{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:09:07Z","timestamp":1792595347509,"version":"4.5.0"},"reference-count":47,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"8","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:sec>\n            <jats:title>Background:<\/jats:title>\n            <jats:p>Thyroid diseases are the second most common hormonal disorders, necessitating accurate diagnostics. Advances in artificial intelligence and radiomics have enhanced diagnostic precision by analyzing quantitative imaging features. However, reproducibility challenges arising from factors such as the field-of-view (FOV) zooming and segmentation variability limit the clinical application of radiomic-based models.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Aim:<\/jats:title>\n            <jats:p>This study focuses on evaluating the impact of segmentation and FOV zooming on the reproducibility of radiomic features and improved performance of machine learning (ML) when using reproducible features for classification of thyroid scintigraphy images into normal, diffuse goiter (DG), multinodular goiter (MNG), and thyroiditis.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Patients and Methods:<\/jats:title>\n            <jats:p>A retrospective analysis was conducted on 872 thyroid scintigraphy cases from 3 centers. Radiomic feature reproducibility was assessed using the intraclass correlation coefficient (ICC), with robust features (ICC\u22650.80) identified under segmentation and zooming conditions. Four ML training scenarios were implemented to train models on Center A data, including (1) all, (2) zoom-robust, (3) segmentation-robust, and (4) mutually robust features, with 3 feature selection methods and 7 classifiers. Models were validated on external data sets (centers B and C).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results:<\/jats:title>\n            <jats:p>FOV zooming significantly reduced feature reproducibility (ICC\u22650.80: 49%), while segmentation effects were minimal (ICC\u22650.80: 96%). Models trained on mutually robust features outperformed those trained using all features. Boruta-MLP achieved the highest accuracy (0.71, <jats:italic toggle=\"yes\">P<\/jats:italic>-value &lt;0.001 vs. all features) in zoomed data sets, and RFE-MLP performed best (0.69, <jats:italic toggle=\"yes\">P<\/jats:italic>-value &lt;0.001 vs. all features) in the baseline data set, with Gray-Level Co-occurrence Matrix (GLCM) features frequently selected.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>Utilizing robust radiomic features significantly improved the performance of ML models in thyroid disease classification, enabling more accurate and generalizable diagnostic outcomes across diverse data sets.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/rlu.0000000000005995","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T05:00:15Z","timestamp":1750136415000},"page":"683-694","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":6,"title":["Impact of Field-of-view Zooming and Segmentation Batches on Radiomics Features Reproducibility and Machine Learning Performance in Thyroid Scintigraphy"],"prefix":"10.1097","volume":"50","author":[{"given":"Soroush","family":"Bagheri","sequence":"first","affiliation":[{"name":"Department of Medical Physics and Radiology, Allied Medical Sciences Faculty, Kashan University of Medical Sciences, Kashan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5359-2407","authenticated-orcid":false,"given":"Ghasem","family":"Hajianfar","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maziar","family":"Sabouri","sequence":"additional","affiliation":[{"name":"Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada"},{"name":"Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3403-9168","authenticated-orcid":false,"given":"Omid","family":"Gharibi","sequence":"additional","affiliation":[{"name":"Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada"},{"name":"Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Babak","family":"Yazdani","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Namazi Hospital, School of Medicine, Shiraz University of Medical Sciences, Shiraz"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atena","family":"Aghaee","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Research Center, Mashhad University of Medical Sciences, Mashhad"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali Mohammad","family":"Nickfarjam","sequence":"additional","affiliation":[{"name":"Health Information Management Research Center, Kashan University of Medical Sciences, Kashan, Iran"},{"name":"Department of Health Information Management and Technology, School of Allied Medical Sciences, Kashan University of Medical Science, Kashan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akram","family":"Yazdani","sequence":"additional","affiliation":[{"name":"Autoimmune