{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T05:11:42Z","timestamp":1792213902859,"version":"4.4.0"},"reference-count":33,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":11,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372280"],"award-info":[{"award-number":["62372280"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402297"],"award-info":[{"award-number":["62402297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022QG051"],"award-info":[{"award-number":["ZR2022QG051"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF094"],"award-info":[{"award-number":["ZR2023QF094"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2024MF139"],"award-info":[{"award-number":["ZR2024MF139"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate spinal MRI segmentation is essential for computer\u2010aided diagnosis of spinal diseases. Existing methods have limitations in global semantic modeling and boundary delineation due to complex anatomy and imaging artifacts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Our work aimed to propose a novel Graph\u2010Guided Frequency\u2010Enhanced State Space Network (GF\u2010SSNet) method to achieve more accurate 3D multi\u2010modal spine MRI automatic segmentation, addressing the limitations of existing algorithms in global semantic modeling of high\u2010dimensional voxel space, cross\u2010modal information synergistic perception, and fine boundary identification of anatomically similar tissues, thereby providing technical support for intelligent diagnosis and precision medicine of spinal diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The proposed network is based on the GF\u2010SSNet architecture. During encoding, a dual frequency\u2010spatial feature enhancement mechanism is employed, which adaptively fuses local frequency dynamic features and global spatial long\u2010range dependencies through Frequency Dynamic Convolution (FDConv) and Three\u2010Directional Mamba\u2010based state space model (TD\u2010Mamba). At the bottleneck, Position\u2010Aware Attention Fusion (PAAF) and Graph Convolutional Networks (GCN) are integrated to explicitly encode topological anatomical constraints between vertebrae, enhancing the global perception capability of spinal continuity structures. During decoding, a Depth\u2010aware Progressive Upsampling (DAPU) strategy is introduced to effectively alleviate the reconstruction loss of fine\u2010grained spatial information. The entire framework achieves end\u2010to\u2010end automatic segmentation of multi\u2010modal MR images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the normal test set, GF\u2010SSNet outperformed all baselines across all metrics. Specifically, Dice and IoU Means reached 92.04\u00a0\u00b1\u00a00.06% and 85.29\u00a0\u00b1\u00a00.10%, exceeding the best baseline results of 89.81\u00a0\u00b1\u00a00.61% and 81.51\u00a0\u00b1\u00a00.91%. HD95 and ASSD were significantly reduced to 3.06\u00a0\u00b1\u00a00.46\u00a0mm and 0.612\u00a0\u00b1\u00a00.018\u00a0mm, compared to top\u2010tier baseline values of 4.76\u00a0\u00b1\u00a01.09\u00a0mm and 1.14\u00a0\u00b1\u00a00.01\u00a0mm, respectively. On an independent pathological test set with various spinal pathologies, GF\u2010SSNet maintained superior performance with Dice Mean of 87.60\u00a0\u00b1\u00a00.10%, still outperforming all baseline methods. The 4.4 percentage point performance decline from normal cases primarily stemmed from intervertebral disc segmentation challenges in degenerative conditions, while vertebrae segmentation remained robust. Ablation studies confirmed significant contributions of all proposed components. The proposed HFD\u2010Tversky loss outperformed conventional losses. All performance differences were statistically significant after correction for multiple comparisons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GF\u2010SSNet demonstrates performance in spinal segmentation through adaptive fusion of frequency features and global dependencies, providing technical support for intelligent spinal disease diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70481","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T02:09:15Z","timestamp":1770948555000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Graph\u2010guided frequency\u2010enhanced state space network for 3D spine segmentation from MR images"],"prefix":"10.1002","volume":"27","author":[{"given":"Linghui","family":"Hong","sequence":"first","affiliation":[{"name":"Center for Medical Artificial Intelligence Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Academy of Chinese Medical Sciences Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8811-8864","authenticated-orcid":false,"given":"Zhengchao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Center for Medical Artificial Intelligence Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Academy of Chinese Medical Sciences Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging Center Qilu Hospital of Shandong University Dezhou Hospital  Dezhou China"},{"name":"Dezhou Key Laboratory of Intelligent Imaging  Dezhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingping","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Medical Artificial Intelligence Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Academy of Chinese Medical Sciences Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benzheng","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Medical Artificial Intelligence Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Academy of Chinese Medical Sciences Shandong University of Traditional Chinese Medicine  Qingdao China"},{"name":"Qingdao Key Laboratory of Artificial Intelligence Technology in Traditional