{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T12:08:06Z","timestamp":1788005286211,"version":"build-2784847793"},"reference-count":110,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:00:00Z","timestamp":1755993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Minister of Education and Science, Poland","award":["NdS-II\/SP\/0189\/2024\/01"],"award-info":[{"award-number":["NdS-II\/SP\/0189\/2024\/01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Thyroid cancer encompasses distinct histological subtypes with varying biological behavior and treatment implications. Accurate preoperative subtype differentiation remains challenging. Although ultrasound (US) is widely used for thyroid nodule evaluation, qualitative assessment alone is often insufficient to distinguish between papillary (PTC), follicular (FTC), and medullary thyroid carcinoma (MTC). Methods: A retrospective analysis was performed on patients with histologically confirmed PTC, FTC, or MTC. A total of 224 standardized B-mode ultrasound images were analyzed. A set of fully quantitative features was extracted, including morphological characteristics (aspect ratio and perimeter-to-area ratio), internal echotexture (echogenicity and local entropy), boundary sharpness (gradient measures and KL divergence), and structural components (calcifications and cystic areas). Feature extraction was conducted using semi-automatic algorithms implemented in MATLAB. Statistical differences were assessed using the Kruskal\u2013Wallis and Dunn\u2013\u0160id\u00e1k tests. A Random Forest classifier was trained and evaluated to determine the discriminatory performance of individual and combined features. Results: Significant differences (p &lt; 0.05) were found among subtypes for key features such as perimeter-to-area ratio, normalized echogenicity, and calcification pattern. The full-feature Random Forest model achieved an overall classification accuracy of 89.3%, with F1-scores of 93.4% for PTC, 85.7% for MTC, and 69.1% for FTC. A reduced model using the top 10 features yielded an even higher accuracy of 91.8%, confirming the robustness and clinical relevance of the selected parameters. Conclusions: Subtype classification of thyroid cancer was effectively performed using quantitative ultrasound features and machine learning. The results suggest that biologically interpretable image-derived metrics may assist in preoperative decision-making and potentially reduce the reliance on invasive diagnostic procedures.<\/jats:p>","DOI":"10.3390\/cancers17172761","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:09:53Z","timestamp":1756080593000},"page":"2761","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Quantitative Ultrasound-Based Precision Diagnosis of Papillary, Follicular, and Medullary Thyroid Carcinomas Using Morphological, Structural, and Textural Features"],"prefix":"10.3390","volume":"17","author":[{"given":"Hanna","family":"Piotrzkowska Wr\u00f3blewska","sequence":"first","affiliation":[{"name":"Ultrasound Department, Institute of Fundamental Technological Research, Polish Academy of Sciences, 02-106 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2104-1130","authenticated-orcid":false,"given":"Piotr","family":"Karwat","sequence":"additional","affiliation":[{"name":"Ultrasound Department, Institute of Fundamental Technological Research, Polish Academy of Sciences, 02-106 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5271-541X","authenticated-orcid":false,"given":"Agnieszka","family":"\u017by\u0142ka","sequence":"additional","affiliation":[{"name":"Department of Endocrine Oncology and Nuclear Medicine, Maria Sklodowska-Curie National Research Institute of Oncology, 02-781 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-4140","authenticated-orcid":false,"given":"Katarzyna","family":"Dobruch Sobczak","sequence":"additional","affiliation":[{"name":"Radiology Department II, Maria Sklodowska-Curie National Research Institute of Oncology, 02-034 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3485-8219","authenticated-orcid":false,"given":"Marek","family":"Dedecjus","sequence":"additional","affiliation":[{"name":"Department of Endocrine Oncology and Nuclear Medicine, Maria Sklodowska-Curie National Research Institute of Oncology, 02-781 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3978-9099","authenticated-orcid":false,"given":"Jerzy","family":"Litniewski","sequence":"additional","affiliation":[{"name":"Ultrasound Department, Institute of Fundamental Technological Research, Polish Academy of Sciences, 02-106 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,24]]},"reference":[{"key":"ref_1","first-page":"209","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"Didkowska, J., Wojciechowska, U., Olasek, P., Micha\u0142ek, I., and Ciuba, A. (2023). Nowotwory Z\u0142o\u015bliwe w Polsce w 2021 Roku, Krajowy Rejestr Nowotwor\u00f3w, Narodowy Instytut Onkologii. (In Polish)."