{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:02:25Z","timestamp":1780603345433,"version":"3.54.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.bspc.2026.110662","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:45:21Z","timestamp":1779479121000},"page":"110662","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Attention guided multi-scale fusion network for 3D temporal bone small organ segmentation"],"prefix":"10.1016","volume":"124","author":[{"given":"Qinglei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiazheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5090-9009","authenticated-orcid":false,"given":"Ying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyun","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.bspc.2026.110662_b0005","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.neunet.2020.01.005","article-title":"A 3D deep supervised densely network for small organs of human temporal bone segmentation in CT images","volume":"124","author":"Li","year":"2020","journal-title":"Neural Netw."},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0010","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1148\/radiol.2351020895","article-title":"CT of the normal temporal bone: Comparison of multi\u2013and single\u2013detector row CT","volume":"235","author":"J\u00e4ger","year":"2005","journal-title":"Radiology"},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0015","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s00405-011-1577-z","article-title":"The role of computed tomography scanning in chronic otitis media","volume":"269","author":"Tatlipinar","year":"2012","journal-title":"Eur. Arch. Otorhinolaryngol."},{"issue":"8","key":"10.1016\/j.bspc.2026.110662_b0020","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat. Rev. Cancer"},{"key":"10.1016\/j.bspc.2026.110662_b0025","doi-asserted-by":"crossref","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems,25. https:\/\/doi.org\/10.1145\/3065386.","DOI":"10.1145\/3065386"},{"key":"10.1016\/j.bspc.2026.110662_b0030","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. InInternational Conference on Medical image computing and computer-assisted intervention(pp. 234-241). Cham: Springer international publishing. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0035","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10462-020-09854-1","article-title":"Deep semantic segmentation of natural and medical images: a review[J]","volume":"54","author":"Asgari Taghanaki","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.bspc.2026.110662_b0040","doi-asserted-by":"crossref","unstructured":"Isensee, F., Petersen, J., Klein, A., Zimmerer, D., Jaeger, P. F., Kohl, S., ... & Maier-Hein, K. H. (2018). nnu-net: Self-adapting framework for u-net-based medical image segmentation.arXiv preprint arXiv:1809.10486. https:\/\/doi.org\/10.48550\/arXiv.1809.10486.","DOI":"10.1007\/978-3-658-25326-4_7"},{"key":"10.1016\/j.bspc.2026.110662_b0045","doi-asserted-by":"crossref","unstructured":"Valanarasu, J. M. J., Oza, P., Hacihaliloglu, I., & Patel, V. M. (2021, September). Medical transformer: Gated axial-attention for medical image segmentation. InInternational conference on medical image computing and computer-assisted intervention(pp. 36-46). Cham: Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-030-87193-2_4.","DOI":"10.1007\/978-3-030-87193-2_4"},{"key":"10.1016\/j.bspc.2026.110662_b0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106666","article-title":"Trans-VNet: Transformer-based tooth semantic segmentation in CBCT images","volume":"97","author":"Wang","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.bspc.2026.110662_b0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102801","article-title":"Transformer guided progressive fusion network for 3D pancreas and pancreatic mass segmentation","volume":"86","author":"Qu","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110662_b0060","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need.Advances in neural information processing systems,30. https:\/\/doi.org\/10.48550\/arXiv.1706.03762."},{"key":"10.1016\/j.bspc.2026.110662_b0065","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016, October). 3D U-Net: learning dense volumetric segmentation from sparse annotation. InInternational conference on medical image computing and computer-assisted intervention(pp. 424-432). Cham: Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49.","DOI":"10.1007\/978-3-319-46723-8_49"},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0070","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.bspc.2026.110662_b0075","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., & Ahmadi, S. A. (2016, October). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In2016 fourth international conference on 3D vision (3DV)(pp. 565-571). Ieee. https:\/\/doi.org\/10.1109\/3DV.2016.79.","DOI":"10.1109\/3DV.2016.79"},{"key":"10.1016\/j.bspc.2026.110662_b0080","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition(pp. 770-778). https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.bspc.2026.110662_b0085","doi-asserted-by":"crossref","unstructured":"Zhao, R., Qian, B., Zhang, X., Li, Y., Wei, R., Liu, Y., & Pan, Y. (2020, November). Rethinking dice loss for medical image segmentation.In2020 EEE international conference on data mining (ICDM)(pp. 851-860).Ieee. https:\/\/doi.org\/10.1109\/ICDM50108.2020.00094.","DOI":"10.1109\/ICDM50108.2020.00094"},{"key":"10.1016\/j.bspc.2026.110662_b0090","doi-asserted-by":"crossref","unstructured":"X Li, X., Sun, X., Meng, Y., Liang, J., Wu, F., & Li, J. (2019). Dice loss for data-imbalanced NLP tasks.arXiv preprint arXiv:1911.02855. https:\/\/doi.org\/10.48550\/arXiv.1911.02855.","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"10.1016\/j.bspc.2026.110662_b0095","unstructured":"Mao, A., Mohri, M., & Zhong, Y. (2023, July). Cross-entropy loss functions: Theoretical analysis and applications. InInternational conference on Machine learning(pp. 23803-23828). pmlr. https:\/\/doi.org\/10.48550\/arXiv.2304.07288."},{"key":"10.1016\/j.bspc.2026.110662_b0100","unstructured":"Zhang, Z., & Sabuncu, M. (2018). Generalized cross entropy loss for training deep neural networks with noisy labels.Advances in neural information processing systems,31. https:\/\/doi.org\/10.48550\/arXiv.1805.07836."},{"key":"10.1016\/j.bspc.2026.110662_b0105","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/ACCESS.2019.2962617","article-title":"The real-world-weight cross-entropy loss function: Modeling the costs of mislabeling","volume":"8","author":"Ho","year":"2019","journal-title":"IEEE Access"},{"issue":"6","key":"10.1016\/j.bspc.2026.110662_b0110","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"Unet++: Redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0115","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"Journal of Big Data"},{"key":"10.1016\/j.bspc.2026.110662_b0120","unstructured":"Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., ... & Rueckert, D. (2018). Attention u-net: Learning where to look for the pancreas.arXiv preprint arXiv:1804.03999. https:\/\/doi.org\/10.48550\/arXiv.1804.03999."},{"key":"10.1016\/j.bspc.2026.110662_b0125","doi-asserted-by":"crossref","unstructured":"Ni, Z. L., Bian, G. B., Zhou, X. H., Hou, Z. G., Xie, X. L., Wang, C., ... & Li, Z. (2019, December). Raunet: Residual attention u-net for semantic segmentation of cataract surgical instruments. InInternational Conference on Neural Information Processing(pp. 139-149). Cham: Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-030-36711-4_13.","DOI":"10.1007\/978-3-030-36711-4_13"},{"key":"10.1016\/j.bspc.2026.110662_b0130","unstructured":"Alshawi, R., Hoque, M. T., Ferdaus, M. M., Abdelguerfi, M., Niles, K., Prathak, K., ... & Lopez, J. J. (2023). Dual attention u-net with feature infusion: Pushing the boundaries of multiclass defect segmentation.arXiv preprint arXiv:2312.14053. https:\/\/doi.org\/10.48550\/arXiv.2312.14053."},{"key":"10.1016\/j.bspc.2026.110662_b0135","doi-asserted-by":"crossref","unstructured":"Guo, C., Szemenyei, M., Yi, Y., Wang, W., Chen, B., & Fan, C. (2021, January). Sa-unet: Spatial attention u-net for retinal vessel segmentation. In2020 25th international conference on pattern recognition (ICPR)(pp. 1236-1242). IEEE. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413346.","DOI":"10.1109\/ICPR48806.2021.9413346"},{"key":"10.1016\/j.bspc.2026.110662_b0140","unstructured":"Chen, J., Mei, J., Li, X., Lu, Y., Yu, Q., Wei, Q., ... & Zhou, Y. (2023). 3d transunet: Advancing medical image segmentation through vision transformers.arXiv preprint arXiv:2310.07781. https:\/\/doi.org\/10.48550\/arXiv.2310.07781."},{"key":"10.1016\/j.bspc.2026.110662_b0145","doi-asserted-by":"crossref","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","article-title":"nnformer: Volumetric medical image segmentation via a 3d transformer","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.bspc.2026.110662_b0150","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., ... & Xu, D. (2022). Unetr: Transformers for 3d medical image segmentation. InProceedings of the IEEE\/CVF winter conference on applications of computer vision(pp. 574-584). https:\/\/doi.org\/10.1109\/WACV51458.2022.00181.","DOI":"10.1109\/WACV51458.2022.00181"},{"issue":"11","key":"10.1016\/j.bspc.2026.110662_b0155","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s11548-017-1658-6","article-title":"Atlas-based segmentation of temporal bone anatomy[J]","volume":"12","author":"Powell","year":"2017","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0160","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1186\/s12880-021-00698-x","article-title":"Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study[J]","volume":"21","author":"Wang","year":"2021","journal-title":"BMC Med. Imaging"},{"key":"10.1016\/j.bspc.2026.110662_b0165","doi-asserted-by":"crossref","DOI":"10.3389\/fninf.2022.937891","article-title":"Application value of a deep learning method based on a 3D V-Net convolutional neural network in the recognition and segmentation of the auditory ossicles[J]","volume":"16","author":"Wang","year":"2022","journal-title":"Front. Neuroinf."