{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T04:37:28Z","timestamp":1769834248251,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819784981","type":"print"},{"value":"9789819784998","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"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\/978-981-97-8499-8_15","type":"book-chapter","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T14:03:02Z","timestamp":1729260182000},"page":"210-224","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Comprehensive Transformer Integration Network (CTIN): Advancing Endoscopic Disease Segmentation with Hybrid Transformer Architecture"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6007-9759","authenticated-orcid":false,"given":"Jiaming","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingdu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caiyan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7261-6398","authenticated-orcid":false,"given":"Teng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shegan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6483-8326","authenticated-orcid":false,"given":"Yan","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,19]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Chang, Q., Ahmad, D., Toth, J., Bascom, R., Higgins, W.E.: ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video. In: Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging, vol. 12468, p. 1246803. SPIE (2023)","DOI":"10.1117\/12.2647897"},{"key":"15_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105766","volume":"178","author":"Y Pang","year":"2020","unstructured":"Pang, Y., Shi, Y., Gao, S., Jiang, F., Veeranampalayam-Sivakumar, A.-N., Thompson, L., Luck, J., Liu, C.: Improved crop row detection with deep neural network for early-season maize stand count in UAV imagery. Comput. Electron. Agric. 178, 105766 (2020)","journal-title":"Comput. Electron. Agric."},{"key":"15_CR3","unstructured":"Thuan, N.H., Oanh, N.T., Thuy, N.T., Perry, S., Sang, D.V.: Rabit: an efficient transformer using bidirectional feature pyramid network with reverse attention for colon polyp segmentation (2023). arXiv:2307.06420"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Pang, Y., Liang, J., Huang, T., Chen, H., Li, Y., Li, D., Huang, L., Wang, Q.: Slim unetr: scale hybrid transformers to efficient 3d medical image segmentation under limited computational resources. IEEE Trans. Med. Imaging (2023)","DOI":"10.1109\/TMI.2023.3326188"},{"key":"15_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2019.108576","volume":"333","author":"Y Pang","year":"2020","unstructured":"Pang, Y., Christenson, J., Jiang, F., Lei, T., Rhoades, R., Kern, D., Thompson, J.A., Liu, C.: Automatic detection and quantification of hand movements toward development of an objective assessment of tremor and bradykinesia in Parkinson\u2019s disease. J. Neurosci. Methods 333, 108576 (2020)","journal-title":"J. Neurosci. Methods"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention-MICCAI: 18th International Conference, Munich, Germany, Proceedings, Part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"6","key":"15_CR7","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"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., Xu, D.: Unetr: transformers for 3d medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Q., Tang, F., Meng, J., Su, J., Song, S.: Stepwise feature fusion: local guides global. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 110\u2013120. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_11"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin unetr: Swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI Brainlesion Workshop, pp. 272\u2013284. Springer (2021)","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"15_CR11","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10\u00a0012\u201310\u00a0022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"1","key":"15_CR12","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., Shao, L.: Pranet: parallel reverse attention network for polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 263\u2013273. Springer (2020)","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Sanderson, E., Matuszewski, B.J.: FCN-transformer feature fusion for polyp segmentation. In: Annual Conference on Medical Image Understanding and Analysis, pp. 892\u2013907. Springer (2022)","DOI":"10.1007\/978-3-031-12053-4_65"},{"key":"15_CR15","unstructured":"Hung, P.V., Manh, N.D., Oanh, N.T., Thuy, N.T., Sang, D.V.: Ugcanet: a unified global context-aware transformer-based network with feature alignment for endoscopic image analysis (2023). arXiv:2307.06260"},{"key":"15_CR16","unstructured":"Ali, S., Ghatwary, N., Braden, B., Lamarque, D., Bailey, A., Realdon, S., Cannizzaro, R., Rittscher, J., Daul, C., East, J.: Endoscopy disease detection challenge 2020 (2020). arXiv:2003.03376"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Arkin, E., Yadikar, N., Muhtar, Y., Ubul, K.: A survey of object detection based on cnn and transformer. In: IEEE 2nd International Conference on Pattern Recognition and Machine learning (PRML), pp. 99\u2013108. IEEE (2021)","DOI":"10.1109\/PRML52754.2021.9520732"},{"issue":"1","key":"15_CR18","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"15_CR19","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"15_CR20","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. PMLR, 2015"},{"key":"15_CR21","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol.\u00a025 (2012)"},{"key":"15_CR22","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions (2017). arXiv:1710.05941"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","DOI":"10.1038\/323533a0"},{"key":"15_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107412","volume":"165","author":"G Wang","year":"2023","unstructured":"Wang, G., Bai, L., Wu, Y., Chen, T., Ren, H.: Rethinking exemplars for continual semantic segmentation in endoscopy scenes: entropy-based mini-batch pseudo-replay. Comput. Biol. Med. 165, 107412 (2023)","journal-title":"Comput. Biol. Med."},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"15_CR27","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus) (2016). arXiv:1606.08415"},{"issue":"4","key":"15_CR28","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., 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(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"15_CR31","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 (2021). arXiv:2102.04306"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yang, D., Li, W., Roth, H.R., Landman, B., Xu, D., Nath, V., Hatamizadeh, A.: Self-supervised pre-training of Swin transformers for 3d medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20\u00a0730\u201320\u00a0740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Tang, F., Xu, Z., Huang, Q., Wang, J., Hou, X., Su, J., Liu, J.: Duat: Dual-aggregation transformer network for medical image segmentation. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 343\u2013356. Springer (2023)","DOI":"10.1007\/978-981-99-8469-5_27"},{"key":"15_CR34","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":"15_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, R., Lai, P., Wan, X., Fan, D.-J., Gao, F., Wu, X.-J., Li, G.: Lesion-aware dynamic kernel for polyp segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 99\u2013109. Springer (2022)","DOI":"10.1007\/978-3-031-16437-8_10"},{"key":"15_CR36","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","volume":"43","author":"J Bernal","year":"2015","unstructured":"Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., Gil, D., Rodr\u00edguez, C., Vilari\u00f1o, F.: Wm-dova maps for accurate polyp highlighting in colonoscopy: validation versus saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99\u2013111 (2015)","journal-title":"Comput. Med. Imaging Graph."},{"issue":"1","key":"15_CR37","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.neuroimage.2009.03.068","volume":"47","author":"H-H Chang","year":"2009","unstructured":"Chang, H.-H., Zhuang, A.H., Valentino, D.J., Chu, W.-C.: Performance measure characterization for evaluating neuroimage segmentation algorithms. Neuroimage 47(1), 122\u2013135 (2009)","journal-title":"Neuroimage"},{"key":"15_CR38","unstructured":"Powers, D.M.W.: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation (2020)"}],"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\/978-981-97-8499-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T14:08:37Z","timestamp":1729260517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8499-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,19]]},"ISBN":["9789819784981","9789819784998"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8499-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,19]]},"assertion":[{"value":"19 October 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"}}]}}