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2783","DOI":"10.1016\/S0140-6736(16)30172-6","article-title":"Thyroid cancer","volume":"388","author":"Cabanillas","year":"2016","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/thy.2015.0020","article-title":"2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer","volume":"26","author":"Haugen","year":"2016","journal-title":"Thyroid"},{"key":"ref_5","unstructured":"Nikiforov, Y.E., Biddinger, P.W., Thompson, L.D., and Lester, D.R. (2012). Diagnostic Pathology and Molecular Genetics of the Thyroid, Wolters Kluwer. [2nd ed.]."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1089\/thy.2014.0335","article-title":"Revised American Thyroid Association guidelines for the management of medullary thyroid carcinoma","volume":"25","author":"Wells","year":"2015","journal-title":"Thyroid"},{"key":"ref_7","first-page":"891","article-title":"Prognosis of medullary thyroid carcinoma: Demographic, clinical, and pathologic predictors of survival","volume":"140","author":"Roman","year":"2005","journal-title":"Arch. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"v219","DOI":"10.1093\/annonc\/mdq190","article-title":"Medullary thyroid cancer: ESMO Clinical Practice Guidelines","volume":"21","author":"Pacini","year":"2010","journal-title":"Ann. Oncol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.jacr.2017.01.046","article-title":"ACR Thyroid Imaging Reporting and Data System (TI-RADS): White paper of the ACR TI-RADS committee","volume":"14","author":"Tessler","year":"2017","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1159\/000478927","article-title":"European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS","volume":"6","author":"Russ","year":"2017","journal-title":"Eur. Thyroid J."},{"key":"ref_11","first-page":"18","article-title":"EU-TIRADS-PL\u2014Polskie wytyczne ultrasonograficznej stratyfikacji ryzyka z\u0142o\u015bliwo\u015bci zmian ogniskowych tarczycy","volume":"73","author":"Migda","year":"2022","journal-title":"Endokrynol. Pol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s40644-021-00402-w","article-title":"Ultrasound features of medullary thyroid carcinoma as predictors of biological behavior","volume":"21","author":"Zhao","year":"2021","journal-title":"Cancer Imaging"},{"key":"ref_13","first-page":"133","article-title":"Ultrasonographic features of thyroid carcinoma of different sizes: Comparison between medullary thyroid carcinomas and papillary thyroid carcinomas","volume":"46","author":"Zhang","year":"2024","journal-title":"Zhonghua Zhong Liu Za Zhi"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1097\/RUQ.0000000000000508","article-title":"Ultrasonic Characteristics of Medullary Thyroid Carcinoma","volume":"37","author":"Lei","year":"2021","journal-title":"Ultrasound Q."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2021","DOI":"10.1007\/s00405-017-4557-0","article-title":"Sonographic differences between conventional and follicular variant papillary thyroid carcinoma","volume":"274","author":"Hughes","year":"2017","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hekimsoy, \u0130., Ertan, Y., Serin, G., Karabulut, A.K., and \u00d6zbek, S. (2024). Comparison of ultrasound findings of papillary thyroid carcinoma subtypes based on the 2022 WHO classification of thyroid neoplasms. Front. Endocrinol., 14.","DOI":"10.3389\/fendo.2024.1434787"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.62347\/GARM5333","article-title":"Efficacy of color Doppler ultrasound signs combined with serum tumor-specific growth factor in the diagnosis of differentiated thyroid cancer","volume":"16","author":"Chen","year":"2024","journal-title":"Am. J. Transl. Res."