Thyroid nodule surgery: predictive diagnostic value of fine-needle aspiration cytology and frozen section

The Use of Artificial Intelligence in the Diagnosis and Classification of Thyroid Nodules: An Update

The incidence of thyroid nodules diagnosed is increasing every year, leading to a greater risk of unnecessary procedures being performed or wrong diagnoses being made. In our paper, we present the latest knowledge on the use of artificial intelligence in diagnosing and classifying thyroid nodules. We particularly focus on the usefulness of artificial intelligence in ultrasonography for the diagnosis and characterization of pathology, as these are the two most developed fields. In our search of the latest innovations, we reviewed only the latest publications of specific types published from 2018 to 2022. We analyzed 930 papers in total, from which we selected 33 that were the most relevant to the topic of our work. In conclusion, there is great scope for the use of artificial intelligence in future thyroid nodule classification and diagnosis. In addition to the most typical uses of artificial intelligence in cancer differentiation, we identified several other novel applications of artificial intelligence during our review.

Features and diagnostic accuracy of fine needle aspiration cytology of thyroid nodules: retrospective study from Oman

BACKGROUND

Fine needle aspiration cytology (FNAC) of the thyroid has been a reliable and cost-effective method for diagnosing thyroid disorders. Since FNAC results are usually operator dependent, there is a compelling need to explore FNAC accuracy among Omanis.

OBJECTIVE

Describe cytological features of FNAC and assess FNAC accuracy compared to the postsurgical histopathology report.

DESIGN

Retrospective diagnostic accuracy study SETTING: Tertiary care center.

PATIENTS AND METHODS

Our study included adult Omani adult patients with thyroid nodules who underwent FNAC from 2014 to 2017 and had final pathology results for patients who underwent thyroid surgery. The results were classified according to the UK Royal college of Pathologists 'Thy' categories. Accuracy of FNAC was calculated by determining false and true positive and negative results based on histopathology findings.

MAIN OUTCOME MEASURES

FNAC accuracy (sensitivity and specificity) compared to the postsurgical histopathology.

SAMPLE SIZE

867 patients with 1359 ultrasound guided FNACs of thyroid nodule; 137 underwent surgery.

RESULTS

The mean age of the 867 patients was 43.7 (13.3) years, with a median of 42 years, and 87.8% were females. Out of 1359 FNACs, 1001 (73.7%) were benign (Thy2), 119 (8.8%) were atypia of undetermined significance or follicular lesion of undetermined significance (Thy3a), 31 (2.3%) were follicular neoplasm or suspicious for a follicular neoplasm (Thy3f), 52 (3.8%) were suspicious for malignancy (Thy4), 55 (4%) were malignant (Thy5), 101 (7.4%) as Unsatisfactory (Thy1). Only 137 patients underwent thyroid surgery, and the FNAC reports were compared with their final histopathology reports. The sensitivity, specificity and total accuracy of FNAC were 80.2%, 98.9% and 89.9%, respectively. The positive and negative predictive values of FNAC were 98.6% and 84.3%, respectively.

CONCLUSION

Our study findings confirmed that FNAC of the thyroid is a sensitive, specific, and accurate initial tool for the diagnosis of thyroid lesions. Most of the FNACs were benign with a very low malignancy rate. Due to the minimal chance of false negative results and the slow-growing nature of thyroid malignancy, it is important that patients with benign FNAC should have periodic clinical and radiological follow-up.

LIMITATIONS

Retrospective design and single-center study, and thyroid nodule size unavailable.

CONFLICT OF INTEREST

None.

Intraoperative frozen section performance for thyroid cancer diagnosis

Objective

A primary medical relevance of thyroid nodules consists of excluding thyroid cancer, present in approximately 5% of all thyroid nodules. Fine-needle aspiration biopsy (FNAB) has a paramount role in distinguishing benign from malignant thyroid nodules due to its availability and diagnostic performance. Nevertheless, intraoperative frozen section (iFS) is still advocated as a valuable tool for surgery planning, especially for indeterminate nodules.

Methods

To compare the FNAB and iFS performances in thyroid cancer diagnosis among nodules in Bethesda Categories (BC) I to VI. The performance of FNAB and iFS tests were calculated using final histopathology results as the gold standard.

Results

In total, 316 patients were included in the analysis. Both FNAB and iFS data were available for 272 patients (86.1%). The overall malignancy rate was 30.4%% (n = 96). The FNAB sensitivity, specificity, and accuracy for benign (BC II) and malignant (BC V and VI) were 89.5%, 97.1%, and 94.1%, respectively. For all nodules evaluated, the iFS sensitivity, specificity, and accuracy were 80.9%, 100%, and 94.9%, respectively. For indeterminate nodules and follicular lesions (BC III and IV), the iFS sensitivity, specificity, and accuracy were 25%, 100%, and 88.7%, respectively. For BC I nodules, iFS had 95.2% of accuracy.

Conclusion

Our results do not support routine iFS for indeterminate nodules or follicular neoplasms (BC III and IV) due to its low sensitivity. In these categories, iFS is not sufficiently accurate to guide the intraoperative management of thyroidectomies. iFS for BC I nodules could be an option and should be specifically investigated.

