Share：
Share this content in WeChat
X
[Chinese][PDF]371
• Review •
Research progress in radiomics for qualitative diagnosis of thyroid nodules
CHEN Lijun  WANG Lin 

Cite this article as: CHEN L J, WANG L. Research progress in radiomics for qualitative diagnosis of thyroid nodules[J]. Chin J Magn Reson Imaging, 2025, 16(2): 165-171. DOI:10.12015/issn.1674-8034.2025.02.027.


[Abstract] Thyroid nodule (TN) is one of the most common endocrine disorders, and its prevalence increases with age. Early differentiation of benign and malignant nodules is crucial for patient treatment and prognosis, and has significant clinical implications. Traditional imaging methods play an irreplaceable role in the diagnosis and evaluation of TN. However, due to their subjectivity, they often fail to provide comprehensive biological characteristics. Radiomics, by extracting a large number of medical imaging features and combining machine learning (ML) and statistical analysis methods, can identify and quantify disease characteristics, offering new perspectives for the prediction, evaluation, and treatment of TN. This article summarized the latest research progress in radiomics for the qualitative diagnosis of TN, focusing on the application of radiomics methods based on ultrasound, CT, and MRI in TN. Additionally, it discussed the challenges faced by radiomics in TN diagnosis and treatment, emphasizing its importance in improving clinical decision-making, in order to provide references for personalized and precise management of TN.
[Keywords] thyroid nodules；radiomics；ultrasonography；magnetic resonance imaging；positron emission tomography

CHEN Lijun1, 2   WANG Lin3*  

1 Clinical Medicine College, Gansu University of Traditional Chinese Medicine, Lanzhou 730000, China

2 Department of Radiology, Gansu Provincial People's Hospital, Lanzhou 730050, China

3 Department of Radiology, Affiliated Hospital of Gansu University of Traditional Chinese Medicine, Lanzhou 730000, China

Corresponding author: WANG L, E-mail: tedyong@163.com

Conflicts of interest   None.

Received  2024-07-25
Accepted  2024-11-10
DOI: 10.12015/issn.1674-8034.2025.02.027
Cite this article as: CHEN L J, WANG L. Research progress in radiomics for qualitative diagnosis of thyroid nodules[J]. Chin J Magn Reson Imaging, 2025, 16(2): 165-171. DOI:10.12015/issn.1674-8034.2025.02.027.

