*1.2. Imaging Techniques for DTC Detection*

Additionally, the discrimination and identification of thyroid cancer nodules and thyroid benign nodules are important. In most cases, the initial presentation of thyroid cancer is a thyroid nodule [15], however, less than 10% of DTCs appear in the thyroid nodules [16]. Given various factors including age, sex, family history, exposure to radiation, and nodule size that could affect the shift from thyroid nodules to cancer [17], responding to this shift in a timely manner is necessary. Differentiating early malignant tumors from benign tumors and providing definite staging are key challenges for diagnosing and treating thyroid cancer. Moreover, estimating tumor progression or predicting prognosis precisely can significantly aid physicians in making clinical decisions regarding treatment strategies in patients with thyroid cancer. Palpation of the thyroid and cervical lymph nodes remains easiest and least expensive routine detection method, but this method is also the least sensitive [18,19]. In contrast, biopsy and histopathological examination are typically the diagnostic gold standard for thyroid cancer [20]. However, fine-needle aspiration biopsy (FNAB) usually samples a small portion of the lesions; thus, this method could provide limited information regarding tumor heterogeneity and may lead to missed diagnoses. Notably, a proportion of patients are still intractable to invasive examination for screening making it difficult to repeat pathological assessments. Noninvasive imaging examinations including high-resolution ultrasound, magnetic resonance imaging (MRI), computed tomography (CT), single-photon emission computed tomography (SPECT), positron emission tomography (PET), and PET/CT, are also playing an increasingly important role in initial tumor screening, staging, restaging, management, and posttreatment follow-up [21]. Of these, high-resolution ultrasound remains the sole fundamental imaging method in the diagnosis and screening of thyroid nodules and cancer [22]. High-resolution ultrasound is a safe noninvasive imaging technique that could aid in enhancing the early detection of pathologies [23].

Ultrasound is based on the pulse-echo principle that makes it possible to determine the thyroid size, location, number, and morphology of individual nodules, and occult nodules omitted by physical examination [18], and present these findings in a single cross-sectional B-scan image. The suspicious ultrasound features of malignant thyroid nodules exhibit the following characteristics: solid nodule structure, hypoechogenicity, taller-than-wide shape, irregular margin, microcalcification, and invasion of surrounding tissue [18,24]. Nodules that present pure cystic or cystic components that represent greater

than 50% of nodule volume tend to be benign [25]. Despite its widespread availability and radiation-free features, the diagnosis significantly relies on the radiologists' experience and subjective judgments, which limits the ability to make an objective diagnosis. Although neck ultrasound is the primary method used to investigate palpable thyroid masses, suspicious neck masses are typically initially screened through CT or MRI examination. Some features may be specific, whereas others may be incidental findings [26]. CT and MRI provide evidence for detecting lymph node metastasis as well as evaluating the invasion of adjacent tissue and organs with the features of cross-sectional imaging and reconstruction function [27]. It has been reported that the CT use rate in the examination of the neck and cervical spine has increased rapidly and is greater than that of ultrasound in the United States [28]. A previous study also verified the value of CT in detecting incidental thyroid nodules and hypothesized that CT imaging may be the current trend rather than ultrasound [29]. Nevertheless, CT also has an obvious limitation given that contrast-enhanced CT with iodinated contrast medium would delay subsequent radioactive iodine therapy [30]. Conversely, based on gadolinium-based contrast agents, MRI can be employed without interfering with radioiodine administration despite the requirement for a longer scan time. In addition, with its higher soft-tissue contrast, MRI combined with diffusion-weighted imaging (DWI) sequences could provide qualitative and quantitative information about tumor lesions at the cell level. DWI has been applied to assess the differentiation of benign and malignant thyroid tumors for several years [31,32]. A recent study verified the potential advantages of DWI in predicting aggressive histological features of thyroid carcinoma [33].

Nuclear medicine examinations have been used in the diagnosis, treatment, and surgical management of thyroid disease. Given the high avidity of radioiodine in functioning thyroid tissues, 131I whole-body scintigraphy (WBS) has a high value in tumor and metastasis detection [34]. WBS is also regarded as a routine diagnostic procedure for DTC patients with thyroidectomy [35]. However, WBS cannot provide a precise anatomic location, which greatly constrains its potential value. Compared with WBS, SPECT/CT not only enables anatomic localization of the tumor but also has higher sensitivity (50%) and specificity (100%) [36]. Besides, PET/CT or PET/MRI is also a relatively high sensitivity imaging technique in the evaluation of recurrent or metastatic tumors. A meta-analysis calculated that the pooled sensitivity was as high as 93.5% for PET/CT in detecting recurrent or metastatic DTC [37]. In addition, PET/CT can detect 21.2% of lymph nodes and soft tissue lesions that were missed by ultrasound [38]. Compared with PET/CT, PET/MRI has low radiation, but the high costs of this method should also be considered. Although some reports have demonstrated the value of the nuclear medicine approach applied in thyroid cancer, underlying issues, such as cost-effectiveness, universality, and radiation, require further discussion. Notwithstanding the above strengths, the current imaging technologies for tumor classification and prediction remain limited. Radiomics is an emerging field that involves segmenting lesions, extracting quantitative radiology features from medical images, and constructing models to classify or predict disease. The current review focuses on the radiomics characteristics of DTC and reviews the classification and prediction ability of radiomics for DTC.