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jiang, S., Xie, Q., Li, N., Chen, H., and Chen, X. (2021). Modified models for predicting malignancy using ultrasound characters have high accuracy in thyroid nodules with small size. Front. Mol. Biosci., 8.","DOI":"10.3389\/fmolb.2021.752417"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"27520","DOI":"10.18632\/oncotarget.15897","article-title":"Ultrasonographic characteristics of medullary thyroid carcinoma: A comparison with papillary thyroid carcinoma","volume":"8","author":"Liu","year":"2017","journal-title":"Oncotarget"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e943228","DOI":"10.12659\/MSM.943228","article-title":"Diagnostic Efficiency of ACR-TIRADS Score for Differentiating Benign and Malignant Thyroid Nodules of Various Pathological Types","volume":"30","author":"Xu","year":"2024","journal-title":"Med. Sci. Monit."},{"key":"ref_21","first-page":"193","article-title":"EU-TIRADS-Based omission of fine-needle aspiration and cytology from thyroid nodules overlooks a substantial number of follicular thyroid cancers","volume":"185","author":"Solymosi","year":"2021","journal-title":"Int. J. Endocrinol."},{"key":"ref_22","first-page":"44","article-title":"Clinical and sonographic features of noninvasive follicular thyroid neoplasm with papillary-like nuclear features","volume":"38","author":"Ni","year":"2022","journal-title":"Ultrasound Q."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"358","DOI":"10.15557\/JoU.2015.0033","article-title":"Shear wave elastography in medullary thyroid carcinoma diagnostics","volume":"15","author":"Mlosek","year":"2015","journal-title":"J. Ultrason."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yang, F., Hou, W., Wang, Y., Mu, J., Wang, H., and Wei, X. (2025). Ultrasonic radiomics in predicting pathologic type for thyroid cancer: A preliminary study. Front. Endocrinol., 16.","DOI":"10.3389\/fendo.2025.1428888"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"101","DOI":"10.3348\/kjr.2009.10.2.101","article-title":"Ultrasonographic findings of medullary thyroid carcinoma: A comparison with papillary thyroid carcinoma","volume":"10","author":"Kim","year":"2009","journal-title":"Korean J. Radiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1002\/dc.23709","article-title":"Sonographic and cytologic differences of NIFTP from infiltrative or invasive encapsulated follicular variant papillary thyroid carcinoma","volume":"45","author":"Yang","year":"2017","journal-title":"Diagn. Cytopathol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1002\/jum.14377","article-title":"Differentiation of the follicular variant of papillary thyroid carcinoma from classic papillary thyroid carcinoma: An ultrasound analysis and complement to fine-needle aspiration cytology","volume":"37","author":"Ng","year":"2018","journal-title":"J. Ultrasound Med."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Slabaugh, G., Beltran, L., Rizvi, H., Deloukas, P., and Marouli, E. (2023). Applications of machine and deep learning to thyroid cytology and histopathology: A review. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.958310"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Cao, C.-L., Li, Q., Tong, J., Shi, L., Li, W.-X., Xu, Y., Cheng, J., Du, T.T., Li, J., and Cui, X.W. (2023). Artificial intelligence in thyroid ultrasound. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1060702"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S2213-8587(21)00027-9","article-title":"Thyroid cancer incidence trends by histology in 25 countries: A population-based study","volume":"9","author":"Bray","year":"2021","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref_31","first-page":"104637","article-title":"Rare thyroid malignancies in Europe: Data from the RARECAREnet project","volume":"104","author":"Locati","year":"2020","journal-title":"Oral Oncol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bikas, A., and Burman, K. (2019). Epidemiology of thyroid cancer. The Thyroid and Its Diseases, Springer.","DOI":"10.1007\/978-3-319-72102-6_35"},{"key":"ref_33","first-page":"306","article-title":"Medullary thyroid cancer: Epidemiology","volume":"19","author":"Rybakov","year":"2023","journal-title":"Int. J. Endocrinol."