Predictive value for malignancy in the finding of microcalcifications on ultrasonography of thyroid nodules

Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules

BACKGROUND

A key challenge in thyroid carcinoma is preoperatively diagnosing malignant thyroid nodules. The purpose of this study was to compare the classification performance of linear and nonlinear machine-learning algorithms for the evaluation of thyroid nodules using pathological reports as reference standard.

METHODS

Ethical approval was obtained for this retrospective analysis, and the informed consent requirement was waived. A total of 1179 thyroid nodules (training cohort, n = 700; validation cohort, n = 479) were confirmed by pathological reports or fine-needle aspiration (FNA) biopsy. The following ultrasonography (US) featu res were measured for each nodule: size (maximum diameter), margins, shape, aspect ratio, capsule, hypoechoic halo, composition, echogenicity, calcification pattern, vascularity, and cervical lymph node status. We analyzed five nonlinear and three linear machine-learning algorithms. The diagnostic performance of each algorithm was compared by using the area under the curve (AUC) of the receiver operating characteristic curve. We repeated this process 1000 times to obtain the mean AUC and 95% confidence interval (CI).

RESULTS

Overall, nonlinear machine-learning algorithms demonstrated similar AUCs compared with linear algorithms. The Random Forest and Kernel Support Vector Machines algorithms achieved slightly greater AUCs in the validation cohort (0.954, 95% CI: 0.939-0.969; 0.954 95%CI: 0.939-0.969, respectively) than other algorithms.

CONCLUSIONS

Overall, nonlinear machine-learning algorithms share similar performance compared with linear algorithms for the evaluation the malignancy risk of thyroid nodules.

European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults: The EU-TIRADS

Thyroid ultrasound (US) is a key examination for the management of thyroid nodules. Thyroid US is easily accessible, noninvasive, and cost-effective, and is a mandatory step in the workup of thyroid nodules. The main disadvantage of the method is that it is operator dependent. Thyroid US assessment of the risk of malignancy is crucial in patients with nodules, in order to select those who should have a fine needle aspiration (FNA) biopsy performed. Due to the pivotal role of thyroid US in the management of patients with nodules, the European Thyroid Association convened a panel of international experts to set up European guidelines on US risk stratification of thyroid nodules. Based on a review of the literature and on the American Association of Clinical Endocrinologists, American Thyroid Association, and Korean guidelines, the panel created the novel European Thyroid Imaging and Reporting Data System, called EU-TIRADS. This comprises a thyroid US lexicon; a standardized report; definitions of benign and low-, intermediate-, and high-risk nodules, with the estimated risks of malignancy in each category; and indications for FNA. Illustrated by numerous US images, the EU-TIRADS aims to serve physicians in their clinical practice, to enhance the interobserver reproducibility of descriptions, and to simplify communication of the results.

Is Ultrasonography More Sensitive Than Computed Tomography for Identifying Calcifications in Thyroid Nodules?

OBJECTIVES

The primary objective of this study was to evaluate the difference and agreement between ultrasonography (US) and computed tomography (CT) for identifying calcifications in thyroid nodules.

METHODS

Data from the medical records of 20,248 patients were reviewed for preoperative diagnostic investigations and postoperative pathologic diagnoses. In total, 5247 records were selected for analysis based on the presence of calcifications reported in any of the following 3 modes: US, CT, and pathologic analysis. All 5247 patients underwent US examinations, whereas 3827 underwent cervical CT examinations. All patients had a postoperative pathologic diagnosis serving as a reference. The value of US for identification of calcifications and prediction of malignancy was analyzed on the basis of the entire cohort of 5247 records, whereas that of CT was based on 3827 records. The agreement between US and CT was analyzed on the basis of the 3827 common records.

RESULTS

Of the 5247 patients who underwent US, 4855 (92.5%) were found to have calcifications, whereas of the 3827 patients who underwent CT, 2040 (53.3%) were found to have calcifications (P < .0005). Among the 404 cases with calcifications reported by pathologic analysis, the agreement rate between US and pathologic findings was significantly higher than that between CT and pathologic findings (87.9% versus 81.9%, respectively; P = .018).

