{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:54:51Z","timestamp":1776311691416,"version":"3.50.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T00:00:00Z","timestamp":1741737600000},"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. Artif. Intell."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>The anatomically constrained registration network (AC-RegNet), which yields anatomically plausible results, has emerged as the state-of-the-art registration architecture for chest X-ray (CXR) images. Nevertheless, accurate lung field registration results may be more favored and exciting than the registration results of the entire CXR images and hold promise for dynamic lung field analysis in clinical practice.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>Based on the above, a registration model of the dynamic lung field of CXR images based on AC-RegNet and static CXR images is urgently developed to register these dynamic lung fields for clinical quantitative analysis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This paper proposes a fully automatic three-stage registration pipeline for the dynamic lung field of CXR images. First, the dynamic lung field mask images are generated from a pre-trained standard lung field segmentation model with the dynamic CXR images. Then, a lung field abstraction model is designed to generate the dynamic lung field images based on the dynamic lung field mask images and their corresponding CXR images. Finally, we propose a three-step registration training method to train the AC-RegNet, obtaining the registration network of the dynamic lung field images (AC-RegNet_V3).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed AC-RegNet_V3 with the four basic segmentation networks achieve the mean dice similarity coefficient (DSC) of 0.991, 0.993, 0.993, and 0.993, mean Hausdorff distance (HD) of 12.512, 12.813, 12.449, and 13.661, mean average symmetric surface distance (ASSD) of 0.654, 0.550, 0.572, and 0.564, and mean squared distance (MSD) of 559.098, 577.797, 548.189, and 559.652, respectively. Besides, compared to the dynamic CXR images, the mean DSC of these four basic segmentation networks with AC-RegNet has been significantly improved by 7.2, 7.4, 7.4, and 7.4% (<jats:italic>p<\/jats:italic>-value\u202f&amp;lt;\u202f0.0001). Meanwhile, the mean HD has been significantly improved by 8.994, 8.693, 9.057, and 7.845 (<jats:italic>p<\/jats:italic>-value\u202f&amp;lt;\u202f0.0001). Similarly, the mean ASSD has significantly improved by 4.576, 4.680, 4.658, and 4.658 (<jats:italic>p<\/jats:italic>-value\u202f&amp;lt;\u202f0.0001). Last, the mean MSD has significantly improved by 508.936, 519.776, 517.904, and 520.626 (<jats:italic>p<\/jats:italic>-value\u202f&amp;lt;\u202f0.0001).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our proposed three-stage registration pipeline has demonstrated its effectiveness in dynamic lung field registration. Therefore, it could become a powerful tool for dynamic lung field analysis in clinical practice, such as pulmonary airflow detection and air trapping location.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1466643","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T08:09:27Z","timestamp":1741766967000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Three-stage registration pipeline for dynamic lung field of chest X-ray images based on convolutional neural networks"],"prefix":"10.3389","volume":"8","author":[{"given":"Yingjian","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingwei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziran","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengcheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanglei","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref2","first-page":"9252","article-title":"An unsupervised learning model for deformable medical image registration","author":"Balakrishnan","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"7552","DOI":"10.3390\/s21227552","article-title":"A comparative study on the voxel values in alveolar bones acquired by MDCT and newly developed dental dual-energy CBCT","volume":"21","author":"Chang","year":"2021","journal-title":"Sensors"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"842404","DOI":"10.3389\/fnint.2022.842404","article-title":"Quantitative evaluation of diaphragmatic motion during forced breathing in chronic obstructive pulmonary disease patients using dynamic chest radiography","volume":"16","author":"Chen","year":"2022","journal-title":"Front. Integr. Neurosci."