016\/j.scib.2024.01.004","volume":"69","author":"B Sheng","year":"2024","unstructured":"Sheng, B., et al.: Large language models for diabetes care: potentials and prospects. Sci. Bull. 69, 583\u2013588 (2024). https:\/\/doi.org\/10.1016\/j.scib.2024.01.004","journal-title":"Sci. Bull."},{"key":"3589_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpbup.2024.100141","volume":"5","author":"M Khalifa","year":"2024","unstructured":"Khalifa, M., Albadawy, M.: Artificial intelligence for diabetes: enhancing prevention, diagnosis, and effective management. Comput. Methods Programs Biomed. Update 5, 100141 (2024). https:\/\/doi.org\/10.1016\/j.cmpbup.2024.100141","journal-title":"Comput. Methods Programs Biomed. Update"},{"key":"3589_CR7","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2024","unstructured":"Karambakhsh, A., et al.: Sparsevoxnet: 3-d object recognition with sparsely aggregation of 3-d dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35, 532\u2013546 (2024). https:\/\/doi.org\/10.1109\/TNNLS.2022.3175775","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3589_CR8","doi-asserted-by":"publisher","first-page":"3675","DOI":"10.1007\/S00371-023-02984-X","volume":"39","author":"AH Al-Jebrni","year":"2023","unstructured":"Al-Jebrni, A.H., et al.: Sthy-net: a feature fusion-enhanced dense-branched modules network for small thyroid nodule classification from ultrasound images. Vis. Comput. 39, 3675\u20133689 (2023). https:\/\/doi.org\/10.1007\/S00371-023-02984-X","journal-title":"Vis. Comput."},{"key":"3589_CR9","doi-asserted-by":"publisher","first-page":"3647","DOI":"10.1007\/S00371-023-02938-3","volume":"39","author":"S Huang","year":"2023","unstructured":"Huang, S., et al.: Transmrsr: transformer-based self-distilled generative prior for brain MRI super-resolution. Vis. Comput. 39, 3647\u20133659 (2023). https:\/\/doi.org\/10.1007\/S00371-023-02938-3","journal-title":"Vis. Comput."},{"key":"3589_CR10","doi-asserted-by":"publisher","first-page":"2557","DOI":"10.1109\/TBME.2022.3150420","volume":"69","author":"R Liu","year":"2022","unstructured":"Liu, R., et al.: Mixed-weight neural bagging for detecting $$m^{6a}$$ modifications in sars-cov-2 RNA sequencing. IEEE Trans. Biomed. Eng. 69, 2557\u20132568 (2022). https:\/\/doi.org\/10.1109\/TBME.2022.3150420","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"3589_CR11","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"A Kamel","year":"2021","unstructured":"Kamel, A., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-d joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51, 2774\u20132788 (2021). https:\/\/doi.org\/10.1109\/TSMC.2019.2916896","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"3589_CR12","doi-asserted-by":"publisher","first-page":"2540","DOI":"10.1109\/TBME.2021.3050310","volume":"68","author":"A Nazir","year":"2021","unstructured":"Nazir, A., et al.: Living donor-recipient pair matching for liver transplant via ternary tree representation with cascade incremental learning. IEEE Trans. Biomed. Eng. 68, 2540\u20132551 (2021). https:\/\/doi.org\/10.1109\/TBME.2021.3050310","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"3589_CR13","doi-asserted-by":"publisher","first-page":"7991","DOI":"10.1109\/TII.2021.3064369","volume":"17","author":"MN Cheema","year":"2021","unstructured":"Cheema, M.N., et al.: Modified GAN-CAED to minimize risk of unintentional liver major vessels cutting by controlled segmentation using CTA\/SPET-CT. IEEE Trans. Ind. Inf. 17, 7991\u20138002 (2021). https:\/\/doi.org\/10.1109\/TII.2021.3064369","journal-title":"IEEE Trans. Ind. Inf."},{"key":"3589_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Promptad: learning prompts with only normal samples for few-shot anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16838\u201316848 (2024)","DOI":"10.1109\/CVPR52733.2024.01594"},{"key":"3589_CR15","doi-asserted-by":"publisher","unstructured":"Zhang, H., et\u00a0al.: Learning task-aware language-image representation for class-incremental object detection. In: Wooldridge, M.J., Dy, J.G. & Natarajan, S. (eds.) Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20\u201327, 2024, Vancouver, Canada, pp. 7096\u20137104. AAAI Press (2024). https:\/\/doi.org\/10.1609\/AAAI.V38I7.28537","DOI":"10.1609\/AAAI.V38I7.28537"},{"key":"3589_CR16","doi-asserted-by":"publisher","unstructured":"Chen, Y., et\u00a0al.: Boosting semi-supervised learning by exploiting all unlabeled data. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023, pp. 7548\u20137557. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00729","DOI":"10.1109\/CVPR52729.2023.00729"},{"key":"3589_CR17","doi-asserted-by":"publisher","first-page":"15328","DOI":"10.1109\/TPAMI.2023.3319470","volume":"45","author":"X Tan","year":"2023","unstructured":"Tan, X., et al.: Positive-negative receptive field reasoning for omni-supervised 3d segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 15328\u201315344 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3319470","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3589_CR18","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1109\/TIP.2023.3267044","volume":"32","author":"Z Xie","year":"2023","unstructured":"Xie, Z., et al.: Boosting night-time scene parsing with learnable frequency. IEEE Trans. Image Process. 32, 2386\u20132398 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3267044","journal-title":"IEEE Trans. Image Process."},{"key":"3589_CR19","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1109\/TIP.2024.3372468","volume":"33","author":"Z Xie","year":"2024","unstructured":"Xie, Z., Wang, S., Yu, Q., Tan, X., Xie, Y.: Csfwinformer: cross-space-frequency window transformer for mirror detection. IEEE Trans. Image Process. 33, 1853\u20131867 (2024). https:\/\/doi.org\/10.1109\/TIP.2024.3372468","journal-title":"IEEE Trans. Image Process."},{"key":"3589_CR20","doi-asserted-by":"publisher","first-page":"9085","DOI":"10.1109\/TIP.2021.3122004","volume":"30","author":"X Tan","year":"2021","unstructured":"Tan, X., et al.: Night-time scene parsing with a large real dataset. IEEE Trans. Image Process. 30, 9085\u20139098 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3122004","journal-title":"IEEE Trans. Image Process."},{"key":"3589_CR21","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/TIP.2024.3372449","volume":"33","author":"T Sun","year":"2024","unstructured":"Sun, T., Zhang, Z., Tan, X., Qu, Y., Xie, Y.: Image understands point cloud: Weakly supervised 3d semantic segmentation via association learning. IEEE Trans. Image Process. 33, 1838\u20131852 (2024). https:\/\/doi.org\/10.1109\/TIP.2024.3372449","journal-title":"IEEE Trans. Image Process."},{"key":"3589_CR22","doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3589_CR23","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1109\/LGRS.2018.2795531","volume":"15","author":"W Sun","year":"2018","unstructured":"Sun, W., Wang, R.: Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM. IEEE Geosci. Remote Sens. Lett. 15, 474\u2013478 (2018). https:\/\/doi.org\/10.1109\/LGRS.2018.2795531","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"3589_CR24","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/JSTARS.2018.2810320","volume":"11","author":"G Chen","year":"2018","unstructured":"Chen, G., et al.: Symmetrical dense-shortcut deep fully convolutional networks for semantic segmentation of very-high-resolution remote sensing images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11, 1633\u20131644 (2018)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"3589_CR25","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.cmpb.2007.08.006","volume":"88","author":"P Bazin","year":"2007","unstructured":"Bazin, P., Pham, D.L.: Topology correction of segmented medical images using a fast marching algorithm. Comput. Methods Programs Biomed. 88, 182\u2013190 (2007). https:\/\/doi.org\/10.1016\/j.cmpb.2007.08.006","journal-title":"Comput. Methods Programs Biomed."},{"key":"3589_CR26","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., III, W. M.W. & Frangi, A.F. (eds.) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015\u201418th International Conference Munich, Germany, October 5\u20139, 2015, Proceedings, Part III, vol. 9351 of Lecture Notes in Computer Science, pp. 234\u2013241. Springer (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3589_CR27","unstructured":"Oktay, O., et\u00a0al.: Attention u-net: learning where to look for the pancreas. CoRR arXiv:1804.03999 (2018)"},{"key":"3589_CR28","doi-asserted-by":"publisher","unstructured":"Fu, J., et\u00a0al.: Dual attention network for scene segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16\u201320, 2019, pp. 3146\u20133154, Computer Vision Foundation\/IEEE (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00326","DOI":"10.1109\/CVPR.2019.00326"},{"key":"3589_CR29","doi-asserted-by":"publisher","unstructured":"Yang, Z., Farsiu, S.: Directional connectivity-based segmentation of medical images. CoRR arXiv:2304.00145 (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.00145","DOI":"10.48550\/arXiv.2304.00145"},{"key":"3589_CR30","doi-asserted-by":"publisher","unstructured":"Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in gans. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19\u201325, 2021, pp. 1532\u20131540. Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00158","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"3589_CR31","unstructured":"Jahanian, A., Chai, L., Isola, P.: On the \u201csteerability\u201d of generative adversarial networks. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020. OpenReview.net (2020)"},{"key":"3589_CR32","doi-asserted-by":"publisher","unstructured":"Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: Ganalyze: toward visual definitions of cognitive image properties. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 5743\u20135752. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00584","DOI":"10.1109\/ICCV.2019.00584"},{"key":"3589_CR33","unstructured":"Wang, Y., Yang, D., Br\u00e9mond, F., Dantcheva, A.: Latent image animator: learning to animate images via latent space navigation. In: The tenth international conference on learning representations, ICLR 2022, virtual event, April 25\u201329, 2022. OpenReview.net (2022)"},{"key":"3589_CR34","unstructured":"Salzmann, M., Ek, C.H., Urtasun, R., Darrell, T.: Factorized orthogonal latent spaces. In: Teh, Y.W., & Titterington, D.M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 13\u201315, 2010, vol.\u00a09 of JMLR Proceedings, 701\u2013708. JMLR.org (2010)"},{"key":"3589_CR35","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C. & Weiss, Y. (eds.) Computer Vision - ECCV 2018\u201415th European Conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part VII, vol. 11211 of Lecture Notes in Computer Science, pp. 833\u2013851. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"3589_CR36","doi-asserted-by":"publisher","first-page":"2547","DOI":"10.1109\/TNNLS.2020.3006524","volume":"32","author":"J Fu","year":"2021","unstructured":"Fu, J., et al.: Scene segmentation with dual relation-aware attention network. IEEE Trans. Neural Netw. Learn. Syst. 32, 2547\u20132560 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2020.3006524","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3589_CR37","doi-asserted-by":"publisher","unstructured":"Zhou, T., Wang, W., Konukoglu, E., Gool, L.V.: Rethinking semantic segmentation: a prototype view. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022, pp. 2572\u20132583. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00261","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"3589_CR38","doi-asserted-by":"publisher","first-page":"6013","DOI":"10.1109\/TIP.2021.3090522","volume":"30","author":"N Gao","year":"2021","unstructured":"Gao, N., Shan, Y., Zhao, X., Huang, K.: Learning category- and instance-aware pixel embedding for fast panoptic segmentation. IEEE Trans. Image Process. 30, 6013\u20136023 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3090522","journal-title":"IEEE Trans. Image Process."},{"key":"3589_CR39","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2018","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3589_CR40","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18\u201322, 2018, pp. 7132\u20137141. Computer Vision Foundation\/IEEE Computer Society (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3589_CR41","doi-asserted-by":"publisher","unstructured":"Li, L., Zhou, T., Wang, W., Li, J., Yang, Y.: Deep hierarchical semantic segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022, pp. 1236\u20131247. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00131","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"3589_CR42","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Guyon, I. et\u00a0al. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017)"},{"key":"3589_CR43","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16 x 16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. OpenReview.net (2021)"},{"key":"3589_CR44","unstructured":"Xie, E., et\u00a0al.: Segformer: simple and efficient design for semantic segmentation with transformers. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6\u201314, 2021, virtual, pp. 12077\u201312090 (2021)"},{"key":"3589_CR45","doi-asserted-by":"publisher","unstructured":"Liu, Z. et\u00a0al.: Swin transformer V2: scaling up capacity and resolution. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022, pp. 11999\u201312009. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01170","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"3589_CR46","doi-asserted-by":"publisher","unstructured":"Liu, Z., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10\u201317, 2021, pp. 9992\u201310002, IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3589_CR47","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)"},{"key":"3589_CR48","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et\u00a0al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7\u201312, 2015, pp 1\u20139. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3589_CR49","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27\u201330, 2016, pp. 770\u2013778, IEEE Computer Society (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3589_CR50","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R.\u00a0B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017, pp. 5987\u20135995. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"3589_CR51","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR arXiv:1608.06993 (2016)","DOI":"10.1109\/CVPR.2017.243"},{"key":"3589_CR52","doi-asserted-by":"publisher","unstructured":"Liu, Z., et\u00a0al.: A convnet for the 2020s. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18\u201324, 2022, pp. 11966\u201311976. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"3589_CR53","doi-asserted-by":"publisher","unstructured":"Barbato, F., Toldo, M., Michieli, U., Zanuttigh, P.: Latent space regularization for unsupervised domain adaptation in semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021, virtual, June 19\u201325, 2021, pp. 2835\u20132845, Computer Vision Foundation\/IEEE (2021). https:\/\/doi.org\/10.1109\/CVPRW53098.2021.00318","DOI":"10.1109\/CVPRW53098.2021.00318"},{"key":"3589_CR54","doi-asserted-by":"publisher","unstructured":"Chen, C. et\u00a0al.: Cooperative training and latent space data augmentation for robust medical image segmentation. In: de\u00a0Bruijne, M. et\u00a0al. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2021\u201424th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part III, vol. 12903 of Lecture Notes in Computer Science, pp. 149\u2013159. Springer (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_14","DOI":"10.1007\/978-3-030-87199-4_14"},{"key":"3589_CR55","doi-asserted-by":"publisher","unstructured":"Luo, Z., et\u00a0al.: Non-local deep features for salient object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21\u201326, 2017, pp. 6593\u20136601. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.698","DOI":"10.1109\/CVPR.2017.698"},{"key":"3589_CR56","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Zhong, Y., Wang, J., Ma, A.: Foreground-aware relation network for geospatial object segmentation in high spatial resolution remote sensing imagery. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020, pp. 4095\u20134104. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00415","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"3589_CR57","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6\u201314, 2021, virtual, pp. 17864\u201317875 (2021)"},{"key":"3589_CR58","doi-asserted-by":"publisher","unstructured":"Deng, J., et\u00a0al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA, pp. 248\u2013255. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3589_CR59","unstructured":"Chen, J., et\u00a0al.: Transunet: transformers make strong encoders for medical image segmentation. CoRR arXiv:2102.04306 (2021)"},{"key":"3589_CR60","doi-asserted-by":"publisher","unstructured":"Cao, H., et\u00a0al.: Swin-unet: unet-like pure transformer for medical image segmentation. In Karlinsky, L., Michaeli, T. & Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops - Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part III, vol. 13803 of Lecture Notes in Computer Science, pp. 205\u2013218. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3589_CR61","unstructured":"Chang, Y., Hu, M., Zhai, G., Zhang, X.: Transclaw u-net: claw u-net with transformers for medical image segmentation. CoRR arXiv:2107.05188 (2021)"},{"key":"3589_CR62","doi-asserted-by":"crossref","unstructured":"Xu, G., Wu, X., Zhang, X., He, X.: Levit-unet: make faster encoders with transformer for medical image segmentation. CoRR arXiv:2107.08623 (2021)","DOI":"10.2139\/ssrn.4116174"},{"key":"3589_CR63","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, 1484\u20131494 (2023). https:\/\/doi.org\/10.1109\/TMI.2022.3230943","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3589_CR64","doi-asserted-by":"publisher","unstructured":"Rahman, M.M., Marculescu, R.: Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation. CoRR arXiv:2303.16892 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.16892","DOI":"10.48550\/arXiv.2303.16892"},{"key":"3589_CR65","unstructured":"Zhou, H., et\u00a0al.: nnformer: interleaved transformer for volumetric segmentation. CoRR arXiv:2109.03201 (2021)"},{"key":"3589_CR66","doi-asserted-by":"publisher","unstructured":"Wang, H., et\u00a0al.: Mixed transformer u-net for medical image segmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23\u201327 May 2022, pp. 2390\u20132394. IEEE (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746172","DOI":"10.1109\/ICASSP43922.2022.9746172"},{"key":"3589_CR67","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203\u2013211 (2021)","journal-title":"Nat. Methods"},{"key":"3589_CR68","doi-asserted-by":"publisher","unstructured":"Rahman, M.M., Marculescu, R.: Medical image segmentation via cascaded attention decoding. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2\u20137, 2023, pp. 6211\u20136220. IEEE (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00616","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"3589_CR69","doi-asserted-by":"publisher","unstructured":"Tragakis, A., Kaul, C., Murray-Smith, R., Husmeier, D.: The fully convolutional transformer for medical image segmentation. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2\u20137, 2023, pp. 3649\u20133658. IEEE (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00365","DOI":"10.1109\/WACV56688.2023.00365"},{"key":"3589_CR70","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: Unet++: a nested u-net architecture for medical image segmentation. In: Stoyanov, D., et\u00a0al. (eds.) 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, vol. 11045 of Lecture Notes in Computer Science, pp. 3\u201311. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"3589_CR71","doi-asserted-by":"crossref","unstructured":"Xiao, X., Lian, S., Luo, Z., Li, S.: Weighted res-unet for high-quality retina vessel segmentation. In: 2018 9th International Conference on Information Technology in Medicine and Education (ITME), pp. 327\u2013331. IEEE (2018)","DOI":"10.1109\/ITME.2018.00080"},{"key":"3589_CR72","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., et al.: Attention gated networks: learning to leverage salient regions in medical images. Medical Image Anal. 53, 197\u2013207 (2019). https:\/\/doi.org\/10.1016\/j.media.2019.01.012","journal-title":"Medical Image Anal."},{"key":"3589_CR73","unstructured":"Landman, B., et\u00a0al.: Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proceedings of the MICCAI Multi-Atlas Labeling Beyond Cranial Vault\u2013Workshop Challenge, vol.\u00a05, p. 12 (2015)"},{"key":"3589_CR74","doi-asserted-by":"publisher","unstructured":"Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? IEEE Trans. Med. Imaging 37, 2514\u20132525 (2018). https:\/\/doi.org\/10.1109\/TMI.2018.2837502","DOI":"10.1109\/TMI.2018.2837502"},{"key":"3589_CR75","doi-asserted-by":"publisher","unstructured":"Gong, H., et\u00a0al.: Multi-task learning for thyroid nodule segmentation with thyroid region prior. In: 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021, Nice, France, April 13\u201316, 2021, pp. 257\u2013261. IEEE (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434087","DOI":"10.1109\/ISBI48211.2021.9434087"},{"key":"3589_CR76","doi-asserted-by":"publisher","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part V, vol. 11209 of Lecture Notes in Computer Science, pp. 432\u2013448. Springer (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26","DOI":"10.1007\/978-3-030-01228-1_26"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03589-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03589-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03589-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T05:08:23Z","timestamp":1741583303000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03589-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":76,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3589"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03589-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4444261\/v1","asserted-by":"object"}]},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"21 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 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"}}]}}