{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T19:43:55Z","timestamp":1792093435733,"version":"4.4.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"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. Bioeng. Biotechnol."],"abstract":"<jats:p><jats:bold>Background:<\/jats:bold> Osteoporosis is a common degenerative disease with high incidence among aging populations. However, in regular radiographic diagnostics, asymptomatic osteoporosis is often overlooked and does not include tests for bone mineral density or bone trabecular condition. Therefore, we proposed a highly generalized classifier for osteoporosis radiography based on the multiscale fractal, lacunarity, and entropy distributions.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> We collected a total of 104 radiographs (92 for training and 12 for testing) of lumbar spine L4 and divided them into three groups (normal, osteopenia, and osteoporosis). In parallel, 174 radiographs (116 for training and 58 for testing) of calcaneus from health and osteoporotic fracture groups were collected. The texture feature data of all the radiographs were pulled out and analyzed. The Davies\u2013Bouldin index was applied to optimize hyperparameters of feature counting. Neighborhood component analysis was performed to reduce feature dimension and increase generalization. A support vector machine classifier was trained with only the most effective six features for each binary classification scenario. The accuracy and sensitivity performance were estimated by calculating the area under the curve.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> Interpretable feature trends of osteoporotic pathological changes were depicted. On the spine test dataset, the accuracy and sensitivity of binary classifiers were 0.851 (95% CI: 0.730\u20130.922), 0.813 (95% CI: 0.718\u20130.878), and 0.936 (95% CI: 0.826\u20131) for osteoporosis diagnosis; 0.721 (95% CI: 0.578\u20130.824), 0.675 (95% CI: 0.563\u20130.772), and 0.774 (95% CI: 0.635\u20130.878) for osteopenia diagnosis; and 0.935 (95% CI: 0.830\u20130.968), 0.928 (95% CI: 0.863\u20130.963), and 0.910 (95% CI: 0.746\u20131) for osteoporosis diagnosis from osteopenia. On the calcaneus test dataset, they were 0.767 (95% CI: 0.629\u20130.879), 0.672 (95% CI: 0.545\u20130.793), and 0.790 (95% CI: 0.621\u20130.923) for osteoporosis diagnosis.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> This method showed the capacity of resisting disturbance on lateral spine radiographs and high generalization on the calcaneus dataset. Pixel-wise texture features not only helped to understand osteoporosis on radiographs better but also shed new light on computer-aided osteopenia and osteoporosis diagnosis.<\/jats:p>","DOI":"10.3389\/fbioe.2023.1054991","type":"journal-article","created":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T05:49:32Z","timestamp":1684475372000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A highly generalized classifier for osteoporosis radiography based on multiscale fractal, lacunarity, and entropy distributions"],"prefix":"10.3389","volume":"11","author":[{"given":"Jingnan","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng Lei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachid","family":"Jennane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songtao","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kerong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsung-Yuan","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,5,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s11606-015-3349-8","article-title":"Underuse and overuse of osteoporosis screening in a regional health system: A retrospective cohort study","volume":"30","author":"Amarnath","year":"2015","journal-title":"J. Gen. Intern. Med."},{"key":"B2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.patcog.2012.07.021","article-title":"An extensive comparative study of cluster validity indices","volume":"46","author":"Arbelaitz","year":"2013","journal-title":"Pattern Recognit."},{"key":"B3","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s00198-017-4328-1","article-title":"Early diagnosis of osteoporosis using radiogrammetry and texture analysis from hand and wrist radiographs in Indian population","volume":"29","author":"Areeckal","year":"","journal-title":"Osteoporos. Int."},{"key":"B4","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1109\/RBME.2018.2852620","article-title":"Current and emerging diagnostic imaging-based techniques for assessment of osteoporosis and fracture risk","volume":"12","author":"Areeckal","year":"","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"B5","doi-asserted-by":"publisher","first-page":"6936","DOI":"10.1109\/TIT.2017.2749310","article-title":"Bounds on variance for unimodal distributions","volume":"63","author":"Chung","year":"2017","journal-title":"IEEE Trans. Inf. Theory"},{"key":"B6","first-page":"665","article-title":"An efficient box-couting fractal dimension approach for experimental image variation characterization","author":"Conci","year":"1996","journal-title":"Proceedings"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2359","DOI":"10.1007\/s00198-014-2794-2","article-title":"Clinician\u2019s guide to prevention and treatment of osteoporosis","volume":"25","author":"Cosman","year":"2014","journal-title":"Osteoporos. Int."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.3390\/e17031197","article-title":"Generalized multiscale entropy analysis: Application to quantifying the complex volatility of human heartbeat time series","volume":"17","author":"Costa","year":"2015","journal-title":"Entropy"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1515\/9783112576205-025","article-title":"Computing fractal dimension of image segments","volume-title":"Proceedings of the 3rd international conference of computer analysis of images and patterns (CAIP\u201989)","author":"Creutzberg","year":"1989"},{"key":"B10","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/tpami.1979.4766909","article-title":"A cluster separation measure","author":"Davies","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B11","doi-asserted-by":"publisher","first-page":"5269","DOI":"10.1364\/boe.9.005269","article-title":"Rapid quantification of mitochondrial fractal dimension in individual cells","volume":"9","author":"Enkins","year":"2018","journal-title":"Biomed. Opt. Express"},{"key":"B12","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.mcna.2015.01.010","article-title":"Osteoporosis: Screening, prevention, and management","volume":"99","author":"Golob","year":"2015","journal-title":"Med. Clin. North Am."},{"key":"B13","doi-asserted-by":"publisher","first-page":"976","DOI":"10.14336\/AD.2018.0124","article-title":"Age-related changes in femoral head trabecular microarchitecture","volume":"9","author":"Greenwood","year":"2018","journal-title":"Aging Dis."},{"key":"B14","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"12","author":"Hansen","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B15","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1016\/j.bspc.2013.06.009","article-title":"Piecewise Whittle estimator for trabecular bone radiograph characterization","volume":"8","author":"Harrar","year":"2013","journal-title":"Biomed. Signal Process. Control"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1109\/JBHI.2016.2619420","article-title":"Fractional brownian motion and rao geodesic distance for bone X-ray image characterization","volume":"21","author":"Hassouni","year":"2017","journal-title":"IEEE J. Biomed. Heal. Inf."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.1016\/j.physleta.2016.02.029","article-title":"Multivariate refined composite multiscale entropy analysis","volume":"380","author":"Humeau-Heurtier","year":"2016","journal-title":"Phys. Lett. A"},{"key":"B18","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.cmpb.2019.03.011","article-title":"Computer-aided osteoporosis detection from DXA imaging","volume":"173","author":"Hussain","year":"2019","journal-title":"Comput. Methods Programs Biomed."},{"key":"B19","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/42.925297","article-title":"Fractal analysis of bone X-ray tomographic microscopy projections","volume":"20","author":"Jennane","year":"2001","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1007\/s00198-006-0172-4","article-title":"An estimate of the worldwide prevalence and disability associated with osteoporotic fractures","volume":"17","author":"Johnell","year":"2006","journal-title":"Osteoporos. Int."},{"key":"B21","article-title":"Reviewing lacunarity analysis and classification of microglia in neuroscience","volume-title":"Proceedings of the 8th European conference on mathematical and theoretical biology","author":"Karperien","year":"2011"},{"key":"B22","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s00256-019-03342-6","article-title":"The exploration of feature extraction and machine learning for predicting bone density from simple spine X-ray images in a Korean population","volume":"49","author":"Lee","year":"2020","journal-title":"Skelet. Radiol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.1016\/j.patcog.2009.03.001","article-title":"An improved box-counting method for image fractal dimension estimation","volume":"42","author":"Li","year":"2009","journal-title":"Pattern Recognit."},{"key":"B24","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1016\/j.media.2009.05.003","article-title":"Fractal and multifractal analysis: A review","volume":"13","author":"Lopes","year":"2009","journal-title":"Med. Image Anal."},{"key":"B25","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1007\/978-3-0348-8501-0_2","article-title":"A Fractal\u2019s Lacunarity, and how it can be Tuned and Measured","volume-title":"Fractals in biology and medicine","author":"Mandelbrot","year":"1994"},{"key":"B26","unstructured":"Peoples health. Network2018"},{"key":"B27","article-title":"Bone health and osteoporosis: A report of the Surgeon general","volume-title":"US health and human services","year":"2004"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2150095","DOI":"10.1142\/S0218348X2150095X","article-title":"Fractal analysis as a method for feature extraction in detecting osteoporotic bone destruction","volume":"29","author":"Omiotek","year":"2021","journal-title":"Fractals"},{"key":"B29","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.bspc.2016.10.009","article-title":"Trabecular bone characterization using circular parametric models","volume":"33","author":"Oulhaj","year":"2017","journal-title":"Biomed. Signal Process. Control"},{"key":"B30","unstructured":"Orleans university2022"},{"key":"B31","doi-asserted-by":"publisher","first-page":"103559","DOI":"10.1016\/j.compbiomed.2019.103559","article-title":"Multifractal-based lacunarity analysis of trabecular bone in radiography","volume":"116","author":"Palanivel","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"B32","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.1109\/TENCON.2019.8929524","article-title":"Trabecular bone texture characterization using regularization