},{"issue":"8","key":"10.1016\/j.bspc.2026.110662_b0170","doi-asserted-by":"crossref","first-page":"9806","DOI":"10.1109\/TPAMI.2023.3259038","article-title":"Geotransformer: Fast and robust point cloud registration with geometric transformer","volume":"45","author":"Qin","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"10.1016\/j.bspc.2026.110662_b0175","doi-asserted-by":"crossref","first-page":"8517","DOI":"10.1109\/TPAMI.2024.3410324","article-title":"Lowis3d: Language-driven open-world instance-level 3d scene understanding","volume":"46","author":"Ding","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.bspc.2026.110662_b0180","doi-asserted-by":"crossref","first-page":"98909","DOI":"10.1109\/ACCESS.2022.3206449","article-title":"A survey on attention mechanisms for medical applications: are we moving toward better algorithms?","volume":"10","author":"Gon\u00e7alves","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.bspc.2026.110662_b0185","unstructured":"Moya, J. A. B. (2024). Addressing the gaps in early dementia detection: A path towards enhanced diagnostic models through machine learning.arXiv preprint arXiv:2409.03147. https:\/\/doi.org\/10.48550\/arXiv.2409.03147."},{"key":"10.1016\/j.bspc.2026.110662_b0190","doi-asserted-by":"crossref","first-page":"40290","DOI":"10.1109\/ACCESS.2024.3374108","article-title":"MAGRes-UNet: improved medical image segmentation through a deep learning paradigm of multi-attention gated residual U-Net","volume":"12","author":"Hussain","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.bspc.2026.110662_b0195","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. InProceedings of the European conference on computer vision (ECCV)(pp. 3-19). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"10.1016\/j.bspc.2026.110662_b0200","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020). ECA-Net: Efficient channel attention for deep convolutional neural networks. InProceedings of the IEEE\/CVF conference on computer vision and pattern recognition(pp. 11534-11542). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"10.1016\/j.bspc.2026.110662_b0205","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018). Image super-resolution using very deep residual channel attention networks. InProceedings of the European conference on computer vision (ECCV)(pp. 286-301). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_18.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"10.1016\/j.bspc.2026.110662_b0210","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. InProceedings of the European conference on computer vision (ECCV)(pp. 3-19). https:\/\/doi.org\/10.48550\/arXiv.1807.06521.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.bspc.2026.110662_b0215","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.bspc.2026.110662_b0220","doi-asserted-by":"crossref","unstructured":"Zhang, Q. L., & Yang, Y. B. (2021, June). Sa-net: Shuffle attention for deep convolutional neural networks. InICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP)(pp. 2235-2239). IEEE. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414568.","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"issue":"1","key":"10.1016\/j.bspc.2026.110662_b0225","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.aej.2021.04.072","article-title":"Automatic polyp detection and segmentation using shuffle efficient channel attention network","volume":"61","author":"Yang","year":"2022","journal-title":"Alex. Eng. J."},{"issue":"2","key":"10.1016\/j.bspc.2026.110662_b0230","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.compbiomed.2009.11.020","article-title":"Fast segmentation of bone in CT images using 3D adaptive thresholding","volume":"40","author":"Zhang","year":"2010","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.bspc.2026.110662_b0235","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., & Wang, M. (2022, October). Swin-unet: Unet-like pure transformer for medical image segmentation. InEuropean conference on computer vision(pp. 205-218). Cham: Springer Nature Switzerland. https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9.","DOI":"10.1007\/978-3-031-25066-8_9"}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426012164?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426012164?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:34:25Z","timestamp":1780601665000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426012164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":47,"alternative-id":["S1746809426012164"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110662","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Attention guided multi-scale fusion network for 3D temporal bone small organ segmentation","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110662","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"110662"}}