Diseases Research Center, Kashan University of Medical Sciences, Kashan, Iran"},{"name":"Department of Biostatistics & Epidemiology, Faculty of Health, Kashan University of Medical Sciences, Kashan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akbar","family":"Aliasgharzadeh","sequence":"additional","affiliation":[{"name":"Department of Medical Physics and Radiology, Allied Medical Sciences Faculty, Kashan University of Medical Sciences, Kashan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Habiballah","family":"Moradi","sequence":"additional","affiliation":[{"name":"Department of Medical Physics and Radiology, Allied Medical Sciences Faculty, Kashan University of Medical Sciences, Kashan, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9980-2403","authenticated-orcid":false,"given":"Arman","family":"Rahmim","sequence":"additional","affiliation":[{"name":"Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada"},{"name":"Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7559-5297","authenticated-orcid":false,"given":"Habib","family":"Zaidi","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"},{"name":"Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands"},{"name":"Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"R1-20250630","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/S2213-8587(22)00035-3","article-title":"The epidemiological landscape of thyroid cancer worldwide: GLOBOCAN estimates for incidence and mortality rates in 2020","volume":"10","author":"Pizzato","year":"2022","journal-title":"Lancet Diabetes Endocrinol"},{"key":"R2-20250630","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1002\/ijc.33690","article-title":"Thyroid cancer, recent advances in diagnosis and therapy","volume":"149","author":"Nabhan","year":"2021","journal-title":"Int J Cancer"},{"key":"R3-20250630","doi-asserted-by":"crossref","first-page":"104267","DOI":"10.1016\/j.compbiomed.2021.104267","article-title":"Early diagnosis of thyroid cancer diseases using computational intelligence techniques: a case study of a Saudi Arabian dataset","volume":"131","author":"Olatunji","year":"2021","journal-title":"Comput Biol Med"},{"key":"R5-20250630","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.2214\/AJR.19.21913","article-title":"Interreader concordance of the TI-RADS: impact of radiologist experience","volume":"214","author":"Chung","year":"2020","journal-title":"AJR Am J Roentgenol"},{"key":"R6-20250630","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.nic.2021.04.008","article-title":"Imaging of the thyroid: practical approach","volume":"31","author":"Calle","year":"2021","journal-title":"Neuroimaging Clinics"},{"key":"R7-20250630","doi-asserted-by":"crossref","first-page":"107531","DOI":"10.1016\/j.knosys.2021.107531","article-title":"Fusing deep and handcrafted features for intelligent recognition of uptake patterns on thyroid scintigraphy","volume":"236","author":"Pi","year":"2022","journal-title":"Knowl Based Syst"},{"key":"R8-20250630","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.2147\/CMAR.S353877","article-title":"Contrast-enhanced CT-based radiomics for the differentiation of nodular goiter from papillary thyroid carcinoma in thyroid nodules","volume":"14","author":"Li","year":"2022","journal-title":"Cancer Manag Res"},{"key":"R9-20250630","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.otc.2018.01.014","article-title":"Thyroid disease around the world","volume":"51","author":"Maniakas","year":"2018","journal-title":"Otolaryngol Clin North Am"},{"key":"R10-20250630","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1053\/j.ctsap.2005.12.002","article-title":"Thyroid scintigraphy in hyperthyroidism","volume":"21","author":"Broome","year":"2006","journal-title":"Clin Tech Small Anim Pract"},{"key":"R11-20250630","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1111\/1754-9485.12166","article-title":"The role of scintigraphy and ultrasound in the imaging of neonatal hypothyroidism: 5-year retrospective review of single-centre experience","volume":"58","author":"De Silva","year":"2014","journal-title":"J Med Imaging Radiat Oncol"},{"key":"R12-20250630","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1089\/thy.2008.0354","article-title":"Interobserver and intraobserver variations in ultrasound assessment of thyroid nodules","volume":"20","author":"Choi","year":"2010","journal-title":"Thyroid"},{"key":"R14-20250630","doi-asserted-by":"crossref","first-page":"0300060520982842","DOI":"10.1177\/0300060520982842","article-title":"Deep learning for intelligent diagnosis in thyroid scintigraphy","volume":"49","author":"Qiao","year":"2021","journal-title":"J Int Med Res"},{"key":"R16-20250630","doi-asserted-by":"crossref","first-page":"77","DOI":"10.4103\/KKUJHS.KKUJHS_17_21","article-title":"Is 99m technetium (Pertechnetate) more efficient in