{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T06:10:10Z","timestamp":1756447810090,"version":"3.44.0"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Spinal X-ray image segmentation faces several challenges, such as complex anatomical structures, large variations in scale, and blurry or low-contrast boundaries between vertebrae and surrounding tissues. These factors make it difficult for traditional models to achieve accurate and robust segmentation. To address these issues, this study proposes MDWC-Net, a novel deep learning framework designed to improve the accuracy and efficiency of spinal structure identification in clinical settings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>MDWC-Net adopts an encoder\u2013decoder architecture and introduces three modules\u2014MSCAW, DFCB, and BIEB\u2014to address key challenges in spinal X-ray image segmentation. The network is trained and evaluated on the Spine Dataset, which contains 280 X-ray images provided by Henan Provincial People\u2019s Hospital and is randomly divided into training, validation, and test sets with a 7:1:2 ratio. In addition, to evaluate the model\u2019s generalizability, further validation was conducted on the Chest X-ray dataset for lung field segmentation and the ISIC2016 dataset for melanoma boundary delineation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>MDWC-Net outperformed other mainstream models overall. On the Spine Dataset, it achieved a Dice score of 89.86% \u00b1 0.356, MIoU of 90.53% \u00b1 0.315, GPA of 96.82% \u00b1 0.289, and Sensitivity of 96.77% \u00b1 0.212. A series of ablation experiments further confirmed the effectiveness of the MSCAW, DFCB, and BIEB modules.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>MDWC-Net delivers accurate and efficient segmentation of spinal structures, showing strong potential for integration into clinical workflows. Its high performance and generalizability suggest broad applicability to other medical image segmentation tasks.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fphys.2025.1651296","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T05:44:39Z","timestamp":1756446279000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MDWC-Net: a multi-scale dynamic-weighting context network for precise spinal X-ray segmentation"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhongzheng","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baojun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1002\/mp.16731","article-title":"Anatomy-aware computed tomography-to-ultrasound spine registration","volume":"51","author":"Azampour","year":"2024","journal-title":"Med. Phys."},{"key":"B2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3390\/s24010209","article-title":"Mid-DeepLabv3+: a novel approach for image semantic segmentation applied to African food dietary assessments","volume":"24","author":"Baban","year":"2023","journal-title":"Sensors (Basel)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1307492","DOI":"10.3389\/fpls.2023.1307492","article-title":"An efficient approach to detect and track winter flush growth of litchi tree based on UAV remote sensing and semantic segmentation","volume":"14","author":"Bai","year":"2023","journal-title":"Front. Plant Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/tmi.2013.2290491","article-title":"Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration","volume":"33","author":"Candemir","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B5","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/tip.2011.2169273","article-title":"The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods","volume":"21","author":"Carneiro","year":"2012","journal-title":"IEEE Trans. Image Process"},{"key":"B6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/tpami.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B7","doi-asserted-by":"publisher","first-page":"108120","DOI":"10.1016\/j.compbiomed.2024.108120","article-title":"LD-UNet: a long-distance perceptual model for segmentation of blurred boundaries in medical images","volume":"171","author":"Chen","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"3341","DOI":"10.1038\/s41598-023-49923-3","article-title":"VertXNet: an ensemble method for vertebral body segmentation and identification from cervical and lumbar spinal X-rays","volume":"14","author":"Chen","year":"2024","journal-title":"Sci. Rep."},{"key":"B9","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"B10","doi-asserted-by":"publisher","first-page":"103385","DOI":"10.1016\/j.media.2024.103385","article-title":"A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond","volume":"100","author":"Chen","year":"2025","journal-title":"Med. Image Anal."