{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:00:52Z","timestamp":1774119652706,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Objective: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis. Materials and methods: We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model\u2019s performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model. Results: Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91\u20130.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8\u20130.84, F1-score = 0.9, PPV = 90%. Conclusions: Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods.<\/jats:p>","DOI":"10.3390\/diagnostics14010061","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T05:43:15Z","timestamp":1703655795000},"page":"61","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI"],"prefix":"10.3390","volume":"14","author":[{"given":"Marta","family":"Forestieri","sequence":"first","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Napolitano","sequence":"additional","affiliation":[{"name":"Medical Physics Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0158-4760","authenticated-orcid":false,"given":"Paolo","family":"Tom\u00e0","sequence":"additional","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Bascetta","sequence":"additional","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Cirillo","sequence":"additional","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuela","family":"Tagliente","sequence":"additional","affiliation":[{"name":"Medical Physics Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2021-0972","authenticated-orcid":false,"given":"Donatella","family":"Fracassi","sequence":"additional","affiliation":[{"name":"Medical Physics Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"D\u2019Angelo","sequence":"additional","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ines","family":"Casazza","sequence":"additional","affiliation":[{"name":"Imaging Department, Bambino Ges\u00f9 Children\u2019s Hospital, IRCCS, 00165 Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.clim.2012.07.012","article-title":"Attenuated TLR4\/MAPK signaling in monocytes from patients with CRMO results in impaired IL-10 expression","volume":"145","author":"Hofmann","year":"2012","journal-title":"Clin. Immunol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/1546-0096-12-30","article-title":"Deregulation of the IL-1\u03b2 axis in chronic recurrent multifocal osteomyelitis","volume":"12","author":"Scianaro","year":"2014","journal-title":"Pediatr. Rheumatol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1007\/s11914-017-0405-9","article-title":"Chronic Recurrent Multifocal Osteomyelitis (CRMO): Presentation, Pathogenesis, and Treatment","volume":"15","author":"Hofmann","year":"2017","journal-title":"Curr. Osteoporos Rep."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1097\/BOR.0000000000000734","article-title":"Comparing children and adults with chronic nonbacterial osteomyelitis","volume":"32","author":"Lenert","year":"2020","journal-title":"Curr. Opin. Rheumatol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/s00247-020-04827-6","article-title":"Chronic nonbacterial osteomyelitis\u2014Clinical and magnetic resonance imaging features","volume":"51","author":"Toma","year":"2021","journal-title":"Pediatr. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"R74","DOI":"10.1186\/ar2992","article-title":"Chronic nonbacterial osteomyelitis in childhood: Prospective follow-up during the first year of anti-inflammatory treatment","volume":"12","author":"Beck","year":"2010","journal-title":"Arthritis Res. Ther."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1111\/j.1651-2227.2011.02205.x","article-title":"Nonbacterial osteitis in children: Data of a German Incidence Surveillance Study: Nonbacterial osteitis in children","volume":"100","author":"Jansson","year":"2011","journal-title":"Acta Paediatr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"100095","DOI":"10.1016\/j.jtauto.2021.100095","article-title":"Chronic nonbacterial osteomyelitis (CNO) and chronic recurrent multifocal osteomyelitis (CRMO)","volume":"4","author":"Zhao","year":"2021","journal-title":"J. Transl. Autoimmun."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"CARRA SVARD CRMO\/CNO workgroup, Oliver, M., Lee, T.C., Halpern-Felsher, B., Murray, E., Schwartz, R., and Zhao, Y. (2018). Disease burden and social impact of pediatric chronic nonbacterial osteomyelitis from the patient and family perspective. Pediatr. Rheumatol., 16, 78.","DOI":"10.1186\/s12969-018-0294-1"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e1190","DOI":"10.1542\/peds.2011-3788","article-title":"Pediatric Chronic Nonbacterial Osteomyelitis","volume":"130","author":"Borzutzky","year":"2012","journal-title":"Pediatrics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1097\/MNM.0000000000000126","article-title":"Chronic recurrent multifocal osteomyelitis: Typical patterns of bone involvement in whole-body bone scintigraphy","volume":"35","author":"Acikgoz","year":"2014","journal-title":"Nucl. Med. Commun."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1002\/art.24402","article-title":"Clinical score for nonbacterial osteitis in children and adults","volume":"60","author":"Jansson","year":"2009","journal-title":"Arthritis Rheum."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/s12969-016-0109-1","article-title":"Chronic recurrent multifocal osteomyelitis (CRMO)\u2014Advancing the diagnosis","volume":"14","author":"Roderick","year":"2016","journal-title":"Pediatr. Rheumatol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/s12969-017-0216-7","article-title":"Dealing with Chronic Non-Bacterial Osteomyelitis: A practical approach","volume":"15","author":"Taddio","year":"2017","journal-title":"Pediatr Rheumatol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s40272-017-0226-4","article-title":"An Update on the Pathogenesis and Treatment of Chronic Recurrent Multifocal Osteomyelitis in Children","volume":"19","author":"Taddio","year":"2017","journal-title":"Pediatr. Drugs."},{"key":"ref_16","first-page":"578","article-title":"Comparison of magnetic resonance imaging and 99mTechnetium-labelled methylene diphosphonate bone scintigraphy in the initial assessment of chronic non-bacterial osteomyelitis of childhood and adolescents","volume":"30","author":"Morbach","year":"2012","journal-title":"Clin. Exp. Rheumatol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1148\/radiol.2523081335","article-title":"Chronic Recurrent Multifocal Osteomyelitis: Comparison of Whole-Body MR Imaging with Radiography and Correlation with Clinical and Laboratory Data","volume":"252","author":"Fritz","year":"2009","journal-title":"Radiology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"737.e3","DOI":"10.1016\/j.crad.2019.02.021","article-title":"Radiological diagnosis of chronic recurrent multifocal osteomyelitis using whole-body MRI-based lesion distribution patterns","volume":"74","author":"Andronikou","year":"2019","journal-title":"Clin. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1186\/ar2075","article-title":"What is MRI bone oedema in rheumatoid arthritis and why does it matter?","volume":"8","author":"McQueen","year":"2006","journal-title":"Arthritis Res. Ther."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1002\/art.22496","article-title":"Bone erosions and bone marrow edema as defined by magnetic resonance imaging reflect true bone marrow inflammation in rheumatoid arthritis","volume":"56","author":"Dorotka","year":"2007","journal-title":"Arthritis Rheum."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1148\/rg.2016160056","article-title":"MR Imaging of Pediatric Bone Marrow","volume":"36","author":"Chan","year":"2016","journal-title":"RadioGraphics"},{"key":"ref_22","first-page":"11","article-title":"Magnetic Resonance Imaging of Bone Marrow: A Review\u2014Part I","volume":"1","author":"Wang","year":"2012","journal-title":"J. Am. Osteopath Coll. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1007\/s003300050547","article-title":"Magnetic resonance imaging of normal bone marrow","volume":"8","author":"Malghem","year":"1998","journal-title":"Eur. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1016\/j.ijrobp.2018.05.053","article-title":"Repeatability and Reproducibility of Radiomic Features: A Systematic Review","volume":"102","author":"Traverso","year":"2018","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/s12969-020-00442-9","article-title":"Artificial intelligence for interpretation of segments of whole body MRI in CNO: Pilot study comparing radiologists versus machine learning algorithm","volume":"18","author":"Bhat","year":"2020","journal-title":"Pediatr. Rheumatol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"601425","DOI":"10.3389\/fonc.2021.601425","article-title":"AI and High-Grade Glioma for Diagnosis and Outcome Prediction: Do All Machine Learning Models Perform Equally Well?","volume":"11","author":"Pasquini","year":"2021","journal-title":"Front. Oncol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Pasquini, L., Napolitano, A., Tagliente, E., Dellepiane, F., Lucignani, M., Vidiri, A., Ranazzi, G., Stoppacciaro, A., Moltoni, G., and Nicolai, M. (2021). Deep Learning Can Differentiate IDH-Mutant from IDH-Wild GBM. JPM, 11.","DOI":"10.3390\/jpm11040290"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1007\/s00247-021-05270-x","article-title":"Automated segmentation of magnetic resonance bone marrow signal: A feasibility study","volume":"52","author":"Jenssen","year":"2022","journal-title":"Pediatr. Radiol."