CONCLUSIONS

US is more sensitive and accurate than CT for detecting calcifications in thyroid nodules. Hence, US is recommended as the preferred imaging modality for calcification detection in thyroid nodules.

AMERICAN ASSOCIATION OF CLINICAL ENDOCRINOLOGISTS, AMERICAN COLLEGE OF ENDOCRINOLOGY, AND ASSOCIAZIONE MEDICI ENDOCRINOLOGI MEDICAL GUIDELINES FOR CLINICAL PRACTICE FOR THE DIAGNOSIS AND MANAGEMENT OF THYROID NODULES--2016 UPDATE

Thyroid nodules are detected in up to 50 to 60% of healthy subjects. Most nodules do not cause clinically significant symptoms, and as a result, the main challenge in their management is to rule out malignancy, with ultrasonography (US) and fine-needle aspiration (FNA) biopsy serving as diagnostic cornerstones. The key issues discussed in these guidelines are as follows: (1) US-based categorization of the malignancy risk and indications for US-guided FNA (henceforth, FNA), (2) cytologic classification of FNA samples, (3) the roles of immunocytochemistry and molecular testing applied to thyroid FNA, (4) therapeutic options, and (5) follow-up strategy. Thyroid nodule management during pregnancy and in children are also addressed. On the basis of US features, thyroid nodules may be categorized into 3 groups: low-, intermediate-and high-malignancy risk. FNA should be considered for nodules ≤10 mm diameter only when suspicious US signs are present, while nodules ≤5 mm should be monitored rather than biopsied. A classification scheme of 5 categories (nondiagnostic, benign, indeterminate, suspicious for malignancy, or malignant) is recommended for the cytologic report. Indeterminate lesions are further subdivided into 2 subclasses to more accurately stratify the risk of malignancy. At present, no single cytochemical or genetic marker can definitely rule out malignancy in indeterminate nodules. Nevertheless, these tools should be considered together with clinical data, US signs, elastographic pattern, or results of other imaging techniques to improve the management of these lesions. Most thyroid nodules do not require any treatment, and levothyroxine (LT4) suppressive therapy is not recommended. Percutaneous ethanol injection (PEI) should be the first-line treatment option for relapsing, benign cystic lesions, while US-guided thermal ablation treatments may be considered for solid or mixed symptomatic benign thyroid nodules. Surgery remains the treatment of choice for malignant or suspicious nodules. The present document updates previous guidelines released in 2006 and 2010 by the American Association of Clinical Endocrinologists (AACE), American College of Endocrinology (ACE) and Associazione Medici Endocrinologi (AME).

Evaluation of cytopathological findings in thyroid nodules with macrocalcification: macrocalcification is not innocent as it seems

Objective Microcalcification is strongly correlated with papillary thyroid cancer. It is not clear whether macrocalcification is associated with malignancy. In this study, we aimed to assess the result of fine needle aspiration biopsies (FNAB) of thyroid nodules with macrocalcifications. Subjects and methods We retrospectively evaluated 269 patients (907 nodules). Macrocalcifications were classified as eggshell and parenchymal macrocalcification. FNAB results were divided into four groups: benign, malignant, suspicious for malignancy, and non-diagnostic. Results There were 79.9% female and 20.1% male and mean age was 56.9 years. Macrocalcification was detected in 46.3% nodules and 53.7% nodules had no macrocalcification. Parenchymal and eggshell macrocalcification were observed in 40.5% and 5.8% nodules, respectively. Cytologically, malignant and suspicious for malignancy rates were higher in nodules with macrocalcification compared to nodules without macrocalcification (p = 0.004 and p = 0.003, respectively). Benign and non-diagnostic cytology results were similar in two groups (p > 0.05). Nodules with eggshell calcification had higher rate of suspicious for malignancy and nodules with parenchymal macrocalcification had higher rates of malignant and suspicious for malignancy compared to those without macrocalcification (p = 0.01, p = 0.003 and p = 0.007, respectively). Conclusions Our findings suggest that macrocalcifications are not always benign and are not associated with increased nondiagnostic FNAB results. Macrocalcification, particularly the parenchymal type should be taken into consideration. Arq Bras Endocrinol Metab. 2014;58(9):939-45

