{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T14:56:05Z","timestamp":1778079365470,"version":"3.51.4"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"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":[[2025,10]]},"DOI":"10.1007\/s00371-025-04056-8","type":"journal-article","created":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T09:05:55Z","timestamp":1751187955000},"page":"10577-10597","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Attention-guided fusion of transformers and CNNs for enhanced medical image segmentation"],"prefix":"10.1007","volume":"41","author":[{"given":"Shiyao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"4056_CR1","first-page":"81","volume":"12032","author":"A Lou","year":"2022","unstructured":"Lou, A., Guan, S., Ko, H., Loew, M.H.: CaraNet: context axial reverse attention network for segmentation of small medical objects. Med. Imaging 2022: Image Process. 12032, 81\u201392 (2022)","journal-title":"Med. Imaging 2022: Image Process."},{"key":"4056_CR2","doi-asserted-by":"crossref","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)","DOI":"10.1109\/BIBM55620.2022.9995040"},{"key":"4056_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q.: Transfuse: fusing transformers and cnns 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. 14\u201324. Springer International Publishing (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"4056_CR4","doi-asserted-by":"crossref","unstructured":"Xu, Z., Lu, D., Wang, Y., Luo, J., Jayender, J., Ma, K., Li, X.: Noisy labels are treasure: mean-teacher-assisted confident learning for hepatic vessel 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. 3\u201313. Springer International Publishing. (2021).","DOI":"10.1007\/978-3-030-87193-2_1"},{"key":"4056_CR5","doi-asserted-by":"publisher","first-page":"107454","DOI":"10.1016\/j.engappai.2023.107454","volume":"128","author":"Q Qin","year":"2024","unstructured":"Qin, Q., Chen, Y.: A review of retinal vessel segmentation for fundus image analysis. Eng. Appl. Artif. Intell. 128, 107454 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"4","key":"4056_CR6","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/TCYB.2022.3162873","volume":"53","author":"H Wu","year":"2022","unstructured":"Wu, H., Zhao, Z., Zhong, J., Wang, W., Wen, Z., Qin, J.: Polypseg+: A lightweight context-aware network for real-time polyp segmentation. IEEE Trans. Cybern. 53(4), 2610\u20132621 (2022)","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"4056_CR7","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1007\/s10555-023-10158-3","volume":"43","author":"R Abedizadeh","year":"2024","unstructured":"Abedizadeh, R., Majidi, F., Khorasani, H.R., Abedi, H., Sabour, D.: Colorectal cancer: a comprehensive review of carcinogenesis, diagnosis, and novel strategies for classified treatments. Cancer Metastasis Rev. 43(2), 729\u2013753 (2024)","journal-title":"Cancer Metastasis Rev."},{"key":"4056_CR8","doi-asserted-by":"publisher","first-page":"102327","DOI":"10.1016\/j.media.2021.102327","volume":"76","author":"H Wu","year":"2022","unstructured":"Wu, H., Chen, S., Chen, G., Wang, W., Lei, B., Wen, Z.: FAT-Net: Feature adaptive transformers for automated skin lesion segmentation. Med. Image Anal. 76, 102327 (2022)","journal-title":"Med. Image Anal."},{"issue":"3","key":"4056_CR9","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.clindermatol.2023.12.022","volume":"42","author":"M Strzelecki","year":"2024","unstructured":"Strzelecki, M., Kocio\u0142ek, M., Str\u0105kowska, M., Koz\u0142owski, M., Grzybowski, A., Szczypi\u0144ski, P.M.: Artificial Intelligence in the detection of skin cancer: state of the art. Clin. Dermatol. 42(3), 280\u2013295 (2024)","journal-title":"Clin. Dermatol."},{"key":"4056_CR10","doi-asserted-by":"crossref","unstructured":"Ge, Z., Demyanov, S., Chakravorty, R., Bowling, A., Garnavi, R. Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images. In: Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11\u201313, 2017, Proceedings, Part III 20 pp, 250\u2013258. Springer International Publishing (2017)","DOI":"10.1007\/978-3-319-66179-7_29"},{"issue":"3","key":"4056_CR11","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1159\/000446488","volume":"32","author":"FT Kolligs","year":"2016","unstructured":"Kolligs, F.T.: Diagnostics and epidemiology of colorectal cancer. Visc. Med. 32(3), 158\u2013164 (2016)","journal-title":"Visc. Med."