{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T09:29:02Z","timestamp":1789550942054,"version":"build-2803163510"},"reference-count":66,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-014"],"award-info":[{"award-number":["GXXT-2022-014"]}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"crossref","award":["2108085MF211"],"award-info":[{"award-number":["2108085MF211"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376005"],"award-info":[{"award-number":["62376005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2024,2,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Chest x-ray image representation and learning is an important problem in computer-aided diagnostic area. Existing methods usually adopt CNN or Transformers for feature representation learning and focus on learning effective representations for chest x-ray images. Although good performance can be obtained, however, these works are still limited mainly due to the ignorance of mining the correlations of channels and pay little attention on the local context-aware feature representation of chest x-ray image.\n                    <jats:italic>Approach<\/jats:italic>\n                    . To address these problems, in this paper, we propose a novel spatial-channel high-order attention model (SCHA) for chest x-ray image representation and diagnosis. The proposed network architecture mainly contains three modules, i.e. CEBN, SHAM and CHAM. To be specific, firstly, we introduce a context-enhanced backbone network by employing multi-head self-attention to extract initial features for the input chest x-ray images. Then, we develop a novel SCHA which contains both spatial and channel high-order attention learning branches. For the spatial branch, we develop a novel local biased self-attention mechanism which can capture both local and long-range global dependences of positions to learn rich context-aware representation. For the channel branch, we employ Brownian Distance Covariance to encode the correlation information of channels and regard it as the image representation. Finally, the two learning branches are integrated together for the final multi-label diagnosis classification and prediction.\n                    <jats:italic>Main results<\/jats:italic>\n                    . Experiments on the commonly used datasets including ChestX-ray14 and CheXpert demonstrate that our proposed SCHA approach can obtain better performance when comparing many related approaches.\n                    <jats:italic>Significance<\/jats:italic>\n                    . This study obtains a more discriminative method for chest x-ray classification and provides a technique for computer-aided diagnosis.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ad2014","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T02:07:27Z","timestamp":1707790047000},"page":"045026","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Chest x-ray diagnosis via spatial-channel high-order attention representation learning"],"prefix":"10.1088","volume":"69","author":[{"given":"Xinyue","family":"Gao","sequence":"first","affiliation":[{"name":"Anhui University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":true,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Anhui University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixi","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Huang","sequence":"additional","affiliation":[{"name":"Anhui University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengzheng","family":"Tu","sequence":"additional","affiliation":[{"name":"Anhui University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,2,13]]},"reference":[{"key":"pmbad2014bib1","first-page":"804","type":"other","article-title":"Anaxnet: anatomy aware multi-label finding classification in chest x-ray","author":"Agu","year":"2021"},{"key":"pmbad2014bib2","first-page":"1961","type":"other","article-title":"Mrscatt: a spatio-channel attention-guided network for mars rover image classification","author":"Chakravarthy","year":"2021"},{"key":"pmbad2014bib3","doi-asserted-by":"publisher","first-page":"2292","DOI":"10.1109\/JBHI.2020.2967084","type":"journal-article","article-title":"Label co-occurrence learning with graph convolutional networks for multi-label chest x-ray image classification","volume":"24","author":"Chen","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbad2014bib4","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.18653\/v1\/2020.emnlp-main.112","type":"conference-proceedings","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2022"},{"key":"pmbad2014bib5","first-page":"T1","type":"journal-article","article-title":"Keras: Deep learning library for theano and tensorflow","volume":"7","author":"Chollet","year":"2015"},{"key":"pmbad2014bib6","first-page":"248","type":"other","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"pmbad2014bib7","article-title":"An image is worth 16 x 16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"pmbad2014bib8","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/JBHI.2021.3094311","type":"journal-article","article-title":"Cervical