},{"key":"ref_34","first-page":"563","article-title":"A closer look at \u201ctaller-than-wide\u201d thyroid nodules: Examining dimension ratio to predict malignancy","volume":"165","author":"Mattingly","year":"2021","journal-title":"Otolaryngol. Head Neck Surg."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1089\/thy.2014.0353","article-title":"Thyroid ultrasound features and risk of carcinoma: A systematic review and meta-analysis of observational studies","volume":"25","author":"Remonti","year":"2015","journal-title":"Thyroid"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1507\/endocrj.EJ20-0379","article-title":"Reconfirmation of the accuracy of the taller-than-wide sign in multicenter collaborative research in Japan","volume":"68","author":"Fukushima","year":"2021","journal-title":"Endocr. J."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1089\/thy.2010.0372","article-title":"A taller-than-wide shape in thyroid nodules in transverse and longitudinal planes and the prediction of malignancy","volume":"21","author":"Moon","year":"2011","journal-title":"Thyroid"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2021","DOI":"10.21873\/invivo.12014","article-title":"Taller-than-wide thyroid nodules with microcalcifications are at high risk of malignancy","volume":"34","author":"Papapostolou","year":"2020","journal-title":"Vivo"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s12020-019-02184-5","article-title":"Sonographic features of follicular variant of papillary thyroid carcinoma and performance of the 2017 ACR TI-RADS","volume":"67","author":"Zhang","year":"2020","journal-title":"Endocrine"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1685","DOI":"10.7863\/jum.2009.28.12.1685","article-title":"Sonographic features of follicular variant papillary thyroid carcinomas vs conventional papillary carcinomas","volume":"28","author":"Kim","year":"2009","journal-title":"J. Ultrasound Med."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3776","DOI":"10.21037\/qims-22-968","article-title":"Comparison of the diagnostic performance and clinical role of different ultrasound-based thyroid malignancy risk stratification systems for medullary thyroid carcinoma","volume":"13","author":"Liu","year":"2023","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1093\/bjr\/tqae103","article-title":"Predicting tall-cell subtype of papillary thyroid carcinomas independently with preoperative multimodal ultrasound","volume":"97","author":"Ye","year":"2024","journal-title":"Br. J. Radiol."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Borowczyk, M., Woli\u0144ski, K., Wi\u0119ckowska, B., Jod\u0142owska-Siewert, E., Szczepanek-Parulska, E., Verburg, F., and Rucha\u0142a, M. (2021). Sonographic features differentiating follicular thyroid cancer from adenoma\u2014A meta-analysis. Cancers, 13.","DOI":"10.3390\/cancers13050938"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1089\/thy.2017.0514","article-title":"Preoperative predictors for lateral cervical lymph node metastases in sporadic medullary thyroid carcinoma","volume":"28","author":"Oh","year":"2018","journal-title":"Thyroid"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"110158","DOI":"10.1016\/j.apacoust.2024.110158","article-title":"Ultrasound fuzzy entropy imaging based on time-series signal for tissue characterization","volume":"224","author":"Zhang","year":"2024","journal-title":"Appl. Acoust."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejrad.2017.12.004","article-title":"Texture analysis and machine learning to characterize thyroid nodules and differentiated cancer","volume":"99","author":"Sollini","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1016\/j.tranon.2017.09.003","article-title":"MRI texture analysis reflects histopathology parameters in thyroid cancer\u2014A preliminary study","volume":"10","author":"Meyer","year":"2017","journal-title":"Transl. Oncol."