},{"key":"4056_CR12","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":"4056_CR13","doi-asserted-by":"crossref","unstructured":"Li, Q., Yang, G., Chen, Z., Huang, B., Chen, L., Xu, D., Wang, T.: Colorectal polyp segmentation using a fully convolutional neural network. In 2017 10th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI). pp 1\u20135. IEEE (2017)","DOI":"10.1109\/CISP-BMEI.2017.8301980"},{"key":"4056_CR14","doi-asserted-by":"crossref","unstructured":"Brandao, P., Mazomenos, E., Ciuti, G., Cali\u00f2, R., Bianchi, F., Menciassi, A., Stoyanov, D.: Fully convolutional neural networks for polyp segmentation in colonoscopy. In: Medical Imaging 2017: Computer-Aided Diagnosis. Spie. Vol. 10134, pp. 101-107 (2017)","DOI":"10.1117\/12.2254361"},{"key":"4056_CR15","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\u2014MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, part III 18 pp, 234\u2013241. Springer International Publishing (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"4056_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman Siddiquee, 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: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4. pp 3\u201311. Springer International Publishing (2018)","DOI":"10.1007\/978-3-030-00889-5_1"},{"issue":"3","key":"4056_CR17","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1016\/j.bbe.2020.07.007","volume":"40","author":"A Khanna","year":"2020","unstructured":"Khanna, A., Londhe, N.D., Gupta, S., Semwal, A.: A deep Residual U-Net convolutional neural network for automated lung segmentation in computed tomography images. Biocybern. Biomed. Eng. 40(3), 1314\u20131327 (2020)","journal-title":"Biocybern. Biomed. Eng."},{"key":"4056_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, Q., Li, X., Li, H., Zhang, L.: Automated segmentation of cervical nuclei in pap smear images using deformable multi-path ensemble model. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) pp, 1514\u20131518). IEEE (2019)","DOI":"10.1109\/ISBI.2019.8759262"},{"key":"4056_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4056_CR20","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp, 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"4056_CR21","doi-asserted-by":"crossref","unstructured":"Sun, X., Zhang, P., Wang, D., Cao, Y., Liu, B.: Colorectal polyp segmentation by U-Net with dilation convolution. In 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA) pp, 851\u2013858. IEEE (2019)","DOI":"10.1109\/ICMLA.2019.00148"},{"key":"4056_CR22","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4056_CR23","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning. pp 10347\u201310357. PMLR (2021)"},{"key":"4056_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., 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)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"3","key":"4056_CR25","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., Shao, L.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Vis. Med. 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Med."},{"key":"4056_CR26","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"4056_CR27","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Zhou, Y.: Transunet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"4056_CR28","doi-asserted-by":"crossref","unstructured":"Wenxuan, W., Chen, C., Meng, D., Hong, Y., Sen, Z., Jiangyun, L.: Transbts: multimodal brain tumor segmentation using transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp, 109\u2013119 (2021)","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"4056_CR29","first-page":"1","volume":"71","author":"A Lin","year":"2022","unstructured":"Lin, A., Chen, B., Xu, J., Zhang, Z., Lu, G., Zhang, D.: Ds-transunet: Dual swin transformer u-net for medical image segmentation. IEEE Trans. Instrum. Meas. 71, 1\u201315 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4056_CR30","doi-asserted-by":"publisher","first-page":"108235","DOI":"10.1016\/j.cmpb.2024.108235","volume":"252","author":"Z Huang","year":"2024","unstructured":"Huang, Z., Zhao, Y., Yu, Z., Qin, P., Han, X., Wang, M., Gregersen, H.: BiU-net: a dual-branch structure based on two-stage fusion strategy for biomedical image segmentation. Comput. Methods Progr. Biomed. 252, 108235 (2024)","journal-title":"Comput. Methods Progr. Biomed."},{"issue":"1","key":"4056_CR31","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., 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"},{"issue":"11","key":"4056_CR32","doi-asserted-by":"publisher","first-page":"5953","DOI":"10.1007\/s00371-022-02705-w","volume":"39","author":"L Qian","year":"2023","unstructured":"Qian, L., Huang, H., Xia, X., Li, Y., Zhou, X.: Automatic segmentation method using FCN with multi-scale dilated convolution for medical ultrasound image. Vis. Comput. 39(11), 5953\u20135969 (2023)","journal-title":"Vis. Comput."