Chinese Medicine  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis\u20102013\u2010204428"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(12)61729\u20102"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(99)01312\u20104"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(12)61689\u20104"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1097\/00007632\u2010200109010\u201000011"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2493071999"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102166"},{"key":"e_1_2_12_9_1","unstructured":"RonnebergerO FischerP BroxT U\u2010Net: convolutional networks for biomedical image segmentation. arXiv. Preprint posted online May 18 2015. doi:10.48550\/arXiv.1505.04597"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_12_12_1","doi-asserted-by":"crossref","unstructured":"HuangH LinL TongR et\u00a0al.UNet 3+: a Full\u2010Scale Connected UNet for Medical Image Segmentation. In:ICASSP 2020 \u2010 2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).IEEE;2020:1055\u20101059. doi:10.1109\/ICASSP40776.2020.9053405","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"e_1_2_12_13_1","unstructured":"ChenJ LuY YuQ et\u00a0al.TransUNet: transformers make strong encoders for medical image segmentation. arXiv. Preprint posted online February 8 2021. doi:10.48550\/arXiv.2102.04306"},{"key":"e_1_2_12_14_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA TangY NathV et\u00a0al.UNETR: transformers for 3D medical image segmentation. In:2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV).IEEE;2022:1748\u20101758. doi:10.1109\/WACV51458.2022.00181","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"e_1_2_12_15_1","doi-asserted-by":"crossref","unstructured":"HatamizadehA NathV TangY YangD RothH XuD SwinUNETR: swin transformers for semantic segmentation of brain tumors in MRI images. arXiv. Preprint posted online January 4 2022. doi:10.48550\/arXiv.2201.01266","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108795"},{"key":"e_1_2_12_17_1","unstructured":"GuA GoelK R\u00e9C Efficiently Modeling Long Sequences with Structured State Spaces. arXiv. Preprint posted online August 5 2022. doi:10.48550\/arXiv.2111.00396"},{"key":"e_1_2_12_18_1","unstructured":"GuA DaoT Mamba: linear\u2010Time Sequence Modeling with Selective State Spaces. arXiv. Preprint posted online May 31 2024. doi:10.48550\/arXiv.2312.00752"},{"key":"e_1_2_12_19_1","unstructured":"MaJ LiF WangB U\u2010Mamba: enhancing Long\u2010range Dependency for Biomedical Image Segmentation. arXiv. Preprint posted online January 9 2024. doi:10.48550\/arXiv.2401.04722"},{"key":"e_1_2_12_20_1","doi-asserted-by":"crossref","unstructured":"XingZ YeT YangY LiuG ZhuL SegMamba: long\u2010range sequential modeling mamba for 3D medical image segmentation. arXiv. Preprint posted online September 15 2024. doi:10.48550\/arXiv.2401.13560","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"e_1_2_12_21_1","doi-asserted-by":"crossref","unstructured":"PangS LeungS NachumIB FengQ LiS Direct automated quantitative measurement of spine via cascade amplifier regression network. arXiv. Preprint posted online June 14 2018. doi:10.48550\/arXiv.1806.05570","DOI":"10.1007\/978-3-030-00934-2_104"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107290"},{"key":"e_1_2_12_23_1","doi-asserted-by":"crossref","unstructured":"WangW WangJ ChenC et\u00a0al.FreMIM: Fourier transform meets masked image modeling for medical image segmentation. In:2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV).IEEE;2024:7845\u20107855. doi:10.1109\/WACV57701.2024.00768","DOI":"10.1109\/WACV57701.2024.00768"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106280"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11101034"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e35698"},{"key":"e_1_2_12_27_1","doi-asserted-by":"crossref","unstructured":"ZhouZ HeA WuY YaoR XieX LiT Spatial\u2010frequency dual domain attention network for medical image segmentation. In:2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).IEEE;2024:4076\u20104081. doi:10.1109\/BIBM62325.2024.10822613","DOI":"10.1109\/BIBM62325.2024.10822613"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102235"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105153"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3025087"},{"key":"e_1_2_12_31_1","unstructured":"PeirisH HayatM ChenZ EganG HarandiM A robust volumetric transformer for accurate 3D tumor segmentation. arXiv. Preprint posted online July 1 2022. doi:10.48550\/arXiv.2111.13300"},{"key":"e_1_2_12_32_1","unstructured":"ZhouR FengY WangG et\u00a0al.TSUBF\u2010net: trans\u2010spatial UNet\u2010like network with bi\u2010direction fusion for segmentation of adenoid hypertrophy in CT. arXiv. Preprint posted online December 1 2024. doi:10.48550\/arXiv.2412.00787"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102531"},{"key":"e_1_2_12_34_1","doi-asserted-by":"crossref","unstructured":"BozorgpourA AzadB AzadR VelichkoY BagciU Merhof D. HCA\u2010Net: Hierarchical Context Attention Network for Intervertebral Disc Semantic Labeling. arXiv. Preprint posted online November 21 2023:arXiv:2311.12486. doi:10.48550\/arXiv.2311.12486","DOI":"10.1109\/ISBI56570.2024.10635688"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70481","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70481","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T13:43:27Z","timestamp":1791985407000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/acm2.70481"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70481","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"2025-09-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70481"}}