dimension and box-counting dimension","volume-title":"TENCON 2019-2019 IEEE region 10 conference (TENCON)","author":"Palanivel","year":"2019"},{"key":"B33","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TPAMI.1984.4767557","article-title":"Multiple resolution texture analysis and classification","volume":"6","author":"Peleg","year":"1984","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B34","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.eswa.2018.06.031","article-title":"Classification of focal and non-focal EEG signals using neighborhood component analysis and machine learning algorithms","volume":"113","author":"Raghu","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"B35","unstructured":"Orleans university2022"},{"key":"B36","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/0004-3702(87)90062-2","article-title":"A theory of diagnosis from first principles","volume":"32","author":"Reiter","year":"1987","journal-title":"Artif. Intell."},{"key":"B37","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1109\/21.259692","article-title":"An efficient differential box-counting approach to compute fractal dimension of image","volume":"24","author":"Sarkar","year":"1994","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"B38","doi-asserted-by":"publisher","first-page":"107","DOI":"10.3390\/bioengineering5040107","article-title":"Detection of osteoporosis from percussion responses using an electronic stethoscope and machine learning","volume":"5","author":"Scanlan","year":"2018","journal-title":"Bioengineering"},{"key":"B39","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/0895-7177(94)90188-0","article-title":"Life as a manifestation of the second law of thermodynamics","volume":"19","author":"Schneider","year":"1994","journal-title":"Math. Comput. Model."},{"key":"B40","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/584091.584093","article-title":"A mathematical theory of communication","volume":"5","author":"Shannon","year":"2001","journal-title":"ACM Sigmob. Mob. Comput. Commun. Rev."},{"key":"B41","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1002\/jbmr.4292","article-title":"Machine learning solutions for osteoporosis\u2014a review","volume":"36","author":"Smets","year":"2021","journal-title":"J. Bone Min. Res."},{"key":"B42","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/S0165-0270(96)00080-5","article-title":"Fractal methods and results in cellular morphology - dimensions, lacunarity and multifractals","volume":"69","author":"Smith","year":"1996","journal-title":"J. Neurosci. Methods"},{"key":"B43","doi-asserted-by":"publisher","first-page":"960","DOI":"10.14336\/AD.2021.1201","article-title":"COVID-19 pandemic and osteoporosis in elderly patients","volume":"13","author":"Tang","year":"2022","journal-title":"Aging Dis."},{"key":"B44","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.jhsa.2019.11.019","article-title":"Convolutional neural network for second metacarpal radiographic osteoporosis screening","volume":"45","author":"Tecle","year":"2020","journal-title":"J. Hand Surg. Am."},{"key":"B45","first-page":"92","article-title":"Osteoporosis: A review of treatment options","volume":"43","author":"Tu","year":"2018","journal-title":"P T"},{"key":"B46","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-3-319-21852-6_3","article-title":"On the uniform convergence of relative frequencies of events to their probabilities","volume-title":"Measures of complexity","author":"Vapnik","year":"2015"},{"key":"B47","volume-title":"The nature of statistical learning theory","author":"Vapnik","year":"1999"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2787","DOI":"10.1210\/jc.2004-1568","article-title":"Hip fracture in women without osteoporosis","volume":"90","author":"Wainwright","year":"2005","journal-title":"J. Clin. Endocrinol. \\& Metab."},{"key":"B49","doi-asserted-by":"publisher","first-page":"100295","DOI":"10.1016\/j.bonr.2020.100295","article-title":"Prediction of trabecular bone architectural features by deep learning models using simulated DXA images","volume":"13","author":"Xiao","year":"2020","journal-title":"Bone Rep."},{"key":"B50","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.3390\/biom10111534","article-title":"Deep learning for osteoporosis classification using hip radiographs and patient clinical covariates","volume":"10","author":"Yamamoto","year":"2020","journal-title":"Biomolecules"},{"key":"B51","doi-asserted-by":"publisher","first-page":"161","DOI":"10.4304\/jcp.7.1.161-168","article-title":"Neighborhood component feature selection for high-dimensional data","volume":"7","author":"Yang","year":"2012","journal-title":"J. Comput."},{"key":"B52","volume-title":"Application of covariance matrices and wavelet marginals","author":"Yger","year":"2014"},{"key":"B53","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":"B54","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/EMBC.2016.7590879","article-title":"Bone texture characterization for osteoporosis diagnosis using digital radiography","volume":"2016","author":"Zheng","year":"2016","journal-title":"Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1054991\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T05:49:44Z","timestamp":1684475384000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1054991\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":54,"alternative-id":["10.3389\/fbioe.2023.1054991"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2023.1054991","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,19]]},"article-number":"1054991"}}