[1]
LIN P, HE R Q, HUANG Z G, et al. Role of global aberrant alternative splicing events in papillary thyroid cancer prognosis[J]. Aging, 2019, 11(7): 2082-2097. DOI: 10.18632/aging.101902.
[2]
GUO J F, SONG X Y, SHEN T C, et al. The value of predicting cervical lymph node metastasis in papillary thyroid carcinoma based on multimodal radiomics combined with machine learning model[J]. Radiologic Practice, 2024, 39(9): 1152-1157. DOI: 10.13609/j.cnki.1000-0313.2024.09.006.
[3]
CHEN X J, HUANG L J, MAO F, et al. Value of CEUS features in diagnosing thyroid nodules with halo sign on B-mode ultrasound[J/OL]. BMC Med Imaging, 2023, 23(1): 11 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/36681788/. DOI: 10.1186/s12880-023-00966-y.
[4]
KOBALY K, KIM C S, MANDEL S J. Contemporary management of thyroid nodules[J/OL]. Annu Rev Med, 2022, 73: 517-528 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/34416120/. DOI: 10.1146/annurev-med-042220-015032.
[5]
Chinese Society of Ultrasound Medicine Superficial Organs and vascular Group, China Thyroid and Breast Ultrasound Artificial Intelligence Alliance. 2020 Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS[J]. Chin J Ultrason, 2021, 30(3): 185-200. DOI: 10.3760/cma.j.cn131148-20210205-00092.
[6]
Thyroid Tumor Ablation Experts Group of Chinese Medical Doctor Association, Chinese Association of Thyroid Oncology, Interventional Ultrasound Committee of Chinese College of Interventionalists, et al. Expert consensus on thermal ablation for thyroid benign nodes, microcarcinoma and metastatic cervical lymph nodes (2018 edition)[J]. China Cancer, 2018, 27(10): 768-773. DOI: 10.11735/j.issn.1004-0242.2018.10.A006.
[7]
LEE J Y, BAEK J H, HA E J, et al. 2020 imaging guidelines for thyroid nodules and differentiated thyroid cancer: Korean society of thyroid radiology[J]. Korean J Radiol, 2021, 22(5): 840-860. DOI: 10.3348/kjr.2020.0578.
[8]
SOELBERG K K, BONNEMA S J, BRIX T H, et al. Risk of malignancy in thyroid incidentalomas detected by 18F-fluorodeoxyglucose positron emission tomography: a systematic review[J]. Thyroid, 2012, 22(9): 918-925. DOI: 10.1089/thy.2012.0005.
[9]
JAHANGIR M Z BIN, HOSSAIN R, ISLAM R, et al. Introduction to medical imaging informatics[EB/OL]. 2023: arXiv: 2306.00421. http://arxiv.org/abs/2306.00421
[10]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[11]
ZHAO Y G, ZHU Z, YU Z, et al. Development and Application of Medical Imaging Analysis Platform Based on Radiomics and Machine Learning Technologies[J]. Chinese Journal of Medical Instrumentation, 2023, 47(3): 272-277. DOI: 10.3969/j.issn.1671-7104.2023.03.008.
[12]
MAHMOOD T, SABA T, REHMAN A, et al. Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography[J/OL]. Expert Syst Appl, 2024, 249: 123747 [2024-07-24]. https://www.sciencedirect.com/science/article/abs/pii/S0957417424006134. DOI: 10.1016/j.eswa.2024.123747.
[13]
CHU Z P, SINGH S, SOWMYA A. Robust automated tumour segmentation network using 3D direction-wise convolution and transformer[J]. J Imaging Inform Med, 2024, 37(5): 2444-2453. DOI: 10.1007/s10278-024-01131-9.
[14]
YANG T Y, ZHOU L Q, LI D, et al. An improved CNN-based thyroid nodule screening algorithm in ultrasound images[J/OL]. Biomed Signal Process Contr, 2024, 87: 105371 [2024-07-24]. https://www.sciencedirect.com/science/article/abs/pii/S1746809423008042. DOI: 10.1016/j.bspc.2023.105371.
[15]
PUDJIHARTONO N, FADASON T, KEMPA-LIEHR A W, et al. A review of feature selection methods for machine learning-based disease risk prediction[J/OL]. Front Bioinform, 2022, 2: 927312 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/36304293/. DOI: 10.3389/fbinf.2022.927312.
[16]
GUIDO R, FERRISI S, LOFARO D, et al. An overview on the advancements of support vector machine models in healthcare applications: a review[J/OL]. Information, 2024, 15(4): 235 [2024-07-24]. https://www.mdpi.com/2078-2489/15/4/235. DOI: 10.3390/info15040235.
