Factors associated with the sensitivity of fine-needle aspiration cytology for the diagnosis of follicular variant papillary thyroid carcinoma

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

Introduction. Thyroid cancer is one of the most common malignant neoplasms of the endocrine system. well-differentiated thyroid cancer constitutes about 90 % of all malignant tumors of the thyroid gland. Despite growing morbidity and high incidence of this pathology, in case of timely diagnosis and treatment well-differentiated thyroid cancer has favorable prognosis.

Aim. using clinical examples, to demonstrate the possibility of thyroglobulin measurement in needle washouts of fineneedle aspiration biopsy in the detection of cervical metastases of highly differentiated thyroid cancer.

Materials and methods. five patients (2 patients with combined oncological pathology, 2 patients with nodes in the thyroid gland, 1 patient after a thyroidectomy) with cervical adenopathy measured the level of thyroglobulin in the wash out fluid of lymph-nodes biopsy using the immunoradiometric method using the commercial kits of the Institute of Isotopes-IRmA (Hungary).

Results. Cervical metastases of highly differentiated thyroid cancer were detected or excluded by the determination of fine-needle aspiration biopsy in patients with non-informational cytological studies. The determination of fineneedle aspiration biopsy is a useful diagnostic method in the differential diagnosis of cervical metastases in patients who have other morphological forms of cancer in addition to well-differentiated thyroid cancer, as well as for the differential diagnosis of cervical adenopathy in patients with a history of highly differentiated thyroid cancer.

Conclusion. Determination of thyroglobulin level in puncture needle washout is a simple and useful diagnostic method for differential diagnosis of metastases in lymph nodes of the neck in patients with several morphological forms of malignant tumors.

Classic and Follicular Variant of Papillary Thyroid Microcarcinoma: 2 Different Phenotypes Beyond Tumor Size

Context

Despite the wide revision of current guidelines, the management of papillary thyroid microcarcinoma (mPTC) still has to be decided case by case. There is conflicting evidence about the role of more frequent histological subtypes, and no data about potential differences at presentation.

Objective

Our aim was to compare the phenotype of the 2 most frequent mPTC variants, namely, classical papillary thyroid microcarcinoma (mPTCc) and the follicular variant of papillary thyroid microcarcinoma (mFVPTC) .

Methods

Retrospective observational study, from January 2008 to December 2017 of a consecutive series of patients with mPTCc and mFVPTC. All cases were classified according to the 2015 American Thyroid Association (ATA) risk classification. Clinical and preclinical features of mPTCc and mFVPTC at diagnosis were collected. The comparison was also performed according to the incidental/nonincidental diagnosis and differences were verified by binary logistic analysis.

Results

In total, 235 patients were eligible for the analysis (125 and 110 mPTCc and mFVPTC, respectively). Compared with mPTCc, mFVPTCs were more often incidental and significantly smaller (4 vs 7 mm) (P < .001 all), possibly influenced by the higher rate of incidental detection. mFVPTC and incidental (P < .001 both) tumors were significantly more often allocated within the low-risk class. A logistic regression model, with ATA risk class as the dependent variable, showed that both mFVPTC (OR 0.465 [0.235-0.922]; P = .028]) and incidental diagnosis (OR 0.074 [0.036-0.163]; P < .001) independently predicted ATA risk stratification.

Conclusion

mFVPTC shows some differences in diagnostic presentation compared with mPTCc, and seems to retain a significant number of favorable features, including a prevalent onset as incidental diagnosis.

Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules

Fine needle aspiration (FNA) is the procedure of choice for evaluating thyroid nodules. It is indicated for nodules >2 cm, even in cases of very low suspicion of malignancy. FNA has associated risks and expenses. In this study, we developed an image analysis model using a deep learning algorithm and evaluated if the algorithm could predict thyroid nodules with benign FNA results.Ultrasonographic images of thyroid nodules with cytologic or histologic results were retrospectively collected. For algorithm training, 1358 (670 benign, 688 malignant) thyroid nodule images were input into the Inception-V3 network model. The model was pretrained to classify nodules as benign or malignant using the ImageNet database. The diagnostic performance of the algorithm was tested with the prospectively collected internal (n = 55) and external test sets (n = 100).For the internal test set, 20 of the 21 FNA malignant nodules were correctly classified as malignant by the algorithm (sensitivity, 95.2%); and of the 22 nodules algorithm classified as benign, 21 were FNA benign (negative predictive value [NPV], 95.5%). For the external test set, 47 of the 50 FNA malignant nodules were correctly classified by the algorithm (sensitivity, 94.0%); and of the 31 nodules the algorithm classified as benign, 28 were FNA benign (NPV, 90.3%).The sensitivity and NPV of the deep learning algorithm shown in this study are promising. Artificial intelligence may assist clinicians to recognize nodules that are likely to be benign and avoid unnecessary FNA.