{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:08:42Z","timestamp":1778782122221,"version":"3.51.4"},"reference-count":47,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"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                    Sacroiliitis is an early pathological manifestation of ankylosing spondylitis (AS), and a positive sacroiliitis test on imaging may help clinical practitioners diagnose AS early. Deep learning based automatic diagnosis algorithms can deliver grading findings for sacroiliitis, however, it requires a large amount of data with precise labels to train the model and lacks grading features visualization. In this paper, we aimed to propose a radiomics and deep learning based deep feature visualization positive diagnosis algorithm for sacroiliitis on CT scans. Visualization of grading features can enhance clinical interpretability with visual grading features, which assist doctors in diagnosis and treatment more effectively.\n                    <jats:italic>Approach.<\/jats:italic>\n                    The region of interest (ROI) is identified by segmenting the sacroiliac joint (SIJ) 3D CT images using a combination of the U-net model and certain statistical approaches. Then, in addition to extracting spatial and frequency domain features from ROI according to the radiographic manifestations of sacroiliitis, the radiomics features have also been integrated into the proposed encoder module to obtain a powerful encoder and extract features effectively. Finally, a multi-task learning technique and five-class labels are utilized to help with performing positive tests to reduce discrepancies in the evaluation of several radiologists.\n                    <jats:italic>Main results.<\/jats:italic>\n                    On our private dataset, proposed methods have obtained an accuracy rate of 87.3%, which is 9.8% higher than the baseline and consistent with assessments made by qualified medical professionals.\n                    <jats:italic>Significance.<\/jats:italic>\n                    The results of the ablation experiment and interpreting analysis demonstrated that the proposed methods are applied in automatic CT scan sacroiliitis diagnosis due to their excellently interpretable and portable advantages.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ad2010","type":"journal-article","created":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T17:25:05Z","timestamp":1705598705000},"page":"045034","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Sacroiliitis diagnosis based on interpretable features and multi-task learning"],"prefix":"10.1088","volume":"69","author":[{"given":"Lei","family":"Liu","sequence":"first","affiliation":[{"name":"Shantou University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8851-0630","authenticated-orcid":true,"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shantou University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shantou University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Mei","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Shantou University Medical College"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibin","family":"Huang","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Shantou University Medical College"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"pmbad2010bib1","doi-asserted-by":"publisher","first-page":"317","DOI":"10.18280\/ts.400131","type":"journal-article","article-title":"Automatic detection of knee osteoarthritis disease with the developed cnn, nca and svm based hybrid model","volume":"40","author":"Aslan","year":"2023","journal-title":"Trait. Signal"},{"key":"pmbad2010bib2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.221843","type":"journal-article","article-title":"Combining deep learning and handcrafted radiomics for classification of suspicious lesions on contrast-enhanced mammograms","volume":"307","author":"Beuque","year":"2023","journal-title":"Radiology"},{"key":"pmbad2010bib3","doi-asserted-by":"publisher","first-page":"14132","DOI":"10.1038\/s41598-022-18085-z","type":"journal-article","article-title":"Radiomics and deep learning methods for the prediction of 2 year overall survival in lung1 dataset","volume":"12","author":"Braghetto","year":"2022","journal-title":"Sci. Rep."},{"key":"pmbad2010bib4","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1148\/radiol.212526","type":"journal-article","article-title":"Deep learning detects changes indicative of axial spondyloarthritis at mri of sacroiliac joints","volume":"305","author":"Bressem","year":"2022","journal-title":"Radiology"},{"key":"pmbad2010bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101718","type":"journal-article","article-title":"Early detection of ankylosing spondylitis using texture features and statistical machine learning, and deep learning, with some patient age analysis","volume":"82","author":"Castro-Zunti","year":"2020","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbad2010bib6","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/S0304-405X(00)00046-5","type":"journal-article","article-title":"A study towards a unified approach to the joint estimation of objective and risk neutral measures for the purpose of options valuation","volume":"56","author":"Chernov","year":"2000","journal-title":"J. Financ. Econ."