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Nugroho, H., Rahmawaty, M., Triyani, Y., and Ardiyanto, I. (2016, January 29\u201330). Texture analysis for classification of thyroid ultrasound images. Proceedings of the 2016 International Electronics Symposium (IES), Denpasar, Indonesia.","DOI":"10.1109\/ELECSYM.2016.7861053"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"034501","DOI":"10.1117\/1.JMI.9.3.034501","article-title":"A machine-learning algorithm for distinguishing malignant from benign indeterminate thyroid nodules using ultrasound radiomic features","volume":"9","author":"Keutgen","year":"2022","journal-title":"J. Med. Imaging"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1177\/0161734619839648","article-title":"A variance-reduction approach to detection of the thyroid nodule boundary on ultrasound images","volume":"41","author":"Chiu","year":"2019","journal-title":"Ultrason. Imaging"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chen, J., and Chen, J. (2024). Multimodal image feature fusion for improving medical ultrasound image segmentation. Biomed. Signal Process. Control, 89.","DOI":"10.1016\/j.bspc.2023.105705"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Ferreira, L., Gimba, E., Vinagre, J., Sobrinho-Sim\u00f5es, M., and Soares, P. (2020). Molecular aspects of thyroid calcification. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21207718"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1177\/147323001204000136","article-title":"Correlation between thyroid nodule calcification morphology on ultrasound and carcinoma","volume":"40","author":"Shi","year":"2012","journal-title":"J. Int. Med. Res."},{"key":"ref_54","first-page":"2652","article-title":"Relationship between morphologic characteristics of ultrasonic calcification in thyroid nodules and carcinoma","volume":"45","author":"Lu","year":"2019","journal-title":"Ultrasound Med. Biol."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.4103\/jcrt.JCRT_1031_17","article-title":"The clinical significance of ultrasound grayscale ratio in differentiating markedly hypoechoic and anechoic thyroid nodules","volume":"14","author":"Lei","year":"2018","journal-title":"J. Cancer Res. Ther."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Nugroho, H.A., Nugroho, A., Frannita, E.L., Ardiyanto, I., and Choridah, L. (2017, January 23\u201326). Feature extraction based on laws\u2019 texture energy for lesion echogenicity classification of thyroid ultrasound images. Proceedings of the 2017 International Conference on Computer, Control, Informatics and its Applications (IC3INA), Jakarta, Indonesia.","DOI":"10.1109\/IC3INA.2017.8251737"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"4","DOI":"10.33545\/26644436.2023.v6.i4a.356","article-title":"A study of evaluation of focal thyroid nodule\/nodules on ultrasound (grey scale), color doppler and elastography with histopathology correlation","volume":"6","author":"Sharda","year":"2023","journal-title":"Int. J. Radiol. Diagn. Imaging"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"486","DOI":"10.5812\/ijem.3505","article-title":"Normality tests for statistical analysis: A guide for non-statisticians","volume":"10","author":"Ghasemi","year":"2012","journal-title":"Int. J. Endocrinol. Metab."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1080\/00401706.1964.10490181","article-title":"Multiple comparisons using rank sums","volume":"6","author":"Dunn","year":"1964","journal-title":"Technometrics"},{"key":"ref_60","first-page":"626","article-title":"Rectangular confidence regions for the means of multivariate normal distributions","volume":"62","year":"1967","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Lange, T.M., G\u00fcltas, M., Schmitt, A., and Heinrich, F. (2025). optRF: Optimising random forest stability by determining the optimal number of trees. BMC Bioinform., 26.","DOI":"10.1186\/s12859-025-06097-1"},{"key":"ref_62","first-page":"1","article-title":"To tune or not to tune the number of trees in random forest?","volume":"18","author":"Probst","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Oshiro, T.M., Perez, P.S., and Baranauskas, J.A. (2012). How many trees in a random forest?. International Workshop on Machine Learning and Data Mining in Pattern Recognition, Springer.","DOI":"10.1007\/978-3-642-31537-4_13"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1007\/s41066-017-0049-2","article-title":"Semi-random partitioning of data into training and test sets in granular computing","volume":"2","author":"Liu","year":"2017","journal-title":"Granul. Comput."