{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:58:40Z","timestamp":1757617120897,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784950"},{"type":"electronic","value":"9789819784967"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8496-7_10","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T02:02:22Z","timestamp":1730512942000},"page":"133-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Decoder with\u00a0Parallel Transformer and\u00a0CNN for\u00a0Medical Image Segmentation"],"prefix":"10.1007","author":[{"given":"Shijie","family":"Li","sequence":"first","affiliation":[]},{"given":"Yu","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Qingyuan","family":"Xiang","sequence":"additional","affiliation":[]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"issue":"11","key":"10_CR1","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P.A., Cetin, I., Lekadir, K., Camara, O., Ballester, M.A.G., et al.: Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514\u20132525 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: CVPR. vol.\u00a02, pp. 60\u201365. IEEE (2005)","DOI":"10.1109\/CVPR.2005.38"},{"key":"10_CR3","doi-asserted-by":"crossref","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: ECCV, pp. 205\u2013218. Springer (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"10_CR5","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. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"10_CR6","doi-asserted-by":"crossref","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: CVPR, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"10_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Fang, X., Shi, Y., Guo, Q., Wang, L., Liu, Z.: Sub-band based attention for robust polyp segmentation. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 736\u2013744 (2023)","DOI":"10.24963\/ijcai.2023\/82"},{"key":"10_CR9","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Huang, H., Lin, L., Tong, R., Hu, H., Zhang, Q., Iwamoto, Y., Han, X., Chen, Y.W., Wu, J.: Unet 3+: A full-scale connected unet for medical image segmentation. In: ICASSP, pp. 1055\u20131059, IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"issue":"5","key":"10_CR11","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":"10_CR12","doi-asserted-by":"crossref","unstructured":"Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., Johansen, H.D.: Doubleu-net: A deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd International Symposium on Computer-based Medical Systems (CBMS), pp. 558\u2013564. IEEE (2020)","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Jha, D., Smedsrud, P.H., Riegler, M.A., Johansen, D., De\u00a0Lange, T., Halvorsen, P., Johansen, H.D.: Resunet++: An advanced architecture for medical image segmentation. In: 2019 IEEE International Symposium on Multimedia (ISM), pp. 225\u20132255. IEEE (2019)","DOI":"10.1109\/ISM46123.2019.00049"},{"key":"10_CR14","unstructured":"Landman, B., Xu, Z., Igelsias, J., Styner, M., Langerak, T., Klein, A.: Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proceedings MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge. vol.\u00a05, p.\u00a012 (2015)"},{"key":"10_CR15","doi-asserted-by":"crossref","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: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10_CR16","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., et\u00a0al.: Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: Medical image segmentation via cascaded attention decoding. In: WACV, pp. 6222\u20136231 (2023)","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"10_CR20","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.media.2016.08.008","volume":"35","author":"K Sirinukunwattana","year":"2017","unstructured":"Sirinukunwattana, K., Pluim, J.P., Chen, H., Qi, X., Heng, P.A., Guo, Y.B., Wang, L.Y., Matuszewski, B.J., Bruni, E., Sanchez, U., et al.: Gland segmentation in colon histology images: the glas challenge contest. Med. Image Anal. 35, 489\u2013502 (2017)","journal-title":"Med. Image Anal."},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Tomar, N.K., Jha, D., Bagci, U., Ali, S.: Tganet: Text-guided attention for improved polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 151\u2013160. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_15"},{"key":"10_CR22","doi-asserted-by":"publisher","first-page":"2620","DOI":"10.1109\/TIP.2023.3268004","volume":"32","author":"Y Tu","year":"2023","unstructured":"Tu, Y., Li, L., Su, L., Du, J., Lu, K., Huang, Q.: Viewpoint-adaptive representation disentanglement network for change captioning. IEEE Trans. Image Process. 32, 2620\u20132635 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3268004","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"10_CR23","doi-asserted-by":"publisher","first-page":"4926","DOI":"10.1109\/TPAMI.2024.3365104","volume":"46","author":"Y Tu","year":"2024","unstructured":"Tu, Y., Li, L., Su, L., Zha, Z.J., Huang, Q.: Smart: syntax-calibrated multi-aspect relation transformer for change captioning. IEEE Trans. Pattern Anal. Mach. Intell. 46(7), 4926\u20134943 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3365104","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Tu, Y., Li, L., Su, L., Zha, Z.J., Yan, C., Huang, Q.: Self-supervised cross-view representation reconstruction for change captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2805\u20132815 (2023)","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., Li, Y.: Maxvit: Multi-axis vision transformer. In: ECCV, pp. 459\u2013479. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Oza, P., Hacihaliloglu, I., Patel, V.M.: Medical transformer: Gated axial-attention for medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24, pp. 36\u201346. Springer (2021)","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Q., Tang, F., Meng, J., Su, J., Song, S.: Stepwise feature fusion: Local guides global. In: MICCAI, pp. 110\u2013120. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_11"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: CVPR, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: ECCV, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Xu, G., Zhang, X., He, X., Wu, X.: Levit-unet: Make faster encoders with transformer for medical image segmentation. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 42\u201353. Springer (2023)","DOI":"10.1007\/978-981-99-8543-2_4"},{"key":"10_CR32","first-page":"29582","volume":"35","author":"C You","year":"2022","unstructured":"You, C., Zhao, R., Liu, F., Dong, S., Chinchali, S., Topcu, U., Staib, L., Duncan, J.: Class-aware adversarial transformers for medical image segmentation. NeurIPS 35, 29582\u201329596 (2022)","journal-title":"NeurIPS"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q.: Transfuse: Fusing transformers and cnns for medical image segmentation. In: MICCAI, pp. 14\u201324. Springer (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"issue":"6","key":"10_CR34","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: 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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8496-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T23:43:28Z","timestamp":1757115808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8496-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819784950","9789819784967"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8496-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}