[17]
KUMAR V, GADDAM M, MOUSTAFA A, et al. The utility of artificial intelligence in the diagnosis and management of pancreatic cancer[J/OL]. Cureus, 2023, 15(11): e49560 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/38156176/. DOI: 10.7759/cureus.49560.
[18]
PARK V Y, LEE E, LEE H S, et al. Combining radiomics with ultrasound-based risk stratification systems for thyroid nodules: an approach for improving performance[J]. Eur Radiol, 2021, 31(4): 2405-2413. DOI: 10.1007/s00330-020-07365-9.
[19]
ZHU R Y, FAN X, QIU J H, et al. Comparative study of CT radiomics and conventional imaging for predicting cervical lymph node metastasis in papillary thyroid cancer[J]. J Imag Res Med Appl, 2024, 8(18): 18-22. DOI: 10.3969/j.issn.2096-3807.2024.18.006.
[20]
GAO X F. Study on MRI imageology assisted diagnosis of benign and malignant thyroid nodules[D].Changchun: Jilin University, 2024. DOI: 10.27162/d.cnki.gjlin.2024.006495.
[21]
DENG C W. Advances on radiomics in 18F-FDG PET/CT for thyroid cancer[J]. J Tongji Univ Med Sci, 2020, 41(6): 801-804. DOI: 10.16118/j.1008-0392.2020.06.020.
[22]
HUSSEIN M A, ELESAWY Y F, GHOWEBA D E A A R, et al. Correlation of ultrasound features in the TIRADS scoring system with cytological findings in the FNAC of thyroid nodules and their association with the metabolic status[J/OL]. Egypt J Intern Med, 2024, 36(1): 29 [2024-07-24]. https://ejim.springeropen.com/articles/10.1186/s43162-024-00290-z. DOI: 10.1186/s43162-024-00290-z.
[23]
XIA M W, SONG F L, ZHAO Y F, et al. Ultrasonography-based radiomics and computer-aided diagnosis in thyroid nodule management: performance comparison and clinical strategy optimization[J/OL]. Front Endocrinol, 2023, 14: 1140816 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/37251675/. DOI: 10.3389/fendo.2023.1140816.
[24]
LUO P, FANG Z, ZHANG P, et al. Radiomics score combined with ACR TI-RADS in discriminating benign and malignant thyroid nodules based on ultrasound images: a retrospective study[J/OL]. Diagnostics, 2021, 11(6): 1011 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/34205943/. DOI: 10.3390/diagnostics11061011.
[25]
CHEN Z, ZHAN W T, WU Z J, et al. The ultrasound-based radiomics-clinical machine learning model to predict papillary thyroid microcarcinoma in TI-RADS 3 nodules[J]. Transl Cancer Res, 2024, 13(1): 278-289. DOI: 10.21037/tcr-23-1375.
[26]
POZDEYEV N, DIGHE M, BARRIO M, et al. Thyroid cancer polygenic risk score improves classification of thyroid nodules as benign or malignant[J]. J Clin Endocrinol Metab, 2024, 109(2): 402-412. DOI: 10.1210/clinem/dgad530.
[27]
LI J, LI S Y, ZHOU W, et al. Enhancing malignancy prediction in thyroid nodules: a multimodal ultrasound radiomics approach in TI-RADS category 4 lesions[J]. J Clin Ultrasound, 2024, 52(5): 511-521. DOI: 10.1002/jcu.23662.
[28]
REN J Y, LIN J J, LV W Z, et al. A comparative study of two radiomics-based blood flow modes with thyroid imaging reporting and data system in predicting malignancy of thyroid nodules and reducing unnecessary fine-needle aspiration rate[J]. Acad Radiol, 2024, 31(7): 2739-2752. DOI: 10.1016/j.acra.2024.02.007.
[29]
LIU A X, CHEN C C, HUANG F G, et al. Application progress of ultrasound imaging in thyroid nodules[J]. J Youjiang Med Univ Natl, 2024, 46(1): 132-136. DOI: 10.3969/j.issn.1001-5817.2024.01.023.
[30]
LI G, MA S, ZHANG F, et al. The predictive models based on multimodality ultrasonography for the differential diagnosis of thyroid nodules smaller than 10 mm[J/OL]. Br J Radiol, 2023, 96(1149): 20221120 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/37427752/. DOI: 10.1259/bjr.20221120.
[31]
LI Z Y, ZHANG H M, CHEN W Y, et al. Contrast-enhanced CT-based radiomics for the differentiation of nodular goiter from papillary thyroid carcinoma in thyroid nodules[J/OL]. Cancer Manag Res, 2022, 14: 1131-1140 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/35342307/. DOI: 10.2147/CMAR.S353877.