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/1754-9485.13261","article-title":"A review of medical image data augmentation techniques for deep learning applications","volume":"65","author":"Chlap","year":"2021","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s11517-024-03016-z","article-title":"COPD stage detection: leveraging the auto-metric graph neural network with inspiratory and expiratory chest CT images","volume":"62","author":"Deng","year":"2024","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"146","DOI":"10.3233\/SHTI230835","article-title":"Exploring the effectiveness of multi-objective training for organ substructure segmentation in medical imaging","volume":"308","author":"Duan","year":"2023","journal-title":"Stud. Health Technol. Inform."},{"key":"ref8","first-page":"294","article-title":"On the adaptability of unsupervised CNN-based deformable image registration to unseen image domains","author":"Ferrante","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1664","DOI":"10.3390\/diagnostics12071664","article-title":"Novel survival features generated by clinical text information and radiomics features may improve the prediction of ischemic stroke outcome","volume":"12","author":"Guo","year":"2022","journal-title":"Diagnostics"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"889090","DOI":"10.3389\/fneur.2022.889090","article-title":"Radiomics features of DSC-PWI in time dimension may provide a new chance to identify ischemic stroke","volume":"13","author":"Guo","year":"2022","journal-title":"Front. Neurol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"5364","DOI":"10.3390\/jcm11185364","article-title":"A focus on the role of DSC-PWI dynamic radiomics features in diagnosis and outcome prediction of ischemic stroke","volume":"11","author":"Guo","year":"2022","journal-title":"J. Clin. Med."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.3390\/life12111847","article-title":"The combination of whole-brain features and local-lesion features in DSC-PWI may improve ischemic stroke outcome prediction","volume":"12","author":"Guo","year":"2022","journal-title":"Life"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"13","DOI":"10.33022\/ijcs.v13i1.3700","article-title":"Lung segmentation from chest X-ray images using Deeplabv3plus-based CNN model","volume":"13","author":"Hasan","year":"2024","journal-title":"Indones. J. Comput. Sci."},{"key":"ref14","first-page":"341","article-title":"Early clinical use of the X-ray","volume":"127","author":"Howell","year":"2016","journal-title":"Trans. Am. Clin. Climatol. Assoc."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"109573","DOI":"10.1016\/j.engappai.2024.109573","article-title":"An end-to-end deep convolutional neural network-based data-driven fusion framework for identification of human induced pluripotent stem cell-derived endothelial cells in photomicrographs","volume":"139","author":"Iqbal","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"101843","DOI":"10.1016\/j.compmedimag.2020.101843","article-title":"Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images","volume":"88","author":"Iqbal","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref17","first-page":"28","article-title":"Spatial transformer networks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"988","DOI":"10.3390\/jpm12060988","article-title":"CardioNet: automatic semantic segmentation to calculate the cardiothoracic ratio for cardiomegaly and other chest diseases","volume":"12","author":"Jafar","year":"2022","journal-title":"J. Pers. Med."},{"key":"ref19","first-page":"225","article-title":"ResUNet++: An advanced architecture for medical image segmentation","author":"Jha","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"108150","DOI":"10.1016\/j.compbiomed.2024.108150","article-title":"Multi-scale simulations of pulmonary airflow based on a coupled 3D-1D-0D model","volume":"171","author":"Jiang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11082-024-06507-3","article-title":"Segmentation of lung on P-A CXR images based on CXR-auto encoder segmentation with MRF","volume":"56","author":"Kiruthika","year":"2024","journal-title":"Opt. Quant. Electron."},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-32778-1_13","article-title":"Cycle-consistent training for reducing negative jacobian determinant in deep registration networks","author":"Kuang","year":"2019"},{"key":"ref23","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.neunet.2020.01.023","article-title":"Learning deformable registration of medical images with anatomical constraints","volume":"124","author":"Mansilla","year":"2020","journal-title":"Neural Netw."