Identification of Tissue-Specific DNA Methylation Signatures for Thyroid Nodule Diagnostics

PURPOSE

Thyroid cancer is frequently difficult to diagnose due to an overlap of cytologic features between malignant and benign nodules. This overlap leads to unnecessary removal of the thyroid in patients without cancer. While providing some improvement over cytopathologic diagnostics, molecular methods frequently fail to provide a correct diagnosis for thyroid nodules. These approaches are based on the difference between cancer and adjacent thyroid tissue and assume that adjacent tissues are the same as benign nodules. However, in contrast to adjacent tissues, benign thyroid nodules can contain genetic alterations that can be found in cancer.Experimental Design: For the development of a new molecular diagnostic test for thyroid cancer, we evaluated DNA methylation in 109 thyroid tissues by using genome-wide single-base resolution DNA methylation analysis. The test was validated in a retrospective cohort containing 65 thyroid nodules.

RESULTS

By conducting reduced representation bisulfite sequencing in 109 thyroid specimens, we found significant differences between adjacent tissue, benign nodules, and cancer. These tissue-specific signatures are strongly linked to active enhancers and cancer-associated genes. Based on these signatures, we developed a new epigenetic approach for thyroid diagnostics. According to the validation cohort, our test has an estimated specificity of 97% [95% confidence interval (CI), 81-100], sensitivity of 100% (95% CI, 87-100), positive predictive value of 97% (95% CI, 83-100), and negative predictive value of 100% (95% CI, 86-100).

CONCLUSIONS

These data show that epigenetic testing can provide outstanding diagnostic accuracy for thyroid nodules.See related commentary by Mitmaker et al., p. 457.

Intraoperative measurement of thyroglobulin in lymph node aspirates for the detection of metastatic papillary thyroid carcinoma

BACKGROUND

Among patients with papillary thyroid carcinoma (PTC), 30%-80% have cervical lymph node (LN) metastases, which are most commonly located in the central compartment. However, preoperative ultrasonography identifies malignant central compartment LNs in only 20%-30% of cases. We aimed to evaluate the diagnostic value of intraoperative thyroglobulin (Tg) measurement in fine-needle aspirates (FNA-Tg) of suspicious metastatic LNs.

METHODS

In total, 75 patients (75 LNs) with PTC or suspected PTC were enrolled in this study. Suspicious metastatic LNs were isolated intraoperatively, and FNA-Tg was performed. Then, the Tg values were compared with the corresponding pathological results and preoperative ultrasonography.

RESULTS

In total, 37 LNs were diagnosed as malignant, and 38 were benign. According to the receiver operating characteristic (ROC) curve, the optimal cutoff value of intraoperative FNA-Tg was 147.5 ng/mL (sensitivity, 81.1%; specificity, 100%; p=0.000). The sensitivity and specificity for detecting central compartment LN metastasis were 77.78% (21/27) and 100% (36/36), respectively. The corresponding sensitivity of preoperative ultrasonography was lower than that of FNA-Tg (p=0.000). Serum Tg-antibody (Ab), thyroid-stimulating hormone (TSH) and thyroid peroxidase antibody (TPO-Ab) were not significantly associated with FNA-Tg values. There was no statistical correlation between preoperative serum Tg and intraoperative FNA-Tg (p=0.451).

CONCLUSION

Intraoperative FNA-Tg levels of suspicious metastatic cervical LNs can be useful for diagnosing metastatic PTC. Intraoperative LN-FNA-Tg may have an important role in determining which surgical procedure to perform.

Retrospective evaluation of frozen section use for thyroid nodules with a prior fine needle aspiration diagnosis of Bethesda II-VI: The Weill Cornell Medical College experience

Objective

To evaluate the Weill Cornell Medical College (WCMC)/New York Presbyterian Hospital (NYPH) experience with intraoperative frozen (IOF) section in the management of thyroid nodules with a fine needle aspiration (FNA) diagnosis of Bethesda II–VI and to analyze the cost and pathology benefit it provides.

Methods

The surgical and cytopathology files at WCMC/NYPH were searched within the time period of January 2008 to May 2013. A total of 435 thyroid specimens were identified for which both an FNA and subsequent IOF section was performed. The FNA was correlated with the locations of the resected nodule and the nodule frozen for intraoperative diagnosis. The results of the FNA were compared to the IOF section diagnosis and final diagnosis (FD).

Results

Among 435 cases, the FNA diagnosis was Bethesda II: 149 cases, Bethesda III: 170 cases, Bethesda IV: 91 cases, Bethesda V: 19 cases, and Bethesda VI: 6 cases. There were a total of 83 carcinomas identified on FD, which included 69 papillary thyroid carcinomas (PTCs), 12 follicular carcinomas, and 2 poorly differentiated carcinomas. The preoperative FNA diagnosis for these carcinomas was as follows: Bethesda II, 11/149 (7.4%), Bethesda III, 24/170 (14%), Bethesda IV, 26/91 (29%), Bethesda V, 16/19 (84%), and Bethesda VI, 6/6 (100%). IOF section contributed to the diagnosis of malignancy in 16/429 (4%) cases: 1/149 (0.7%) Bethesda II, 5/170 (3%) Bethesda III, 2/91 (1.1%) Bethesda IV, and 8/19 (42%) Bethesda V. The diagnosis of malignancy was confirmed in the 6 Bethesda VI cases by IOF section. There were no false positives on IOF section. IOF had a sensitivity and specificity of 26% and 100%, respectively.

Conclusion

The role of IOF section is limited in the evaluation of thyroid nodules. IOF section is most useful for nodules with an FNA diagnosis of Bethesda V lesions. The diagnosis of follicular variant of PTC remains difficult on frozen section.