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s40537-020-00327-4","article-title":"Selecting critical features for data classification based on machine learning methods","volume":"7","author":"Chen","year":"2020","journal-title":"J. Big Data"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s41060-024-00509-w","article-title":"A review of random forest-based feature selection methods for data science education and applications","volume":"20","author":"Iranzad","year":"2024","journal-title":"Int. J. Data Sci. Anal."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1080\/03610926.2024.2317359","article-title":"On impurity functions in decision trees","volume":"54","author":"Zeng","year":"2024","journal-title":"Commun. Stat. Theory Methods"},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"2516","DOI":"10.1109\/TNNLS.2017.2698204","article-title":"New splitting criteria for decision trees in stationary data streams","volume":"29","author":"Jaworski","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1158\/2767-9764.CRC-24-0474","article-title":"Tumor Cell Plasticity and Stromal Microenvironment Distinguish Papillary and Follicular Growth Patterns in a Mouse Model of BRAFV600E-induced Thyroid Cancer","volume":"5","author":"Schoultz","year":"2025","journal-title":"Cancer Res. Commun."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Basolo, F., and Ugolini, C. (2021). Pathology of Thyroid Cancer. Oxford Textbook of Endocrinology and Diabetes 3e, Oxford University Press.","DOI":"10.1093\/med\/9780198870197.003.0078"},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1159\/000437263","article-title":"Thyroid Growth and Cancer","volume":"4","author":"Williams","year":"2015","journal-title":"Eur. Thyroid J."},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"984","DOI":"10.5858\/2006-130-984-TTWAFG","article-title":"Thyroid tumors with a follicular growth pattern: Problems in differential diagnosis","volume":"130","author":"Suster","year":"2006","journal-title":"Arch. Pathol. Lab. Med."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s12022-024-09812-5","article-title":"RAS-Mutant Follicular Thyroid Tumors: A Continuous Challenge for Pathologists","volume":"35","author":"Wenig","year":"2024","journal-title":"Endocr. Pathol."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1089\/thy.2024.0076","article-title":"Anatomic Patterns of Nodal Spread in Unilateral Papillary and Medullary Thyroid Cancer","volume":"34","author":"Machens","year":"2024","journal-title":"Thyroid"},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Li, L., Lian, S., Luo, Z., Wang, B., and Li, S. (2024). Contour-aware consistency for semi-supervised medical image segmentation. Biomed. Signal Process. Control, 89.","DOI":"10.1016\/j.bspc.2023.105694"},{"key":"ref_76","doi-asserted-by":"crossref","unstructured":"Chen, S., Luo, C., Liu, S., Li, H., Liu, Y., Zhou, H., Liu, L., and Chen, H. (2024). LD-UNet: A long-distance perceptual model for segmentation of blurred boundaries in medical images. Comput. Biol. Med., 168.","DOI":"10.1016\/j.compbiomed.2024.108120"},{"key":"ref_77","first-page":"102126","article-title":"Hyper-fusion network for semi-automatic segmentation of skin lesions","volume":"72","author":"Bi","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_78","doi-asserted-by":"crossref","unstructured":"Cui, W., Meng, D., Lu, K., Wu, Y., Pan, Z., Li, X., and Sun, S. (2023). Automatic segmentation of ultrasound images using SegNet and local Nakagami distribution fitting model. Biomed. Signal Process. Control, 80.","DOI":"10.1016\/j.bspc.2022.104431"},{"key":"ref_79","first-page":"111856","article-title":"Aggregate-aware model with bidirectional edge generation for medical image segmentation","volume":"150","author":"Ma","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_80","doi-asserted-by":"crossref","first-page":"672","DOI":"10.2214\/AJR.18.20799","article-title":"Peripheral Thyroid Nodule Calcifications on Sonography: Evaluation of Malignant Potential","volume":"213","author":"Malhi","year":"2019","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_81","doi-asserted-by":"crossref","first-page":"e366","DOI":"10.5114\/pjr.2021.107450","article-title":"Different sonographic features of peripheral thyroid nodule calcification and risk of malignancy: A prospective observational study","volume":"86","author":"Nabahati","year":"2021","journal-title":"Pol. J. Radiol."