},{"key":"ref25","first-page":"134","article-title":"SimpleElastix: a user-friendly, multi-lingual library for medical image registration","author":"Marstal","year":"2016"},{"key":"ref26","first-page":"21","article-title":"Medical image registration and its application in retinal images: a review","volume-title":"Vis. Comput. Ind. Biomed. Art","author":"Nie","year":"2024"},{"key":"ref27","article-title":"Image registration using rigid registration and maximization of mutual information","author":"Rahunathan","year":"2005"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger","year":"2015"},{"key":"ref29","volume-title":"Modeling, simulation, and visualization of 3d lung dynamics","author":"Santhanam","year":"2006"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e496","DOI":"10.1016\/S2589-7500(21)00106-0","article-title":"Effect of a comprehensive deep-learning model on the accuracy of chest x-ray interpretation by radiologists: a retrospective, multireader multicase study","volume":"3","author":"Seah","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref31","first-page":"3371","article-title":"Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e28724","DOI":"10.1016\/j.heliyon.2024.e28724","article-title":"Acute exacerbation prediction of COPD based on auto-metric graph neural network with inspiratory and expiratory chest CT images","volume":"10","author":"Wang","year":"2024","journal-title":"Heliyon"},{"key":"ref33","first-page":"302","article-title":"AttU-net: Attention U-net for brain tumor segmentation","author":"Wang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"107434","DOI":"10.1016\/j.compbiomed.2023.107434","article-title":"Deep learning-based lung image registration: a review","volume":"165","author":"Xiao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1394879","DOI":"10.3389\/fneur.2024.1394879","article-title":"Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network","volume":"15","author":"Yang","year":"2024","journal-title":"Front. Neurol."},{"key":"ref36","first-page":"1","article-title":"A method of abstracting single pulmonary lobe from computed tomography pulmonary images for locating COPD","author":"Yang","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/7511905","article-title":"GCP-net: a gating context-aware pooling network for cervical cell nuclei segmentation","volume":"2022","author":"Yang","year":"2022","journal-title":"Mob. Inf. Syst."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"4193","DOI":"10.3934\/mbe.2021210","article-title":"Lung parenchyma parameters measure of rats from pulmonary window computed tomography images based on ResU-net model for medical respiratory researches","volume":"18","author":"Yang","year":"2021","journal-title":"Math. Biosci. Eng."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"7826","DOI":"10.3934\/mbe.2022366","article-title":"Lung radiomics features for characterizing and classifying COPD stage based on feature combination strategy and multi-layer perceptron classifier","volume":"19","author":"Yang","year":"2022","journal-title":"Math. Biosci. Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"6912","DOI":"10.3389\/fphys.2024.1416912","article-title":"Automatic cardiothoracic ratio calculation based on lung fields abstracted from chest X-ray images without heart segmentation","volume":"15","author":"Yang","year":"2024","journal-title":"Front. Physiol."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.3233\/XST-240108","article-title":"Hemi-diaphragm detection of chest X-ray images based on convolutional neural network and graphics","volume":"32","author":"Yang","year":"2024","journal-title":"J. Xray Sci. Technol."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"155016","DOI":"10.1088\/1361-6560\/ace6f0","article-title":"Predicting dice similarity coefficient of deformably registered contours using Siamese neural network","volume":"68","author":"Yeap","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1363930","DOI":"10.3389\/fnins.2024.1363930","article-title":"Adaptive feature medical segmentation network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging","volume":"18","author":"Zaman","year":"2024","journal-title":"Front. Neurosci."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.3390\/diagnostics13132161","article-title":"Tubular structure segmentation via multi-scale reverse attention sparse convolution","volume":"13","author":"Zeng","year":"2023","journal-title":"Diagnostics"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"104216","DOI":"10.1016\/j.resp.2024.104216","article-title":"Longitudinal changes in respiratory reactance in patients with COPD: associations with longitudinal change in air-trap**, exacerbations, and mortality","volume":"322","author":"Zhang","year":"2024","journal-title":"Respir. Physiol. Neurobiol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1466643\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T08:09:30Z","timestamp":1741766970000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1466643\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,12]]},"references-count":45,"alternative-id":["10.3389\/frai.2025.1466643"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1466643","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,12]]},"article-number":"1466643"}}