Diagnostic Value of Ultrasound-detected Calcification in Thyroid Nodules

Introduction: This study analyses the diagnostic value of ultrasonography (US) detection for calcification in thyroid nodules. Materials and Methods: We analysed the preoperative US findings and clinical characteristics of 577 malignant and 3434 benign thyroid patients who underwent surgery in our hospital. Results: The malignant rate in patients with microcalcification hyperechoic and tiny calcification foci ≤2 mm in diameter was significantly higher than the non-calcification and other calcification group (P <0.001). The malignant rate in single calcification nodule was significantly higher than that in multiple nodule group (P <0.01). Most of the patients (37/39) with lymph node calcification were malignant. The malignant rate of calcification and microcalcification was significantly higher in patients <45 years old than in older patients (P <0.05). Conclusion: Compared with other calcifications, microcalcification should be a better predictor of thyroid carcinoma. Malignancy should be highly suspected in patients with single calcification nodule, especially with lymph node calcification. Patients younger than 45 years of age with calcification or microcalcification have a greater risk for thyroid carcinoma. Key words: Age, Single nodule, Thyroid carcinoma, Ultrasonography

Correlation between Thyroid Nodule Calcification Morphology on Ultrasound and Thyroid Carcinoma

OBJECTIVE: This study investigated the detection of thyroid nodule calcifications on ultrasound and their relationship to thyroid carcinoma. METHODS: Microcalcifications (≤ 2 mm) and macrocalcifications (> 2 mm) on preoperative ultrasound examination of thyroid and lymph nodes were compared with postoperative pathological diagnoses in 4186 patients undergoing thyroid surgery. RESULTS: Higher incidences of micro- and macrocalcifications were found in patients with thyroid carcinoma than in those with benign disease. The incidence of malignant disease was significantly higher in patients with microcalcifications than those with macrocalcifications, suggesting that the presence of microcalcifications is a better predictor of malignant thyroid carcinoma than other calcification types. The specificity of microcalcifications for a diagnosis of malignant thyroid carcinoma was 96.5%. Microcalcifications were significantly more frequent in patients aged ≤ 45 years, but there was no difference between genders. The incidence of malignancy was significantly higher in patients with single nodule calcifications than in those with multiple nodule calcifications. Lymph node calcifications were seen in 12 patients, all of whom had papillary carcinoma. CONCLUSIONS: Thyroid microcalcifications are strongly associated with thyroid carcinoma, especially micropapillary carcinoma. When cervical lymph node calcification is present, immediate surgery is required.

Clinical value of using ultrasound to assess calcification patterns in thyroid nodules

BACKGROUND

Differentiating between benign and malignant thyroid nodules is important for providing appropriate treatment. In the present study we examined the clinical usefulness of ultrasound in examining calcification patterns in thyroid nodules, and thus predict malignancy.

METHODS

The records of 1,498 Chinese patients who underwent thyroidectomy for nodular thyroid disease were retrospectively examined. All patients underwent thyroid ultrasound within 1 month before surgery. Calcification patterns in thyroid nodules were examined, and tissue samples were analyzed to determine a pathological diagnosis. Calcifications were defined as macrocalcifications, microcalcifications, rim calcifications, or isolated calcifications.

RESULTS

A total of 2,122 thyroid nodules were examined, and 259 nodules (12.2%) were found to be malignant. Papillary carcinoma accounted for 85.3% of all malignancies. The majority of benign lesions were nodular goiters. Calcification was detected in 49.6% of malignant nodules and 15.7% of benign nodules. Microcalcifications were significantly more common in malignant nodules as compared to benign nodules (33.7 vs. 6.4%; P < 0.001). The sensitivity and specificity of microcalcifications for predicting malignancy were 33.7 and 93.6%, respectively, while the positive and negative likelihood ratios were 42.0 and 91.1%, respectively.

CONCLUSIONS

Calcifications, as detected by ultrasonography, are evident in benign and malignant thyroid nodules. Although microcalcifications are more common in malignant thyroid nodules than in benign ones, the clinical value of using the presence of microcalcifications alone for predicting malignancy is limited.