[32]
MOON J, LEE J H, ROH J, et al. Contrast-enhanced CT-based radiomics for the differentiation of anaplastic or poorly differentiated thyroid carcinoma from differentiated thyroid carcinoma: a pilot study[J/OL]. Sci Rep, 2023, 13(1): 4562 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/36941287/. DOI: 10.1038/s41598-023-31212-8.
[33]
DONG L J, ZI X Y, LI Q W, et al. The value of diagnostic nomogram based on CT radiomics for the preoperative differentiation between thyroid papillary carcinoma and nodular goiter[J]. J Clin Radiol, 2023, 42(9): 1409-1416. DOI: 10.13437/j.cnki.jcr.2023.09.029.
[34]
XU H, WANG X M, GUAN C Q, et al. Value of whole-thyroid CT-based radiomics in predicting benign and malignant thyroid nodules[J/OL]. Front Oncol, 2022, 12: 828259 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/35600338/. DOI: 10.3389/fonc.2022.828259.
[35]
WU X X, LI J J, MAO N, et al. A radiomics nomogram based on computed tomography for predicting benign and malignant thyroid nodules[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2020, 34(3): 32-39. DOI: 10.6040/j.issn.1673-3770.1.2020.028.
[36]
ANANTHAKRISHNAN L, KULKARNI N, TOSHAV A. Dual-energy computed tomography: integration into clinical practice and cost considerations[J]. Radiol Clin North Am, 2023, 61(6): 963-971. DOI: 10.1016/j.rcl.2023.05.003.
[37]
DURMA A D, SARACYN M, ZEGADŁO A, et al. Utility of non-contrast Dual Energy Computed Tomography in diagnosis of differentiated thyroid cancer - two case study[J/OL]. Cancer Imaging, 2023, 23(1): 39 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/37072868/. DOI: 10.1186/s40644-023-00555-w.
[38]
WEI Q J, LIN S C, HUANG F L, et al. Value of dual-energy CT radiomics in the qualitative diagnosis of thyroid nodules[J]. China Med Devices, 2022, 37(12): 87-90. DOI: 10.3969/j.issn.1674-1633.2022.12.017.
[39]
LU S Y, REN Y Z, LU C, et al. Radiomics features from whole thyroid gland tissue for prediction of cervical lymph node metastasis in the patients with papillary thyroid carcinoma[J]. J Cancer Res Clin Oncol, 2023, 149(14): 13005-13016. DOI: 10.1007/s00432-023-05184-1.
[40]
XU X Q, ZHOU Y, SU G Y, et al. Iodine maps from dual-energy CT to predict extrathyroidal extension and recurrence in papillary thyroid cancer based on a radiomics approach[J]. AJNR Am J Neuroradiol, 2022, 43(5): 748-755. DOI: 10.3174/ajnr.A7484.
[41]
ZHOU Y, SU G Y, HU H, et al. Radiomics from primary tumor on dual-energy CT derived iodine maps can predict cervical lymph node metastasis in papillary thyroid cancer[J/OL]. Acad Radiol, 2022, 29(Suppl 3): S222-S231 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/34366279/. DOI: 10.1016/j.acra.2021.06.014.
[42]
YANG Z X, WANG X F, TAO T, et al. Diagnostic value of contrast-enhanced ultrasonography in the preoperative evaluation of lymph node metastasis in papillary thyroid carcinoma: a single-center retrospective study[J/OL]. BMC Surg, 2023, 23(1): 325 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/37875825/. DOI: 10.1186/s12893-023-02199-w.
[43]
LI Y N, ZHANG Z C. A case of iodine-induced hyperthyroidism caused by iodine-containing contrast media[J]. Chinese Medical Care Repository, 2022, 4(1): E104-E104. DOI: 10.3760/cma.j.cmcr.2022.e00104.
[44]
SOHN S Y, INOUE K, BASHIR M T, et al. Thyroid dysfunction risk after iodinated contrast media administration: a prospective longitudinal cohort analysis[J/OL]. J Clin Endocrinol Metab, 2024: dgae304 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/38700099/. DOI: 10.1210/clinem/dgae304.
[45]
HU W J, WANG H, WEI R, et al. MRI-based radiomics analysis to predict preoperative lymph node metastasis in papillary thyroid carcinoma[J]. Gland Surg, 2020, 9(5): 1214-1226. DOI: 10.21037/gs-20-479.
[46]
HE P, YANG Q, LUO H H, et al. Value of radiomics model based on T1WI, T2WI and enhanced T1WI in differentiating benign and malignant thyroid nodules[J]. J China Clin Med Imag, 2023, 34(12): 871-877. DOI: 10.12117∕jccmi.2023.12.008.