clinical evaluation of thyroid lesions compared to 123 iodine? A scoping review","volume":"7","author":"Alelyani","year":"2022","journal-title":"King Khalid Univ J Health Sci"},{"key":"R19-20250630","doi-asserted-by":"crossref","first-page":"2436","DOI":"10.3390\/cancers13102436","article-title":"Radiomics in differentiated thyroid cancer and nodules: explorations, application, and limitations","volume":"13","author":"Cao","year":"2021","journal-title":"Cancers"},{"key":"R20-20250630","doi-asserted-by":"crossref","first-page":"108992","DOI":"10.1016\/j.ejrad.2020.108992","article-title":"Differential diagnosis of benign and malignant thyroid nodules using deep learning radiomics of thyroid ultrasound images","volume":"127","author":"Zhou","year":"2020","journal-title":"Eur J Radiol"},{"key":"R21-20250630","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00234-021-02813-9","article-title":"Radiomics, machine learning, and artificial intelligence\u2014what the neuroradiologist needs to know","volume":"63","author":"Wagner","year":"2021","journal-title":"Neuroradiol J"},{"key":"R22-20250630","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.cpet.2021.06.007","article-title":"Radiomics in PET imaging: a practical guide for newcomers","volume":"16","author":"Orlhac","year":"2021","journal-title":"PET clinics"},{"key":"R23-20250630","doi-asserted-by":"crossref","first-page":"896","DOI":"10.2214\/AJR.11.7009","article-title":"Interobserver agreement and intraobserver reproducibility in thyroid ultrasound elastography","volume":"198","author":"Lim","year":"2012","journal-title":"AJR Am J Roentgenol"},{"key":"R24-20250630","doi-asserted-by":"crossref","first-page":"1167","DOI":"10.1089\/thy.2009.0110","article-title":"Revised American Thyroid Association management guidelines for patients with thyroid nodules and differentiated thyroid cancer: the American Thyroid Association (ATA) guidelines taskforce on thyroid nodules and differentiated thyroid cancer","volume":"19","author":"Cooper","year":"2009","journal-title":"Thyroid"},{"key":"R25-20250630","doi-asserted-by":"crossref","first-page":"193","DOI":"10.2174\/1573405614666180904122912","article-title":"Assessment of sensitivity, specificity, and accuracy of nuclear medicines, CT scan, and ultrasound in diagnosing thyroid disorders","volume":"16","author":"Bafaraj","year":"2020","journal-title":"Curr Med Imaging Rev"},{"key":"R26-20250630","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"R27-20250630","doi-asserted-by":"crossref","first-page":"2730","DOI":"10.1007\/s12350-020-02109-0","article-title":"Cardiac SPECT radiomic features repeatability and reproducibility: A multi-scanner phantom study","volume":"28","author":"Edalat-Javid","year":"2021","journal-title":"J Nucl Cardiol"},{"key":"R28-20250630","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1002\/mp.17490","article-title":"Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization","volume":"52","author":"Gharibi","year":"2025","journal-title":"Med Phys"},{"key":"R29-20250630","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"R31-20250630","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s11154-023-09822-4","article-title":"Application of radiomics and machine learning to thyroid diseases in nuclear medicine: a systematic review","volume":"25","author":"Dondi","year":"2024","journal-title":"Rev Endocr Metab Disord"},{"key":"R32-20250630","doi-asserted-by":"crossref","first-page":"143","DOI":"10.2967\/jnmt.121.263081","article-title":"Re-Modelling 99m-technetium pertechnetate thyroid uptake; statistical, machine learning and deep learning approaches","volume":"50","author":"Currie","year":"2021","journal-title":"J Nucl Med Technol"},{"key":"R33-20250630","doi-asserted-by":"crossref","first-page":"20200095","DOI":"10.1259\/bjr.20200095","article-title":"Nuclear medicine and molecular imaging advances in the 21st century","volume":"93","author":"Vaz","year":"2020","journal-title":"Br J Radiol"},{"key":"R34-20250630","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1148\/rg.234025716","article-title":"Scintigraphic manifestations of thyrotoxicosis","volume":"23","author":"Intenzo","year":"2003","journal-title":"Radiographics"},{"key":"R35-20250630","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1148\/129.3.759","article-title":"Thyroid scintigraphy: pinhole images versus rectilinear scans","volume":"129","author":"Sostre","year":"1978","journal-title":"Radiology"},{"key":"R36-20250630","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1097\/RLU.0b013e3182a77d0d","article-title":"Advantages of pinhole collimator double-phase scintigraphy with 99mTc-MIBI in secondary hyperparathyroidism","volume":"38","author":"Fuster","year":"2013","journal-title":"Clin Nucl Med"},{"key":"R37-20250630","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1016\/S0140-6736(11)60782-4","article-title":"Thyrotoxicosis","volume":"379","author":"Franklyn","year":"2012","journal-title":"The