**7. Conclusions**

In summary, radiomics is a hot topic and a rapidly evolving field in medical imaging in general. There are still some technological and ethical limitations of radiomics aforementioned are required to be solved. Nevertheless, increased studies have proved the potential applications of radiomics for both the research and clinical lactation field. For prediction, the radiomics is seemly satisfactory to predict lymph node metastasis, distance metastasis, tumor aggressiveness and extrathyroidal extension, and disease-free survival. While previous original studies consistently negated the value of US radiomics in predicting BRAF mutations in DTC. This result may need to be thoroughly discussed to determine the predictive value of other imaging techniques, such as CT and MRI, and provide a direct or indirect relationship between radiomics and tumor mutations of thyroid cancer in the future study. For diagnosis, the current findings may facilitate breakthroughs in thyroid cancer and nodule classification based on a radiomics approach. These studies demonstrated the usefulness of radiomics in discriminating benign and malignant lesions regardless of the image types (US, CT, or MRI). Further studies should address two important issues: (1) optimize the algorithm and models to improve the accuracy of external validation thereby enhance the diagnostic capacity of radiomics; (2) analyze multi-model or multi-parameters imaging data with a larger sample as well as increase the possibility of clinical transformation.

**Author Contributions:** Y.C. (Yuan Cao) and X.Z. wrote the first draft of the paper; Y.C. (Yuan Cao), J.M., Y.C. (Yue Cheng) collected and selected the CT, MRI, and U.S. images; Y.C. (Yuan Cao), X.Z., W.D. and Z.J. edited the paper; Z.J. designed the research. All authors have read and agreed to the published version of the manuscript.

**Funding:** This study was supported by the National Natural Science Foundation of China (Grant Nos. 81771812 and 81971595), the Innovation Spark Project of Sichuan University (Grant No. 2019SCUH0003), and the 1·3·5 Project for Disciplines of Excellence–Clinical Research Incubation Project, West China Hospital, Sichuan University (Grant No. 2020HXFH005).

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** No new data were created or analyzed in this study. Data sharing is not applicable to this article.

**Acknowledgments:** The author Yuan Cao thanks her friends Huaqian Zhang and Yun Bai for their guidance on scientific figures drawing.

**Conflicts of Interest:** The authors declare no conflict of interest.