Symptomatic calcification of a thyroid lobe and surrounding tissue after radioactive iodine treatment to ablate the lobe

BACKGROUND

Fine-needle aspiration diagnosis of follicular carcinoma presents a dilemma because malignancy is confirmed when vascular or capsular invasion is present. Completion thyroidectomy may be necessary when the diagnosis of follicular carcinoma is made following hemithyroidectomy. Ablation of the remaining lobe with radioactive iodine has been used as an alternative to completion thyroidectomy. Here we report an unusual apparent complication of this treatment.

PATIENT FINDINGS

A 51-year-old woman presented in September 24, 2009 with a stony, hard calcification of left thyroid gland. She complained of recent progressive hoarsening of her voice. Her medical history was positive for a subtotal thyroidectomy on September 6, 1993. Histologic analysis identified follicular carcinoma. Two months postoperatively, the remaining tissue was ablated with (131)I (150 mCi) as an alternative to completion thyroidectomy. We performed computed tomography of the neck, which demonstrated 1.6  x 1.9 x  2.2 cm dense speculated calcification of the entire left residual thyroid gland. The calcification infiltrated the trachea wall. Completion thyroidectomy, including resection of the calcification, was performed. Histologic examination revealed dystrophic calcification.

CONCLUSION

We report an unusual replacement of the thyroid remnant with calcification that developed over a period of 16 years following radioactive iodine lobe ablation as an alternative to completion thyroidectomy for thyroid follicular carcinoma. To our knowledge, this is the first such case in the English language literature.

Role of duplex power Doppler ultrasound in differentiation between malignant and benign thyroid nodules

Objective

To evaluate the usage of duplex power Doppler ultrasound (PDUS) for the differentiation of benign and malignant thyroid nodules.

Materials and Methods

We prospectively examined 77 thyroid nodules in 60 patients undergoing ultrasound-guided fine needle aspiration biopsy (FNAB). Each nodule was described according to size, inner structure, borders, parenchymal echogenicity, peripheral halo formation, and the presence of calcification (B-mode ultrasound findings). Vascularity as determined by PDUS imaging was defined as non-vascular, peripheral, central, or of mixed type. For each nodule, the pulsatility index (PI) and resistive index (RI) values were obtained. Results of FNAB and surgical pathological examination (if available) were used as a proof of final diagnosis to categorize all nodules as benign or malignant. A receiver operating characteristic (ROC) curve analysis was performed to establish cut-off, sensitivity, and specificity values associated with RI-PI values.

Results

A significant relationship was observed between malignancy and irregular margins, microcalcifications, and hypoechogenicity on ultrasound examination (p < 0.05). The pattern of vascularity as determined by PDUS analysis was not a statistically significant criterion to suggest benign or malignant disease in this study (p > 0.05). The central, peripheral, and mean RI-PI values were higher in malignant nodules when compared to the other cytologies (p < 0.05).

Conclusion

Vascularity is not a useful parameter for distinguishing malignant from benign thyroid nodules. However, RI and PI values are useful in distinguishing malignant from benign thyroid nodules.

Ultrasonographic characteristics as a criterion for repeat cytology in benign thyroid nodules

OBJECTIVE: To report the results of repeat fine-needle aspiration cytology (FNAC) in thyroid nodules with an initial benign cytological diagnosis that grow during follow-up and/or present suspicious ultrasonographic characteristics. SUBJECTS AND METHODS: The sample consisted of 456 patients with 895 nodules. FNAC was repeated after 12 to 18 months in the case of nodules with suspicious ultrasonographic characteristics, irrespective of growth, and when the nodules showed significant growth. RESULTS: Among the 895 nodules examined, 102 (11.4%) presented suspicious ultrasonographic characteristics. The second FNAC revealed malignancy in 18 (17.6%) nodules, including 20% (2/10) of those showing growth and 17.4% (16/92) that did not. Seventy-six (9.6%) of 793 nodules without suspicious characteristics presented growth. Only one case (1.3%) of malignancy was diagnosed by repeat FNAC. CONCLUSIONS: The study suggests ultrasonographic characteristics rather than growth as a criterion for repeat FNAC in the case of nodules with an initial benign cytological diagnosis.