},{"key":"B11","doi-asserted-by":"publisher","first-page":"102129","DOI":"10.1016\/j.cpcardiol.2023.102129","article-title":"Attention-UNet architectures with pretrained backbones for multi-class cardiac MR image segmentation","volume":"49","author":"Das","year":"2024","journal-title":"Curr. Probl. Cardiol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"105682","DOI":"10.1016\/j.bspc.2023.105682","article-title":"An effective U-Net and BiSeNet complementary network for spine segmentation","volume":"89","author":"Deng","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/s13018-025-05564-y","article-title":"Deep learning-assisted screening and diagnosis of scoliosis: segmentation of bare-back images via an attention-enhanced convolutional neural network","volume":"20","author":"Duan","year":"2025","journal-title":"J. Orthop. Surg. Res."},{"key":"B14","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: deep learning for cell counting, detection, and morphometry","volume":"16","author":"Falk","year":"2019","journal-title":"Nat. Methods"},{"key":"B15","doi-asserted-by":"publisher","first-page":"106081","DOI":"10.1016\/j.cmpb.2021.106081","article-title":"A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-Net model","volume":"205","author":"Gegundez-Arias","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"B16","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41587-021-01094-0","article-title":"Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning","volume":"40","author":"Greenwald","year":"2022","journal-title":"Nat. Biotechnol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"327","DOI":"10.3390\/rs16020327","article-title":"Remote sensing object detection in the deep learning Era-A review","volume":"16","author":"Gui","year":"2024","journal-title":"Remote Sens."},{"key":"B18","article-title":"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)","author":"Gutman","year":"2016"},{"key":"B19","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/tmi.2013.2284099","article-title":"Automatic tuberculosis screening using chest radiographs","volume":"33","author":"Jaeger","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"6761","DOI":"10.1109\/tip.2024.3501076","article-title":"Revisiting domain-adaptive semantic segmentation via knowledge distillation","volume":"33","author":"Jeong","year":"2024","journal-title":"IEEE Trans. Image Process"},{"key":"B21","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1089\/cmb.2023.0102","article-title":"Using attention-UNet models to predict protein contact maps","volume":"31","author":"Jisna","year":"2024","journal-title":"J. Comput. Biol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"20","DOI":"10.14245\/ns.2347138.569","article-title":"Spinal robotics in adult spinal deformity surgery: a systematic review","volume":"21","author":"Khalifeh","year":"2024","journal-title":"Neurospine"},{"key":"B23","doi-asserted-by":"publisher","first-page":"102231","DOI":"10.1016\/j.artmed.2021.102231","article-title":"RMS-UNet: residual multi-scale UNet for liver and lesion segmentation","volume":"124","author":"Khan","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"776","DOI":"10.31616\/asj.2022.0376","article-title":"Adult spinal deformity: a comprehensive review of current advances and future directions","volume":"16","author":"Kim","year":"2022","journal-title":"Asian Spine J."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1038\/s43588-023-00555-7","article-title":"Predicting emerging drug interactions using GNNs","volume":"3","author":"Le","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"B26","doi-asserted-by":"publisher","first-page":"11589","DOI":"10.1007\/s00521-021-05856-4","article-title":"Automatic lumbar spinal MRI image segmentation with a multi-scale attention network","volume":"33","author":"Li","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"B27","doi-asserted-by":"publisher","first-page":"9678","DOI":"10.3390\/s22249678","article-title":"Semantic segmentation of hyperspectral remote sensing images based on PSE-UNet model","volume":"22","author":"Li","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B28","doi-asserted-by":"publisher","first-page":"107596","DOI":"10.1016\/j.compbiomed.2023.107596","article-title":"SUnet: a multi-organ segmentation network based on multiple attention","volume":"167","author":"Li","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"4052","DOI":"10.1109\/jbhi.2023.3278079","article-title":"AC-E network: attentive context-enhanced network for liver segmentation","volume":"27","author":"Li","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B30","doi-asserted-by":"publisher","first-page":"103027","DOI":"10.1016\/j.media.2023.103027","article-title":"Automatic registration with continuous pose updates for marker-less surgical navigation in spine surgery","volume":"91","author":"Liebmann","year":"2024","journal-title":"Med. Image Anal."