},{"issue":"4","key":"4056_CR33","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11760-022-02325-w","volume":"17","author":"I Bakkouri","year":"2023","unstructured":"Bakkouri, I., Afdel, K.: MLCA2F: multi-level context attentional feature fusion for COVID-19 lesion segmentation from CT scans. SIViP 17(4), 1181\u20131188 (2023)","journal-title":"SIViP"},{"key":"4056_CR34","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Rueckert, D.: Attention u-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)"},{"key":"4056_CR35","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., Heinrich, M., Kainz, B., Glocker, B., Rueckert, D.: Attention gated networks: learning to leverage salient regions in medical images. Med. Image Anal. 53, 197\u2013207 (2019)","journal-title":"Med. Image Anal."},{"key":"4056_CR36","doi-asserted-by":"crossref","unstructured":"Jha, D., Smedsrud, P.H., Riegler, M.A., Johansen, D., De Lange, 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":"4056_CR37","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. Cham: Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"4056_CR38","doi-asserted-by":"crossref","unstructured":"Chen, S., Tan, X., Wang, B., Hu, X.: Reverse attention for salient object detection. In: Proceedings of the European Conference on Computer Vision (ECCV). pp 234\u2013250 (2018)","DOI":"10.1007\/978-3-030-01240-3_15"},{"issue":"4","key":"4056_CR39","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1109\/TMI.2022.3223683","volume":"42","author":"R Liu","year":"2022","unstructured":"Liu, R., Wang, T., Li, H., Zhang, P., Li, J., Yang, X., Sheng, B.: TMM-Nets: transferred multi-to mono-modal generation for lupus retinopathy diagnosis. IEEE Trans. Med. Imaging 42(4), 1083\u20131094 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4056_CR40","doi-asserted-by":"publisher","first-page":"1398237","DOI":"10.3389\/fbioe.2024.1398237","volume":"12","author":"G Sun","year":"2024","unstructured":"Sun, G., Pan, Y., Kong, W., Xu, Z., Ma, J., Racharak, T., Xin, J.: DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation. Front. Bioeng. Biotechnol. 12, 1398237 (2024)","journal-title":"Front. Bioeng. Biotechnol."},{"issue":"8","key":"4056_CR41","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1007\/s00371-023-02965-0","volume":"39","author":"D Meng","year":"2023","unstructured":"Meng, D., Li, S., Sheng, B., Wu, H., Tian, S., Ma, W., Yan, X.: 3D reconstruction-oriented fully automatic multi-modal tumor segmentation by dual attention-guided VNet. Vis. Comput. 39(8), 3183\u20133196 (2023)","journal-title":"Vis. Comput."},{"issue":"12","key":"4056_CR42","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1109\/TMI.2021.3087857","volume":"40","author":"R Liu","year":"2021","unstructured":"Liu, R., Liu, M., Sheng, B., Li, H., Li, P., Song, H., Shen, D.: NHBS-Net: a feature fusion attention network for ultrasound neonatal hip bone segmentation. IEEE Trans. Med. Imaging 40(12), 3446\u20133458 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"8","key":"4056_CR43","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2021","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.P.: BaGFN: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learning Syst. 34(8), 4499\u20134513 (2021)","journal-title":"IEEE Trans. Neural Netw. Learning Syst."},{"key":"4056_CR44","doi-asserted-by":"crossref","unstructured":"Chen, C. F. R., Fan, Q., & Panda, R.: Crossvit: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp, 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"4056_CR45","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 International Publishing (2021)","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"4056_CR46","doi-asserted-by":"crossref","unstructured":"Wang, J., Wei, L., Wang, L., Zhou, Q., Zhu, L., Qin, J.: Boundary-aware transformers for skin lesion segmentation. In: Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24 pp. 206\u2013216. Springer International Publishing (2021)","DOI":"10.1007\/978-3-030-87193-2_20"},{"key":"4056_CR47","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Fei-Fei, L.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"4056_CR48","doi-asserted-by":"crossref","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).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"4056_CR49","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"4056_CR50","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"4056_CR51","doi-asserted-by":"crossref","unstructured":"Jha, D., Smedsrud, P. H., Riegler, M. A., Halvorsen, P., De Lange, T., Johansen, D., Johansen, H. D.: Kvasir-seg: a segmented polyp dataset. In: MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, part II 26 pp, 451\u2013462. Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"4056_CR52","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 vs. saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99\u2013111 (2015)","journal-title":"Comput. Med. Imaging Graph."},{"issue":"2","key":"4056_CR53","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","volume":"35","author":"N Tajbakhsh","year":"2015","unstructured":"Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automated polyp detection in colonoscopy videos using shape and context information. IEEE Trans. Med. Imaging 35(2), 630\u2013644 (2015)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4056_CR54","first-page":"4037190","volume":"1","author":"D V\u00e1zquez","year":"2017","unstructured":"V\u00e1zquez, D., Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., L\u00f3pez, A.M., Romero, A., Courville, A.: A benchmark for endoluminal scene segmentation of colonoscopy images. J. Healthc. Eng. 1, 4037190 (2017)","journal-title":"J. Healthc. Eng."},{"key":"4056_CR55","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","volume":"9","author":"J Silva","year":"2014","unstructured":"Silva, J., Histace, A., Romain, O., Dray, X., Granado, B.: Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 9, 283\u2013293 (2014)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"4056_CR56","unstructured":"Huang, C. H., Wu, H. Y., Lin, Y. L.: Hardnet-mseg: a simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps. arXiv preprint arXiv:2101.07172 (2021)"},{"key":"4056_CR57","unstructured":"Gutman, D., Codella, N. C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., Halpern, A.: Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1605.01397 (2016)"},{"key":"4056_CR58","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Chintala, S.: Pytorch: an imperative style, high-performance deep learning library. Advances in neural information processing systems. 32 (2019)"},{"key":"4056_CR59","doi-asserted-by":"crossref","unstructured":"Margolin, R., Zelnik-Manor, L., Tal, A.: How to evaluate foreground maps? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 248\u2013255 (2014)","DOI":"10.1109\/CVPR.2014.39"},{"key":"4056_CR60","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition pp, 1597\u20131604. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"4056_CR61","doi-asserted-by":"crossref","unstructured":"Liao, T. Y., Yang, C. H., Lo, Y. W., Lai, K. Y., Shen, P. H., Lin, Y. L.: HarDNet-DFUS: an enhanced harmonically-connected network for diabetic foot ulcer image segmentation and colonoscopy polyp segmentation. arXiv preprint arXiv:2209.07313 (2022)","DOI":"10.1007\/978-3-031-26354-5_2"},{"key":"4056_CR62","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":"4056_CR63","unstructured":"Biswas, R. Polyp-sam++: Can a text guided sam perform better for polyp segmentation?. arXiv preprint arXiv:2308.06623 (2023)"},{"key":"4056_CR64","unstructured":"Trinh, Q.H., Nguyen, H.D., Ngoc, B.T.N., Jha,D., Bagci, U., Tran, M.T.: SAM-EG: segment Anything Model with Egde Guidance framework for efficient polyp segmentation. arXiv preprint arXiv:2406.14819 (2024)"},{"key":"4056_CR65","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 European Conference on Computer Vision. pp 205\u2013218. Springer Nature Switzerland (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"4056_CR66","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Marculescu, R.: G-cascade: efficient cascaded graph convolutional decoding for 2d medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp 7728\u20137737 (2024)","DOI":"10.1109\/WACV57701.2024.00755"},{"key":"4056_CR67","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Munir, M., Marculescu, R.:Emcad: efficient multi-scale convolutional attention decoding for medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 11769\u201311779 (2024)","DOI":"10.1109\/CVPR52733.2024.01118"},{"issue":"1","key":"4056_CR68","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.vrih.2023.08.005","volume":"6","author":"M Li","year":"2024","unstructured":"Li, M., Jung, Y., Fulham, M., Kim, J.: Importance-aware 3D volume visualization for medical content-based image retrieval-a preliminary study. Virtual Real. Intell. Hardw. 6(1), 71\u201381 (2024)","journal-title":"Virtual Real. Intell. Hardw."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04056-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04056-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04056-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T14:02:47Z","timestamp":1758722567000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04056-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":68,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4056"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04056-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"5 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2025","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}