Lancet"},{"key":"R38-20250630","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"R39-20250630","doi-asserted-by":"crossref","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 Reson Imaging"},{"key":"R40-20250630","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1093\/biomet\/asac017","article-title":"Mean decrease accuracy for random forests: inconsistency, and a practical solution via the Sobol-MDA","volume":"109","author":"B\u00e9nard","year":"2022","journal-title":"Biometrika"},{"key":"R41-20250630","doi-asserted-by":"crossref","first-page":"739","DOI":"10.3390\/diagnostics12030739","article-title":"The role of chest CT radiomics in diagnosis of lung cancer or tuberculosis: a pilot study","volume":"12","author":"Thattaamuriyil Padmakumari","year":"2022","journal-title":"Diagnostics"},{"key":"R42-20250630","doi-asserted-by":"crossref","first-page":"979","DOI":"10.21037\/tlcr.2019.12.19","article-title":"Differentiation of non-small cell lung cancer and histoplasmosis pulmonary nodules: insights from radiomics model performance compared with clinician observers","volume":"8","author":"Uthoff","year":"2019","journal-title":"Transl Lung Cancer Res"},{"key":"R43-20250630","doi-asserted-by":"crossref","first-page":"1933","DOI":"10.2967\/jnumed.121.263598","article-title":"Distinction of lymphoma from sarcoidosis on 18F-FDG PET\/CT: evaluation of radiomics-feature\u2013guided machine learning versus human reader performance","volume":"63","author":"Lovinfosse","year":"2022","journal-title":"J Nucl Med"},{"key":"R44-20250630","doi-asserted-by":"crossref","first-page":"633176","DOI":"10.3389\/fonc.2021.633176","article-title":"Understanding sources of variation to improve the reproducibility of radiomics","volume":"11","author":"Zhao","year":"2021","journal-title":"Front Oncol"},{"key":"R45-20250630","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":"R46-20250630","first-page":"100677","article-title":"A study on the detection of thyroid cancer in Hashimoto\u2019s thyroiditis using computed tomography imaging radiomics","volume":"16","author":"Huang","year":"2023","journal-title":"J Radiat Res Appl Sc"},{"key":"R49-20250630","doi-asserted-by":"crossref","first-page":"615","DOI":"10.3390\/jcm11030615","article-title":"Comparison between two different scanners for the evaluation of the role of 18F-FDG PET\/CT semiquantitative parameters and radiomics features in the prediction of the final diagnosis of thyroid incidentalomas","volume":"11","author":"Dondi","year":"2022","journal-title":"J Clin Med"},{"key":"R50-20250630","doi-asserted-by":"crossref","first-page":"108827","DOI":"10.1016\/j.compbiomed.2024.108827","article-title":"Challenges and limitations in applying radiomics to PET imaging: possible opportunities and avenues for research","volume":"179","author":"Stefano","year":"2024","journal-title":"Comput Biol Med"},{"key":"R51-20250630","doi-asserted-by":"crossref","first-page":"4431","DOI":"10.21037\/qims-21-86","article-title":"Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review","volume":"11","author":"Xue","year":"2021","journal-title":"Quant Imaging Med Surg"},{"key":"R52-20250630","first-page":"242315","article-title":"Machine learning and radiomics-based classification of thyroid disease using 99mTc-pertechnetate scintigraphy","volume":"65 (supplement 2)","author":"Sabouri","year":"2024","journal-title":"Soc Nuclear Med"},{"key":"R53-20250630","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s40644-025-00857-1","article-title":"Robust vs. non-robust radiomic features: the quest for optimal machine learning models using phantom and clinical studies","volume":"25","author":"Hosseini","year":"2025","journal-title":"Cancer Imaging"},{"key":"R54-20250630","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13014-020-01543-1","article-title":"Single-center versus multi-center data sets for molecular prognostic modeling: a simulation study","volume":"15","author":"Samaga","year":"2020","journal-title":"Radiat Oncol"},{"key":"R55-20250630","doi-asserted-by":"crossref","first-page":"1285775","DOI":"10.3389\/fonc.2023.1285775","article-title":"A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability","volume":"13","author":"Tozzi","year":"2023","journal-title":"Front Oncol"}],"container-title":["Clinical Nuclear Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T16:00:59Z","timestamp":1751299259000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/rlu.0000000000005995","relation":{},"ISSN":["0363-9762","1536-0229"],"issn-type":[{"value":"0363-9762","type":"print"},{"value":"1536-0229","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,17]]},"assertion":[{"value":"2025-02-28","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-30","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}