},{"key":"B31","doi-asserted-by":"publisher","first-page":"e1161","DOI":"10.1097\/brs.0000000000004060","article-title":"Scoliosis surgery normalizes cardiac function in adolescent idiopathic scoliosis patients","volume":"46","author":"Sarwahi","year":"2021","journal-title":"Spine (Phila Pa 1976)"},{"key":"B32","doi-asserted-by":"publisher","first-page":"3976","DOI":"10.1109\/jbhi.2022.3158968","article-title":"Attention gate based dual-pathway network for vertebra segmentation of X-ray spine images","volume":"26","author":"Shi","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.1002\/mp.16840","article-title":"PLU-Net: extraction of multiscale feature fusion","volume":"51","author":"Song","year":"2024","journal-title":"Med. Phys."},{"key":"B34","doi-asserted-by":"publisher","first-page":"23103","DOI":"10.1007\/s00521-023-08957-4","article-title":"Deep learning: systematic review, models, challenges, and research directions","volume":"35","author":"Talaei Khoei","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"B35","doi-asserted-by":"publisher","first-page":"4577","DOI":"10.1038\/s41598-024-54096-8","article-title":"A Siamese Swin-Unet for image change detection","volume":"14","author":"Tang","year":"2024","journal-title":"Sci. Rep."},{"key":"B36","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1002\/mp.17782","article-title":"Trade-off of different deep learning-based auto-segmentation approaches for treatment planning of pediatric craniospinal irradiation autocontouring of OARs for pediatric CSI","volume":"52","author":"Thibodeau-Antonacci","year":"2025","journal-title":"Med. Phys."},{"key":"B37","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jare.2021.03.015","article-title":"A review on modern defect detection models using DCNNs - deep convolutional neural networks","volume":"35","author":"Tulbure","year":"2022","journal-title":"J. Adv. Res."},{"key":"B38","doi-asserted-by":"publisher","first-page":"108377","DOI":"10.1016\/j.ymssp.2021.108377","article-title":"Fully convolution network architecture for steel-beam crack detection in fast-stitching images","volume":"165","author":"Wang","year":"2022","journal-title":"Mech. Syst. Signal Process."},{"key":"B39","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.3390\/s23104793","article-title":"Image generation and recognition for railway surface defect detection","volume":"23","author":"Xia","year":"2023","journal-title":"Sensors (Basel)"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1423238","DOI":"10.3389\/fpls.2024.1423238","article-title":"LT-DeepLab: an improved DeepLabV3+ cross-scale segmentation algorithm for Zanthoxylum bungeanum Maxim leaf-trunk diseases in real-world environments","volume":"15","author":"Yang","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B41","doi-asserted-by":"publisher","first-page":"115561","DOI":"10.1016\/j.bone.2020.115561","article-title":"Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: a multicenter retrospective cohort study","volume":"140","author":"Zhang","year":"2020","journal-title":"Bone"},{"key":"B42","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.660","article-title":"Pyramid scene parsing network","volume-title":"Paper presented at the 30th IEEE\/CVF conference on computer vision and pattern recognition (CVPR), Honolulu, HI","author":"Zhao","year":"2017"},{"key":"B43","doi-asserted-by":"publisher","first-page":"107998","DOI":"10.1016\/j.patcog.2021.107998","article-title":"A nested U-shape network with multi-scale upsample attention for robust retinal vascular segmentation","volume":"120","author":"Zhao","year":"2021","journal-title":"Pattern Recognit."},{"key":"B44","doi-asserted-by":"publisher","first-page":"40569","DOI":"10.1021\/acsomega.2c05881","article-title":"Improved prediction model of protein and peptide toxicity by integrating channel attention into a convolutional neural network and gated recurrent units","volume":"7","author":"Zhao","year":"2022","journal-title":"ACS Omega"},{"key":"B45","doi-asserted-by":"publisher","first-page":"4871","DOI":"10.1002\/mp.16253","article-title":"Feature-guided attention network for medical image segmentation","volume":"50","author":"Zhou","year":"2023","journal-title":"Med. Phys."},{"key":"B46","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1109\/tcbb.2023.3284215","article-title":"AR-UNet: a deformable image registration network with cyclic training","volume":"21","author":"Zhou","year":"2024","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B47","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.inffus.2022.10.022","article-title":"Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI","volume":"91","author":"Zhu","year":"2023","journal-title":"Inf. Fusion"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1651296\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T05:44:40Z","timestamp":1756446280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1651296\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":47,"alternative-id":["10.3389\/fphys.2025.1651296"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2025.1651296","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]},"article-number":"1651296"}}