},{"key":"ref_82","first-page":"428","article-title":"Eggshell Calcifications at Thyroid Ultrasound: A Sample-focused Analysis of Cytological Findings and Post-thyroidectomy Pathological Correlates","volume":"127","author":"Radu","year":"2024","journal-title":"Rom. J. Mil. Med."},{"key":"ref_83","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1507\/endocrj.EJ12-0294","article-title":"Relationship between patterns of calcification in thyroid nodules and histopathologic findings","volume":"60","author":"Kim","year":"2013","journal-title":"Endocr. J."},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/S0899-7071(03)00190-6","article-title":"Thyroid calcifications: Sonographic patterns and incidence of cancer","volume":"28","author":"Taki","year":"2004","journal-title":"Clin. Imaging"},{"key":"ref_85","doi-asserted-by":"crossref","first-page":"663","DOI":"10.3348\/kjr.2020.0381","article-title":"Malignancy Risk Stratification of Thyroid Nodules with Macrocalcification and Rim Calcification Based on Ultrasound Patterns","volume":"22","author":"Shin","year":"2021","journal-title":"Korean J. Radiol."},{"key":"ref_86","first-page":"1021","article-title":"Cancer rates and characteristics of thyroid nodules with macrocalcification","volume":"84","author":"Canpolat","year":"2024","journal-title":"Endocrine"},{"key":"ref_87","first-page":"1542","article-title":"Macrocalcifications Do Not Alter Malignancy Risk Within the American Thyroid Association Sonographic Pattern System When Present in Non-High Suspicion Thyroid Nodules","volume":"31","author":"Kobaly","year":"2021","journal-title":"Thyroid"},{"key":"ref_88","first-page":"767","article-title":"Differential Diagnosis of Malignant Thyroid Calcification Nodule Based on Computed Tomography Image Texture","volume":"11","author":"Peng","year":"2021","journal-title":"J. Med. Imaging Health Inform."},{"key":"ref_89","doi-asserted-by":"crossref","unstructured":"Janu\u015b, D., Kujdowicz, M., Kiszka-Wi\u0142koj\u0107, A., Kaleta, K., Taczanowska-Niemczuk, A., Radli\u0144ski, J., Mo\u017ad\u017ce\u0144, K., Nowak, Z., G\u00f3recki, W., and Starzyk, J.B. (2025). Ultrasound and histopathological assessment of benign, borderline, and malignant thyroid tumors in pediatric patients: An illustrative review and literature overview. Front. Endocrinol., 15.","DOI":"10.3389\/fendo.2024.1481804"},{"key":"ref_90","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1148\/radiol.2018171170","article-title":"Thyroid nodules in pediatric patients: Sonographic characteristics and likelihood of cancer","volume":"288","author":"Richman","year":"2018","journal-title":"Radiology"},{"key":"ref_91","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1530\/eje.1.02177","article-title":"Thyroid nodule shape suggests malignancy","volume":"155","author":"Cappelli","year":"2006","journal-title":"Eur. J. Endocrinol."},{"key":"ref_92","doi-asserted-by":"crossref","unstructured":"Mohammad, F., AlZoubi, A., Du, H., and Jassim, S. (2022). Machine learning assessment of border irregularity of thyroid nodules from ultrasound images. Multimodal Image Exploitation and Learning 2022, SPIE.","DOI":"10.1117\/12.2618470"},{"key":"ref_93","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.ejso.2013.11.015","article-title":"Ultrasonographic features associated with malignancy in cytologically indeterminate thyroid nodules","volume":"40","author":"Batawil","year":"2014","journal-title":"Eur. J. Surg. Oncol."},{"key":"ref_94","doi-asserted-by":"crossref","unstructured":"Chen, D., Hu, J., Zhu, M., Tang, N., Yang, Y., and Feng, Y. (2020). Diagnosis of thyroid nodules for ultrasonographic characteristics indicative of malignancy using random forest. BioData Min., 13.","DOI":"10.1186\/s13040-020-00223-w"},{"key":"ref_95","first-page":"3357","article-title":"Ultrasonographic features of medullary thyroid carcinoma: Do they correlate with pre- and post-operative calcitonin levels","volume":"17","author":"Cho","year":"2016","journal-title":"Asian Pac. J. Cancer Prev."},{"key":"ref_96","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.7863\/jum.2008.27.10.1431","article-title":"Sonographic Features of the Follicular Variant of Papillary Thyroid Carcinoma","volume":"27","author":"Yoon","year":"2008","journal-title":"J. Ultrasound Med."},{"key":"ref_97","first-page":"795","article-title":"Thyroid follicular carcinoma: Sonographic features of 50 cases","volume":"192","author":"Sillery","year":"2009","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_98","doi-asserted-by":"crossref","unstructured":"Wu, M.