[47]
XU H J, YANG Q, HE P, et al. Value of radiomics models based on MRI diffusion weighted imaging and apparent diffusion coefficient in differentiating benign and malignant thyroid nodules[J]. Natl Med J China, 2023, 103(41): 3279-3286. DOI: 10.3760/cma.j.cn112137-20230913-00453.
[48]
WANG Q J, CHENG L Q, FU Y G, et al. Differentiation between hashimoto's thyroiditis nodule and papillary thyroid microcarcinoma: application of MRI radiomics-based machine learning[J]. Chin J Med Imag, 2023, 31(3): 213-219. DOI: 10.3969/j.issn.1005-5185.2023.03.005.
[49]
QIN H, QUE Q, LIN P, et al. Magnetic resonance imaging (MRI) radiomics of papillary thyroid cancer (PTC): a comparison of predictive performance of multiple classifiers modeling to identify cervical lymph node metastases before surgery[J]. Radiol Med, 2021, 126(10): 1312-1327. DOI: 10.1007/s11547-021-01393-1.
[50]
HU W J, ZHUANG Y Z, TANG L, et al. Preoperative cervical lymph node metastasis prediction in papillary thyroid carcinoma: a noninvasive clinical multimodal radiomics (CMR) nomogram analysis[J/OL]. J Oncol, 2023, 2023: 3270137 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/36936372/. DOI: 10.1155/2023/3270137.
[51]
HU W J, SONG B, XIE X L, et al. Radiomics based on multiparametric MRI for preoperative prediction of lymph node metastasis in papilla-ry thyroid carcinoma[J]. Radiol Pract, 2023, 38(7): 863-867. DOI: 10.13609/j.cnki.1000-0313.2023.07.009.
[52]
PURBHOO K, VANGU M D T. Normal variants and pitfalls of 18F-FDG PET/CT imaging in pediatric oncology[J/OL]. Front Nucl Med, 2022, 2: 825891 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/39354970/. DOI: 10.3389/fnume.2022.825891.
[53]
SUH H Y, CHOI H, CHO S W, et al. FDG uptake reflects an immune-enriched subtype of thyroid cancer: clinical implications of imaging-based molecular characterization[J]. Cancer Med, 2023, 12(16): 17068-17077. DOI: 10.1002/cam4.6350.
[54]
GIOVANELLA L, MILAN , PICCARDO A, et al. Radiomics analysis improves 18FDG PET/CT-based risk stratification of cytologically indeterminate thyroid nodules[J]. Endocrine, 2022, 75(1): 202-210. DOI: 10.1007/s12020-021-02856-1.
[55]
DE KOSTER E J, NOORTMAN W A, MOSTERT J M, et al. Quantitative classification and radiomics of[18F]FDG-PET/CT in indeterminate thyroid nodules[J]. Eur J Nucl Med Mol Imaging, 2022, 49(7): 2174-2188. DOI: 10.1007/s00259-022-05712-0.
[56]
ABOU KARAM G, MALHOTRA A. PET/CT may assist in avoiding pointless thyroidectomy in indeterminate thyroid nodules: a narrative review[J/OL]. Cancers, 2023, 15(5): 1547 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/36900338/. DOI: 10.3390/cancers15051547.
[57]
KO W S, KIM S J. Prediction of malignant thyroid nodules using 18 F-FDG PET/CT-based radiomics features in thyroid incidentalomas[J]. Clin Nucl Med, 2023, 48(6): 497-504. DOI: 10.1097/RLU.0000000000004637.
[58]
DONDI F, PASINETTI N, GATTA R, et al. 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 final diagnosis of thyroid incidentalomas[J/OL]. J Clin Med, 2022, 11(3): 615 [2024-07-24]. https://pubmed.ncbi.nlm.nih.gov/35160067/. DOI: 10.3390/jcm11030615.
[59]
DONDI F, GATTA R, TREGLIA G, et al. Application of radiomics and machine learning to thyroid diseases in nuclear medicine: a systematic review[J]. Rev Endocr Metab Disord, 2024, 25(1): 175-186. DOI: 10.1007/s11154-023-09822-4.
[60]
ZHANG L Y, WANG Y M, PENG Z Y, et al. The progress of multimodal imaging combination and subregion based radiomics research of cancers[J]. Int J Biol Sci, 2022, 18(8): 3458-3469. DOI: 10.7150/ijbs.71046.

PREV Advances in multi-sequence MRI for differentiating high-grade glioma and brain metastasis
NEXT Application of blood flow analysis method based on computational fluid dynamics and 4D Flow MRI in diagnosis and treatment of cardiovascular and cerebrovascular diseases
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn