Radiomics in the Diagnosis of Thyroid Nodules

The thyroid nodules (TNs) are widespread throughout the world: according to the pathological studies, they can be found in 50–60% of adults. Currently, ultrasound, computed tomography, magnetic resonance imaging and radionuclide diagnostics, such as positron emission tomography with computed tomography, are usually used to diagnose TNs in clinic. These techniques are mainly used to diagnose the nodile benignity and malignancy, the degree of invasion into adjacent tissues and metastases to lymph nodes. Thanks to the development of artificial intelligence, machine learning and the improvement of medical imaging equipment, radiomics has become a popular area of research in recent years. It allowes to obtain various quantitative characteristics from medical images, highlighting invisible features and significantly expanding the possibilities of identifying and predicting. Radiomics has a high potential in detecting and predicting TNs. We present the information on the development and workflow of radiomics. The article summarizes the application of various imaging techniques to identify benign and malignant TNs, determine invasiveness and metastases to lymph nodes, as well as some new advances in the field of molecular level and deep learning. The disadvantages of radiomics method are also given as well as prospects for its further development.

1. Mironov SP, Sergienko VB. Scintigraphy in thyroid nodular pathology. Journal of Radiology and Nuclear Medicine. 2022; 103(4–6): 108–16 (in Russ). https://doi.org/10.20862/0042-4676-2022-103-4-6-108-116.

2. Stanyakina EE, Romanov IS, Gogieva EK, et al. The effectiveness of the method for determining the level of thyroglobulin in needle washouts of fine-needle aspiration biopsy in the differential diagnosis of metastases of highly differentiated thyroid cancer in the lymph nodes of the neck. Head and Neck Tumors. 2022; 12(3): 10–6 (in Russ). https://doi.org/10.17650/2222-1468-2022-12-3-10-16.

3. Gordienko VP, Poberezhestsky AV. Thyroid cancer in the Far Eastern Federal District of Russia. Pacific Medical Journal. 2022; 4: 63–71 (in Russ). https://doi.org/10.34215/1609-1175-2022-4-63-71.

4. Gul M, Bonjoc KC, Gorlin D, et al. Diagnostic utility of radiomics in thyroid and head and neck cancers. Front Oncol. 2021; 11: 639326. https://doi.org/10.3389/fonc.2021.639326.

5. Sun L, Li M. TSH suppression therapy may affect bone health. How to manage differentiated thyroid cancer scientifically? Chinese General Practice. 2021; 24(8): 941–6. https://doi.org/10.12114/j.issn.1007-9572.2021.00.074.

6. Grani G, Sponziello M, Pecce V, et al. Contemporary thyroid nodule evaluation and management. J Clin Endocrinol Metab. 2020; 105(9): 2869–83. https://doi.org/10.1210/clinem/dgaa322.

7. Tessler FN, Middleton WD, Grant EG, et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol. 2017; 14(5): 587–95. https://doi.org/10.1016/j.jacr.2017.01.046.

8. Fresilli D, David E, Pacini P, et al. Thyroid nodule characterization: how to assess the malignancy risk. Update of the literature. Diagnostics (Basel). 2021; 11(8): 1374. https://doi.org/10.3390/diagnostics11081374.

9. Liang J, Huang X, Hu H, et al. Predicting malignancy in thyroid nodules: radiomics score versus 2017 American College of Radiology thyroid imaging, reporting and data system. Thyroid. 2018; 28(8): 1024–33. https://doi.org/10.1089/thy.2017.0525.

10. Yoon J, Lee E, Kang SW, et al. Implications of US radiomics signature for predicting malignancy in thyroid nodules with indeterminate cytology. Eur Radiol. 2021; 31(7): 5059–67. https://doi.org/10.1007/s00330-020-07670-3.

11. Shi Y, Jiang Y, Wang J, et al. Prediction of benign and malignant nodules of thyroid TI-RADS 4~5 based on ultrasonographic nomogram. Chin J Ultrasound Med. 2021; 37(12): 1328–32.

12. Wang Q, Shi Q, Xian X, et al. Application of machine learning in differential diagnosis of nodular hashimoto thyroiditis and thyroid micropapillary carcinoma based on small sample thyroid high b-value diffusion-weighted imaging omics. Chin J Med Imaging. 2021; 29(11): 1064–9.

13. Xia L, Liang Z, Yao G, et al. Value of support vector machine model based on magnetic resonance texture analysis for differential diagnosis of thyroid nodule larger than 1 cm. Shandong Med J. 2021; 61(31): 77–80.

14. Wu Y, Jin J, Feng Y. Analysis of the texture features of enhanced CT in the identification of benign and malignant thyroid nodules. J Southeast Univ (Medical Edition). 2016; 35(1): 112–6.

15. Guo W, Luo H, Zhao Y, et al. CT texture analysis technology to identify benign and malignant thyroid nodules feasibility study. Int J Med Radiol. 2017; 40(1): 3–5.

16. Hu Y, Huang Z, Xie Y, Wang X. Value of first-order ct texture analysis in differentiating benign and malignant thyroid nodules. J Clin Radiol. 2019; 38(3): 422–5.

17. Zhang DAW. Differential diagnosis of benign and malignant thyroid micronodules based on CT image omics. Anhui Medical University. 2020; 56(4): 652655.

18. Du D, Li X, Liu B, et al. CT image omics of thyroid adenoma and the diagnostic value of papillary carcinoma. J Anhui Med Univ. 2019; 54(6): 950–3.

19. Zhou S, Liu T, Zhou J. Preliminary study on application of radiomics in thyroid carcinoma. Oncoradiology. 2017; 26(2): 102–5.

20. Wang X, Agyekum EA, Ren Y, et al. A radiomic nomogram for the ultrasound-based evaluation of extrathyroidal extension in papillary thyroid carcinoma. Front Oncol. 2021; 11: 625646. https://doi.org/10.3389/fonc.2021.625646.

21. Tong Y, Li J, Huang Y, et al. Ultrasound-based radiomic nomogram for predicting lateral cervical lymph node metastasis in papillary thyroid carcinoma. Acad Radiol. 2021; 28(12): 1675–84. https://doi.org/10.1016/j.acra.2020.07.017.

22. Zhang H, Zhang H, Shu Z, et al. The value of MRI T2WI image texture analysis in predicting cervical lymph node metastasis of thyroid papillary carcinoma. Chin J Clin Imaging. 2020; 31(8): 568–71.

23. Yao X, Zhou Q, Zhang Z, Zhou J. Value of MRI texture combined with cripto-1 and SOX2 proteins in the diagnosis of cervical lymph node metastasis of thyroid papillary carcinoma. Chin J Med Phys. 2022; 39(2): 224–8.

24. 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. Radiol Med. 2021; 126(10): 1312–7. https://doi.org/10.1007/s11547-021-01393-1.

25. Shen S, Han D, Zhao L, et al. Prediction of lymph node metastasis in the central group based on small ripple analysis of CT venous phase image of thyroid papillary carcinoma nodules. Chin J Radiol. 2019; 11: 946–51.

26. Su GY, Xu XQ, Zhou Y, et al. Texture analysis of dual-phase contrast-enhanced CT in the diagnosis of cervical lymph node metastasis in patients with papillary thyroid cancer. Acta Radiol. 2021; 62(7): 890–6. https://doi.org/10.1177/0284185120946711.

27. He J, Lu Q, Xu X, Hu S. Study on the value of CT imaging features in predicting cervical lymph node metastasis of papillary thyroid. J Shanghai Jiao Tong Univ (Medical Science). 2021; 41(9): 1233–9.

28. Zhao H, Ye J, Duan S, et al. CT image omics of thyroid papillary carcinoma and adenoma identify. Chin J Med Imaging. 2021; 27(2): 102–6.

29. Zhou Y, Su GY, Hu H, Ge YQ. Diagnosis of cervical lymph node metastasis of papillary thyroid carcinoma based on dual energy CT iodogram. J Int Med Radiol. 2021; 44(1): 119.

30. Zhou H, Jin Y, Dai L, et al. Differential diagnosis of benign and malignant thyroid nodules using deep learning radiomics of thyroid ultrasound images. Eur J Radiol. 2020; 127: 108992. https://doi.org/10.1016/j.ejrad.2020.10899.