cancer diagnostics healthcare system using hybrid object detection adversarial networks","volume":"26","author":"Elakkiya","year":"2021","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbad2014bib9","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.1109\/CVPR.2019.00326","type":"conference-proceedings","article-title":"Dual attention network for scene segmentation,","author":"Fu","year":"2019"},{"key":"pmbad2014bib10","first-page":"37","type":"journal-article","article-title":"Long short-term memory, supervised sequence labelling with recurrent neural networks","volume":"385","author":"Graves","year":"2012","journal-title":"Studies in Computational Intelligence"},{"key":"pmbad2014bib11","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.patrec.2018.10.027","type":"journal-article","article-title":"Multi-label chest x-ray image classification via category-wise residual attention learning","volume":"130","author":"Guan","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"pmbad2014bib12","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.patrec.2018.10.027","type":"journal-article","article-title":"Multi-label chest x-ray image classification via category-wise residual attention learning","volume":"130","author":"Guan","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"pmbad2014bib13","doi-asserted-by":"publisher","first-page":"2476","DOI":"10.1109\/TIP.2021.3052711","type":"journal-article","article-title":"Discriminative feature learning for thorax disease classification in chest x-ray images","volume":"30","author":"Guan","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"pmbad2014bib14","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.neunet.2021.01.005","type":"journal-article","article-title":"Improved deep cnns based on nonlinear hybrid attention module for image classification","volume":"140","author":"Guo","year":"2021","journal-title":"Neural Netw.: Off. J. Int. Neural Netw. Soc."},{"key":"pmbad2014bib15","doi-asserted-by":"crossref","first-page":"750","DOI":"10.1109\/TMI.2022.3217218","type":"journal-article","article-title":"Radiomics-guided global-local transformer for weakly supervised pathology localization in chest x-rays","volume":"42","author":"Han","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad2014bib16","first-page":"4700","type":"other","article-title":"Densely connected convolutional networks,","author":"Huang","year":"2017"},{"key":"pmbad2014bib17","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1609\/aaai.v33i01.3301590","type":"conference-proceedings","article-title":"Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"vol 33","author":"Irvin","year":"2019"},{"key":"pmbad2014bib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103406","type":"journal-article","article-title":"Eff2net: an efficient channel attention-based convolutional neural network for skin disease classification","volume":"73","author":"Karthik","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbad2014bib19","first-page":"15719","type":"other","article-title":"Xprotonet: diagnosis in chest radiography with global and local explanations","author":"Kim","year":"2021"},{"key":"pmbad2014bib20","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","type":"preprint"},{"key":"pmbad2014bib21","first-page":"546","type":"other","article-title":"Boosted cascaded convnets for multilabel classification of thoracic diseases in chest radiographs","author":"Kumar","year":"2018"},{"key":"pmbad2014bib22","first-page":"533","type":"other","article-title":"Robust lane detection via expanded self attention","author":"Lee","year":"2022"},{"key":"pmbad2014bib23","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.1109\/ACCESS.2021.3057373","type":"journal-article","article-title":"Scepa new image dimensional emotion recognition model based on spatial and channel-wise attention mechanisms","volume":"290","author":"Li","year":"2021","journal-title":"IEEE Access"},{"key":"pmbad2014bib24","first-page":"6153","type":"other","article-title":"Scconv: spatial and channel reconstruction convolution for feature redundancy","author":"Li","year":"2023"},{"key":"pmbad2014bib25","first-page":"8290","type":"other","article-title":"Thoracic disease identification and localization with limited supervision","author":"Li","year":"2018"},{"key":"pmbad2014bib26","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1109\/TMI.2023.3247814","type":"journal-article","article-title":"The lighter the better: rethinking transformers in medical image segmentation through adaptive pruning","volume":"42","author":"Lin","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad2014bib27","first-page":"10632","type":"other","article-title":"Align, attend and locate: chest x-ray diagnosis via contrast induced attention network with limited supervision","author":"Liu","year":"2019"},{"key":"pmbad2014bib28","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1109\/TMI.2020.2995518","type":"journal-article","article-title":"Semi-supervised medical image classification with relation-driven self-ensembling model","volume":"39","author":"Liu","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad2014bib29","doi-asserted-by":"publisher","first-page":"4409","DOI":"10.1109\/JBHI.2023.3281466","type":"journal-article","article-title":"Multi-label local to global learning: a novel learning paradigm for chest x-ray abnormality classification","volume":"27","author":"Liu","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbad2014bib30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-32226-7_81","type":"other","article-title":"Multi-label thoracic disease image classification with cross-attention networks","author":"Ma","year":"2019"},{"key":"pmbad2014bib31","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.1109\/TMI.2022.3153322","type":"journal-article","article-title":"Imagegcn: multi-relational image graph convolutional networks for disease identification with chest x-rays","volume":"41","author":"Mao","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad2014bib32","first-page":"1209","type":"other","article-title":"Deep generative classifiers for thoracic disease diagnosis with chest x-ray images","author":"Mao","year":"2018"},{"key":"pmbad2014bib33","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.1041510","type":"journal-article","article-title":"Densenet weed recognition model combining local variance preprocessing and attention mechanism","volume":"13","author":"Mu","year":"2023","journal-title":"Front. Plant Sci."},{"key":"pmbad2014bib34","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac5d74","type":"journal-article","article-title":"H-segnet: hybrid segmentation network for lung segmentation in chest radiographs using mask region-based convolutional neural network and adaptive closed polyline searching method","volume":"67","author":"Peng","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmbad2014bib35","article-title":"Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning","author":"Rajpurkar","year":"2017","type":"preprint"},{"key":"pmbad2014bib36","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1214\/09-AOAS312F","type":"journal-article","article-title":"Discussion of: brownian distance covariance","volume":"3","author":"R\u00e9millard","year":"2009","journal-title":"Ann. Appl. Stat."},{"key":"pmbad2014bib37","first-page":"249","type":"other","article-title":"Glass: global to local attention for scene-text spotting","author":"Ronen","year":"2022"},{"key":"pmbad2014bib38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","type":"preprint"},{"key":"pmbad2014bib39","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/JBHI.2020.2986926","type":"journal-article","article-title":"Multi-scale self-guided attention for medical image segmentation","volume":"25","author":"Sinha","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbad2014bib40","doi-asserted-by":"publisher","first-page":"16514","DOI":"10.1109\/CVPR46437.2021.01625","type":"conference-proceedings","article-title":"Bottleneck Transformers for Visual Recognition","author":"Srinivas","year":"2021"},{"key":"pmbad2014bib41","first-page":"240","type":"other","article-title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations","author":"Sudre","year":"2017"},{"key":"pmbad2014bib42","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ac6f40","type":"journal-article","article-title":"A deep residual inception network with channel attention modules for multi-label cardiac abnormality detection from reduced-lead ecg","volume":"43","author":"Srivastava","year":"2022","journal-title":"Physiol. Meas."},{"key":"pmbad2014bib43","doi-asserted-by":"publisher","first-page":"2769","DOI":"10.1214\/009053607000000505","type":"journal-article","article-title":"Measuring and testing dependence by correlation of distances","volume":"35","author":"Sz\u00e9kely","year":"2007","journal-title":"Ann. Statist."},{"key":"pmbad2014bib44","first-page":"249","type":"other","article-title":"Attention-guided curriculum learning for weakly supervised classification and localization of thoracic diseases on chest radiographs","author":"Tang","year":"2018"},{"key":"pmbad2014bib45","article-title":"Swinchex: multi-label classification on chest x-ray images with transformers","author":"Taslimi","year":"2022","type":"preprint"},{"key":"pmbad2014bib46","first-page":"36","type":"other","article-title":"Medical transformer: gated axial-attention for medical image segmentation","author":"Valanarasu","year":"2021"},{"key":"pmbad2014bib47","first-page":"6000","type":"journal-article","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbad2014bib48","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acc000","type":"journal-article","article-title":"Ctformer: convolution-free token2token dilated vision transformer for low-dose ct denoising","volume":"68","author":"Wang","year":"2023a","journal-title":"Phys. Med. Biol."},{"key":"pmbad2014bib49","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v37i2.25346","type":"preprint","article-title":"Dual memory aggregation network for event-based object detection with learnable representation","author":"Wang","year":"2023b"},{"key":"pmbad2014bib50","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101846","type":"journal-article","article-title":"Triple attention learning for classification of 14 thoracic diseases using chest radiography","volume":"67","author":"Wang","year":"2021a","journal-title":"Med. Image Anal."},{"key":"pmbad2014bib51","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1007\/s10489-021-02496-y","type":"journal-article","article-title":"Deca: a novel multi-scale efficient channel attention module for object detection in real-life fire images","volume":"52","author":"Wang","year":"2021b","journal-title":"Appl. Intell."},{"key":"pmbad2014bib52","first-page":"2097","type":"other","article-title":"Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017"},{"key":"pmbad2014bib53","first-page":"9049","type":"other","article-title":"Tienet: Text-image embedding network for common thorax disease classification and reporting in chest x-rays","author":"Wang","year":"2018"},{"key":"pmbad2014bib54","first-page":"1","type":"other","article-title":"Ct 2: colorization transformer via color tokens","author":"Weng","year":"2022"},{"key":"pmbad2014bib55","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac3dc8","type":"journal-article","article-title":"A vision transformer for emphysema classification using ct images","volume":"66","author":"Wu","year":"2021","journal-title":"Phys. Med. Biol."},{"key":"pmbad2014bib56","first-page":"7972","type":"other","article-title":"Joint distribution matters: deep brownian distance covariance for few-shot classification","author":"Xie","year":"2022"},{"key":"pmbad2014bib57","article-title":"Learning to diagnose from scratch by exploiting dependencies among labels","author":"Yao","year":"2017","type":"preprint"},{"key":"pmbad2014bib58","first-page":"29582","type":"journal-article","article-title":"Class-aware adversarial transformers for medical image segmentation","volume":"35","author":"You","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbad2014bib59","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acdbb4","type":"journal-article","article-title":"A cgan-based tumor segmentation method for breast ultrasound images","author":"You","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbad2014bib60","first-page":"658","type":"other","article-title":"Anatomy-guided weakly-supervised abnormality localization in chest x-rays","author":"Yu","year":"2022"},{"key":"pmbad2014bib61","first-page":"21984","type":"journal-article","article-title":"Few-shot segmentation via cycle-consistent transformer","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbad2014bib62","doi-asserted-by":"publisher","first-page":"4542","DOI":"10.1038\/s41467-023-40260-7","type":"journal-article","article-title":"Knowledge-enhanced visual-language pre-training on chest radiology images","volume":"14","author":"Zhang","year":"2023","journal-title":"Nat. Commun."},{"key":"pmbad2014bib63","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102772","type":"journal-article","article-title":"Triplet attention and dual-pool contrastive learning for clinic-driven multi-label medical image classification","volume":"86","author":"Zhang","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbad2014bib64","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102772","type":"journal-article","article-title":"Triplet attention and dual-pool contrastive learning for clinic-driven multi-label medical image classification","volume":"86","author":"Zhang","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbad2014bib65","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104787","type":"journal-article","article-title":"Ida-net: inheritable deformable attention network of structural mri for alzheimer\u2019s disease diagnosis","volume":"84","author":"Zhao","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbad2014bib66","first-page":"2921","type":"other","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2014","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2014\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2014\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2014\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:26:41Z","timestamp":1778776001000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,13]]},"references-count":66,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2,13]]},"published-print":{"date-parts":[[2024,2,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad2014","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,13]]},"assertion":[{"value":"Chest x-ray diagnosis via spatial-channel high-order attention representation learning","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2023-09-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-02-13","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}