},{"key":"pmbad2010bib7","doi-asserted-by":"publisher","first-page":"1664","DOI":"10.1109\/PROC.1967.5957","type":"journal-article","article-title":"What is the fast fourier transform?","volume":"55","author":"Cochran","year":"1967","journal-title":"Proc. IEEE"},{"key":"pmbad2010bib8","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1007\/s10067-016-3231-z","type":"journal-article","article-title":"Ankylosing spondylitis diagnosis in us patients with back pain: identifying providers involved and factors associated with rheumatology referral delay","volume":"35","author":"Deodhar","year":"2016","journal-title":"Clin. Rheumatol."},{"key":"pmbad2010bib9","article-title":"An image is worth 16 \u00d7 16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"pmbad2010bib10","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-319-68195-5_69","type":"other","article-title":"Pattern recognition of inflammatory sacroiliitis in magnetic resonance imaging","author":"Faleiros","year":"2018"},{"key":"pmbad2010bib11","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s00296-002-0237-4","type":"journal-article","article-title":"Age at disease onset and diagnosis delay in hla-b27 negative versus positive patients with ankylosing spondylitis","volume":"23","author":"Feldtkeller","year":"2003","journal-title":"Rheumatol. Int."},{"key":"pmbad2010bib12","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","type":"journal-article","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"pmbad2010bib13","type":"journal-article","volume":"1","author":"Gornale","year":"2020","journal-title":"Digital knee x-ray images, Mendeley Data"},{"key":"pmbad2010bib14","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac262a","type":"journal-article","article-title":"Automatic segmentation and grading of ankylosing spondylitis on mr images via lightweight hybrid multi-scale convolutional neural network with reinforcement learning","volume":"66","author":"Gou","year":"2021","journal-title":"Phys. Med. Biol."},{"key":"pmbad2010bib15","first-page":"770","type":"other","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbad2010bib16","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.1109\/TMI.2011.2135374","type":"journal-article","article-title":"Frequency-domain optical tomographic imaging of arthritic finger joints","volume":"30","author":"Hielscher","year":"2011","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbad2010bib17","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","type":"preprint"},{"key":"pmbad2010bib18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acc168","type":"journal-article","article-title":"Dadfn: dynamic adaptive deep fusion network based on imaging genomics for prediction recurrence of lung cancer","volume":"68","author":"Jia","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbad2010bib19","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/ICDMW53433.2021.00025","type":"other","article-title":"A multitask learning framework for multimodal sentiment analysis","author":"Jiang","year":"2021"},{"key":"pmbad2010bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109755","type":"journal-article","article-title":"Differentiation of inflammatory from degenerative changes in the sacroiliac joints by machine learning supported texture analysis","volume":"140","author":"Kepp","year":"2021","journal-title":"Eur. J. Radiol."},{"key":"pmbad2010bib21","doi-asserted-by":"publisher","first-page":"066008","DOI":"10.1117\/1.JBO.24.6.066008","type":"journal-article","article-title":"Detecting inflammation in rheumatoid arthritis using fourier transform analysis of dorsal optical transmission images from a pilot study","volume":"24","author":"Lighter","year":"2019","journal-title":"J. Biomed. Opt."},{"key":"pmbad2010bib22","first-page":"2980","type":"other","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"pmbad2010bib23","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1002\/art.1780270401","type":"journal-article","article-title":"Evaluation of diagnostic criteria for ankylosing spondylitis","volume":"27","author":"Linden","year":"1984","journal-title":"Arthritis Rheumatism"},{"key":"pmbad2010bib24","first-page":"868","type":"other","article-title":"Integrate domain knowledge in training cnn for ultrasonography breast cancer diagnosis","author":"Liu","year":"2018"},{"key":"pmbad2010bib25","first-page":"655","type":"other","article-title":"Grading diagnosis of sacroiliitis in ct scans based on radiomics and deep learning","author":"Liu","year":"2022"},{"key":"pmbad2010bib26","first-page":"10012","type":"other","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"pmbad2010bib27","first-page":"5310","type":"other","article-title":"Statistical normalisation of phase-based feature representation for robust speech recognition","author":"Loweimi","year":"2017"},{"key":"pmbad2010bib28","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1002\/art.21445","type":"journal-article","article-title":"Spondyloarthritis research consortium of canada magnetic resonance imaging index for assessment of sacroiliac joint inflammation in ankylosing spondylitis","volume":"53","author":"Maksymowych","year":"2005","journal-title":"Arthritis Care Res."