{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T18:18:11Z","timestamp":1787681891579,"version":"build-2784847793"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T00:00:00Z","timestamp":1646006400000},"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. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>This study aimed to explore the radiomic features from PET images to detect active cardiac sarcoidosis (CS).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Forty sarcoid patients and twenty-nine controls were scanned using FDG PET-CMR. Five feature classes were compared between the groups. From the PET images alone, two different segmentations were drawn. For segmentation A, a region of interest (ROI) was manually delineated for the patients' myocardium hot regions with standardized uptake value (SUV) higher than 2.5 and the controls' normal myocardium region. A second ROI was drawn in the entire left ventricular myocardium for both study groups, segmentation B. The conventional metrics and radiomic features were then extracted for each ROI. Mann-Whitney <jats:italic>U<\/jats:italic>-test and a logistic regression classifier were used to compare the individual features of the study groups.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>For segmentation A, the SUV<jats:sub>min<\/jats:sub> had the highest area under the curve (AUC) and greatest accuracy among the conventional metrics. However, for both segmentations, the AUC and accuracy of the TBR<jats:sub>max<\/jats:sub> were relatively high, &amp;gt;0.85. Twenty-two (from segmentation A) and thirty-five (from segmentation B) of 75 radiomic features fulfilled the criteria: <jats:italic>P<\/jats:italic>-value &amp;lt; 0.00061 (after Bonferroni correction), AUC &amp;gt;0.5, and accuracy &amp;gt;0.7. Principal Component Analysis (PCA) was conducted, with five components leading to cumulative variance higher than 90%. Ten machine learning classifiers were then tested and trained. Most of them had AUCs and accuracies \u22650.8. For segmentation A, the AUCs and accuracies of all classifiers are &amp;gt;0.9, but k-neighbors and neural network classifiers were the highest (=1). For segmentation B, there are four classifiers with AUCs and accuracies \u22650.8. However, the gaussian process classifier indicated the highest AUC and accuracy (0.9 and 0.8, respectively).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Radiomic analysis of the specific PET data was not proven to be necessary for the detection of CS. However, building an automated procedure will help to accelerate the analysis and potentially lead to more reproducible findings across different scanners and imaging centers and consequently improve standardization procedures that are important for clinical trials and development of more robust diagnostic protocols.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2022.840261","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T05:20:35Z","timestamp":1646025635000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Exploring the Utility of Radiomic Feature Extraction to Improve the Diagnostic Accuracy of Cardiac Sarcoidosis Using FDG PET"],"prefix":"10.3389","volume":"9","author":[{"given":"Nouf A.","family":"Mushari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Soultanidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Duff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria G.","family":"Trivieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahi A.","family":"Fayad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Robson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charalampos","family":"Tsoumpas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,2,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.jacc.2016.03.605","article-title":"Cardiac sarcoidosis","volume":"68","author":"Birnie","year":"2016","journal-title":"J Am Coll Cardiol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"50","DOI":"10.3978\/j.issn.2223-3652.2015.12.13","article-title":"Cardiac sarcoidosis\u2014state of the art review","volume":"6","author":"Hulten","year":"2016","journal-title":"Cardiovasc Diag Therapy."},{"key":"B3","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s12024-016-9792-y","article-title":"Sudden unexpected death due to severe pulmonary and cardiac sarcoidosis","volume":"12","author":"Ginelliov\u00e1","year":"2016","journal-title":"Forensic Sci Med Pathol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"S13","DOI":"10.1016\/j.rmed.2018.09.008","article-title":"Cardiac sarcoidosis: diagnosis confirmation by bronchoalveolar lavage and lung biopsy","volume":"144","author":"Petek","year":"2018","journal-title":"Res Med."},{"key":"B5","volume-title":"Cardiac Involvement in Sarcoidosis. Seminars in Respiratory and Critical Care Medicine","author":"Deng","year":"2002"},{"key":"B6","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1111\/j.1440-1827.1993.tb01148.x","article-title":"Pathological studies on sarcoidosis autopsy. I. Epidemiological features of 320 cases in Japan","volume":"43","author":"Iwai","year":"1993","journal-title":"Pathol Int."},{"key":"B7","first-page":"167","article-title":"Causes of death in patients with sarcoidosis. A morphologic study of 38 autopsies with clinicopathologic correlations","volume":"119","author":"Perry","year":"1995","journal-title":"Arch Pathol Lab Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.ahj.2008.09.009","article-title":"Cardiac sarcoidosis","volume":"157","author":"Kim","year":"2009","journal-title":"Am Heart J."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1878","DOI":"10.1016\/j.jacc.2020.08.042","article-title":"Challenges in cardiac and pulmonary sarcoidosis: JACC state-of-the-art review","volume":"76","author":"Trivieri","year":"2020","journal-title":"J Am Coll Cardiol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.2967\/jnumed.117.196287","article-title":"Joint SNMMI\u2013ASNC expert consensus document on the role of 18F-FDG PET\/CT in cardiac sarcoid detection and therapy monitoring","volume":"58","author":"Chareonthaitawee","year":"2017","journal-title":"J Nucl Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s12350-016-0502-7","article-title":"Patient preparation for cardiac fluorine-18 fluorodeoxyglucose positron emission tomography imaging of inflammation","volume":"24","author":"Osborne","year":"2017","journal-title":"J Nucl Cardiol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.jcmg.2017.02.021","article-title":"Hybrid magnetic resonance imaging and positron emission tomography with fluorodeoxyglucose to diagnose active cardiac sarcoidosis","volume":"11","author":"Dweck","year":"2018","journal-title":"JACC."},{"key":"B13","doi-asserted-by":"publisher","first-page":"503","DOI":"10.2967\/jnumed.115.154385","article-title":"PET assessment of vascular inflammation and atherosclerotic plaques: SUV or TBR?","volume":"56","author":"Chen","year":"2015","journal-title":"J Nucl Med."},{"key":"B14","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s12149-014-0806-0","article-title":"Recommendations for 18 F-fluorodeoxyglucose positron emission tomography imaging for cardiac sarcoidosis: Japanese society of nuclear cardiology recommendations","volume":"28","author":"Ishida","year":"2014","journal-title":"Ann Nucl Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1016\/j.hrthm.2014.03.043","article-title":"HRS expert consensus statement on the diagnosis and management of arrhythmias associated with cardiac sarcoidosis","volume":"11","author":"Birnie","year":"2014","journal-title":"Heart Rhythm."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D Slicer as an image computing platform for the Quantitative Imaging Network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn Res Imag"},{"key":"B17","first-page":"277","volume-title":"3D Slicer: A Platform for Subject-Specific Image Analysis, Visualization, and Clinical Support. Intraoperative Imaging and Image-Guided Therapy","author":"Kikinis","year":"2014"},{"key":"B18","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1097\/MAJ.0b013e31827b9b6d","article-title":"Dual time point positron emission tomography\/computed tomography scan in evaluation of intrathoracic lesions in an area endemic for histoplasmosis and with high prevalence of sarcoidosis","volume":"346","author":"Kadaria","year":"2013","journal-title":"Am J Med Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1536012119856965","DOI":"10.1177\/1536012119856965","article-title":"18F-FDG PET\/CT quantitative parameters and texture analysis effectively differentiate endometrial precancerous lesion and early-stage carcinoma","volume":"18","author":"Wang","year":"2019","journal-title":"Mol Imag"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Van Griethuysen","year":"2017","journal-title":"Can Res."},{"key":"B21","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2360","DOI":"10.1007\/s00259-016-3452-z","article-title":"The asphericity of the metabolic tumour volume in NSCLC: correlation with histopathology and molecular markers","volume":"43","author":"Apostolova","year":"2016","journal-title":"Eur J Nucl Med Mol Imag."},{"key":"B23","doi-asserted-by":"publisher","first-page":"e0150509","DOI":"10.1371\/journal.pone.0150509","article-title":"Respiration-averaged CT for attenuation correction of PET images\u2013impact on PET texture features in non-small cell lung cancer patients","volume":"11","author":"Cheng","year":"2016","journal-title":"PLoS ONE."},{"key":"B24","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1007\/s12149-018-1281-9","article-title":"A systematic review of the prognostic value of texture analysis in 18 F-FDG PET in lung cancer","volume":"32","author":"Han","year":"2018","journal-title":"Ann Nucl Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s13550-017-0310-3","article-title":"The effects of segmentation algorithms on the measurement of 18 F-FDG PET texture parameters in non-small cell lung cancer","volume":"7","author":"Bashir","year":"2017","journal-title":"Ejnmmi Res."},{"key":"B26","doi-asserted-by":"publisher","first-page":"e115510","DOI":"10.1371\/journal.pone.0115510","article-title":"Comparison of texture features derived from static and respiratory-gated PET images in non-small cell lung cancer","volume":"9","author":"Yip","year":"2014","journal-title":"PLoS ONE."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.840261\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T05:20:41Z","timestamp":1646025641000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.840261\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,28]]},"references-count":26,"alternative-id":["10.3389\/fmed.2022.840261"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2022.840261","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,28]]},"article-number":"840261"}}