},{"key":"ref_29","unstructured":"Lundberg, S., and Lee, S.I. (2017). A Unified Approach to Interpreting Model Predictions. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s00247-020-04735-9","article-title":"Whole-body magnetic resonance imaging in children\u2014How and why? A systematic review","volume":"51","author":"Zadig","year":"2021","journal-title":"Pediatr. Radiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1007\/s00247-022-05312-y","article-title":"Whole-body MRI in children aged 6\u201318 years. Reliability of identifying and grading high signal intensity changes within bone marrow","volume":"52","author":"Zadig","year":"2022","journal-title":"Pediatr. Radiol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110425","DOI":"10.1016\/j.ejrad.2022.110425","article-title":"Whole body magnetic resonance imaging in healthy children and adolescents. Bone marrow appearances of the axial skeleton","volume":"154","author":"Zadig","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_33","unstructured":"(2023, October 24). IBSI Documentation: 183. Available online: https:\/\/ibsi.readthedocs.io\/en\/latest\/."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature Selection with the Boruta Package","volume":"36","author":"Kursa","year":"2010","journal-title":"J. Stat. Soft."},{"key":"ref_35","first-page":"329","article-title":"AUC: A Better Measure than Accuracy in Comparing Learning Algorithms","volume":"Volume 2671","author":"Xiang","year":"2003","journal-title":"Advances in Artificial Intelligence"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"13087","DOI":"10.1038\/srep13087","article-title":"Machine Learning methods for Quantitative Radiomic Biomarkers","volume":"5","author":"Parmar","year":"2015","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1007\/s00247-006-0129-y","article-title":"High-signal T2 changes of the bone marrow of the foot and ankle in children: Red marrow or traumatic changes?","volume":"36","author":"Shabshin","year":"2006","journal-title":"Pediatr. Radiol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1007\/s002560050515","article-title":"Heterogeneous signal in bone marrow on MRI of children\u2019s feet: A normal finding?","volume":"28","author":"Pal","year":"1999","journal-title":"Skelet. Radiol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.compbiomed.2016.04.006","article-title":"Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance images","volume":"73","author":"Rangayyan","year":"2016","journal-title":"Comput. Biol. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1148\/radiol.2017170236","article-title":"Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Pediatric Hand Radiographs","volume":"287","author":"Larson","year":"2018","journal-title":"Radiology"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1007\/s00330-017-5014-6","article-title":"Diagnostic value of MRI-based 3D texture analysis for tissue characterisation and discrimination of low-grade chondrosarcoma from enchondroma: A pilot study","volume":"28","author":"Lisson","year":"2018","journal-title":"Eur. Radiol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s42358-020-00126-8","article-title":"Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging","volume":"60","author":"Faleiros","year":"2020","journal-title":"Adv. Rheumatol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"109755","DOI":"10.1016\/j.ejrad.2021.109755","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":"ref_44","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: The process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"117693510600200030","DOI":"10.1177\/117693510600200030","article-title":"Applications of Machine Learning in Cancer Prediction and Prognosis","volume":"2","author":"Cruz","year":"2006","journal-title":"Cancer Inform."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"ref_47","first-page":"41","article-title":"Applications of Support Vector Machine (SVM) Learning in Cancer Genomics","volume":"15","author":"Huang","year":"2018","journal-title":"CGP"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat. Biotechnol."},{"key":"ref_49","unstructured":"Andrea, D.M. (2019). Big data analytics: Guida per iniziare a classificare e interpretare dati con il machine learning. Apogeo."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/1\/61\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:42:32Z","timestamp":1760132552000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/1\/61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,27]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["diagnostics14010061"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics14010061","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,27]]}}}