-H., Chen, C.-N., Chen, K.Y., Ho, M., Tai, H., Wang, Y.-H., Chen, A., and Chang, K.J. (2016). Quantitative analysis of echogenicity for patients with thyroid. Sci. Rep., 6.","DOI":"10.1038\/srep35632"},{"key":"ref_99","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1007\/s13534-024-00375-2","article-title":"A segmentation-based algorithm for classification of benign and malignancy thyroid nodules with multi-feature information","volume":"14","author":"Zheng","year":"2024","journal-title":"Biomed. Eng. Lett."},{"key":"ref_100","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1049\/iet-ipr.2019.1540","article-title":"Multi-objectives optimisation of features selection for the classification of thyroid nodules in ultrasound images","volume":"14","author":"Aboudi","year":"2020","journal-title":"IET Image Process."},{"key":"ref_101","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.ultras.2011.11.003","article-title":"Non-invasive automated 3D thyroid lesion classification in ultrasound: A class of ThyroScan\u2122 systems","volume":"52","author":"Acharya","year":"2012","journal-title":"Ultrasonics"},{"key":"ref_102","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.patrec.2020.02.009","article-title":"An adaptive feature extraction model for classification of thyroid lesions in ultrasound images","volume":"131","author":"Mugasa","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_103","doi-asserted-by":"crossref","first-page":"64064","DOI":"10.1109\/ACCESS.2020.2982767","article-title":"Thyroid Nodule Ultrasound Image Classification Through Hybrid Feature Cropping Network","volume":"8","author":"Song","year":"2020","journal-title":"IEEE Access"},{"key":"ref_104","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s13534-023-00325-4","article-title":"A multi-task model for reliable classification of thyroid nodules in ultrasound images","volume":"14","author":"Xing","year":"2023","journal-title":"Biomed. Eng. Lett."},{"key":"ref_105","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1007\/s00530-024-01643-y","article-title":"Enhanced Multiview attention network with random interpolation resize for few-shot surface defect detection","volume":"31","author":"Li","year":"2025","journal-title":"Multimed. Syst."},{"key":"ref_106","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s00530-024-01642-z","article-title":"A content-style control network with style contrastive learning for underwater image enhancement","volume":"31","author":"Wang","year":"2025","journal-title":"Multimed. Syst."},{"key":"ref_107","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1007\/s00530-025-01850-1","article-title":"A weakly supervised pavement crack segmentation based on adversarial learning and transformers","volume":"31","author":"Apedo","year":"2025","journal-title":"Multimed. Syst."},{"key":"ref_108","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/s10278-017-9997-y","article-title":"Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network","volume":"30","author":"Chi","year":"2017","journal-title":"J. Digil. Imaging"},{"key":"ref_109","doi-asserted-by":"crossref","first-page":"52010","DOI":"10.1109\/ACCESS.2020.2980290","article-title":"Comparison Study of Radiomics and Deep Learning-Based Methods for Thyroid Nodules Classification Using Ultrasound Images","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_110","doi-asserted-by":"crossref","first-page":"2619","DOI":"10.1007\/s00330-016-4605-y","article-title":"Prospective validation of the ultrasound based TIRADS (Thyroid Imaging Reporting and Data System) classification: Results in surgically resected thyroid nodules","volume":"27","author":"Horvath","year":"2017","journal-title":"Eur. Radiol."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/17\/2761\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:35:21Z","timestamp":1760034921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/17\/2761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,24]]},"references-count":110,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["cancers17172761"],"URL":"https:\/\/doi.org\/10.3390\/cancers17172761","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,24]]}}}