},{"key":"pmbad2010bib29","first-page":"1905","type":"other","article-title":"Intriguing findings of frequency selection for image deblurring","volume":"vol 37","author":"Mao","year":"2023"},{"key":"pmbad2010bib30","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/JBHI.2022.3217685","type":"journal-article","article-title":"A sub-pixel accurate quantification of joint space narrowing progression in rheumatoid arthritis","volume":"27","author":"Ou","year":"2022","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbad2010bib31","first-page":"6034","type":"other","article-title":"Phase-only image based kernel estimation for single image blind deblurring","author":"Pan","year":"2019"},{"key":"pmbad2010bib32","first-page":"10428","type":"other","article-title":"Designing network design spaces","author":"Radosavovic","year":"2020"},{"key":"pmbad2010bib33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263824","type":"other","article-title":"Gfnet: global filter networks for visual recognition","author":"Rao","year":"2023"},{"key":"pmbad2010bib34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","type":"other","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"pmbad2010bib35","type":"book","article-title":"Monte-Carlo simulation, and machine learning","volume":"vol 133","author":"Rubinstein","year":"2004"},{"key":"pmbad2010bib36","first-page":"618","type":"other","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"pmbad2010bib37","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.media.2019.07.007","type":"journal-article","article-title":"Automatic detection and diagnosis of sacroiliitis in ct scans as incidental findings","volume":"57","author":"Shenkman","year":"2019","journal-title":"Med. Image Anal."},{"key":"pmbad2010bib38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","type":"preprint"},{"key":"pmbad2010bib39","first-page":"20730","type":"other","article-title":"Self-supervised pre-training of swin transformers for 3D medical image analysis","author":"Tang","year":"2022"},{"key":"pmbad2010bib40","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1007\/s11548-020-02219-7","type":"journal-article","article-title":"A study of mri-based radiomics biomarkers for sacroiliitis and spondyloarthritis","volume":"15","author":"Ten\u00f3rio","year":"2020","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"pmbad2010bib41","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","type":"journal-article","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Van Griethuysen","year":"2017","journal-title":"Cancer Res."},{"key":"pmbad2010bib42","first-page":"8684","type":"other","article-title":"High-frequency component helps explain the generalization of convolutional neural networks","author":"Wang","year":"2020"},{"key":"pmbad2010bib43","first-page":"1492","type":"other","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"pmbad2010bib44","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac4667","type":"journal-article","article-title":"Deep-learning and radiomics ensemble classifier for false positive reduction in brain metastases segmentation","volume":"67","author":"Yang","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmbad2010bib45","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1093\/rheumatology\/keab542","type":"journal-article","article-title":"A predictive clinical-radiomics nomogram for diagnosing of axial spondyloarthritis using mri and clinical risk factors","volume":"61","author":"Ye","year":"2022","journal-title":"Rheumatology"},{"key":"pmbad2010bib46","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1007\/s10278-023-00858-1","type":"journal-article","article-title":"Automatic image segmentation and grading diagnosis of sacroiliitis associated with as using a deep convolutional neural network on CT images","volume":"36","author":"Zhang","year":"2023","journal-title":"J. Digit. Imaging"},{"key":"pmbad2010bib47","first-page":"10323","type":"other","article-title":"Biformer: vision transformer with bi-level routing attention","author":"Zhu","year":"2023"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:13:58Z","timestamp":1778778838000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ad2010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2,16]]},"published-print":{"date-parts":[[2024,2,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ad2010","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,16]]},"assertion":[{"value":"Sacroiliitis diagnosis based on interpretable features and multi-task 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":"2023-09-08","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":"2024-02-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}